MF研究者総覧

Researcher Database

Advance
Researchers' Page on researchmap
Last Updated :2024/10/10

Researcher Profile and Settings

Master

Affiliation (Master)

  • Faculty of Health Sciences　Health Sciences　Biomedical Science and Engineering

Affiliation (Master)

  • Faculty of Health Sciences　Health Sciences　Biomedical Science and Engineering

researchmap

Profile and Settings

Degree

  • Ph.D（Hokkaido University）

Profile and Settings

  • Name (Japanese)

    Sugimori

  • Name (Kana)

    Hiroyuki

  • Name

    L-9724-2019, 201301088448768061

Alternate Names

Achievement

Research Interests

  • medical AI   Medical image analysis   Artificial Intelligence   magnetic resonance imaging   

Research Areas

  • Life sciences / Medical systems
  • Life sciences / Radiology

Research Experience

  • 2022/04 - Today 北海道大学医学研究院医理工学グローバルセンター 画像診断部門 画像医理工学セクション 連携研究員
  • 2019/04 - Today Hokkaido university Faculty of Health Sciences Associate Professor
  • 2016/07 - Today Hokkaido University Research and Education Center for Brain Science Staff
  • 2016/04 - 2019/03 Hokkaido university Faculty of Health Sciences Lecturer
  • 2013/04 - 2016/03 Hokkaido University Department of Health Sciences Lecturer (part-time)
  • 2013/04 - 2016/03 Faculty of health sciences, hokkaido university Visiting researcher
  • 2013/04 - 2016/03 Hokkaido university hospital Department of radiological technology Chief radiological technologist
  • 2009/04 - 2013/03 Hokkaido university hospital Department of radiological technology Radiological technologist
  • 1999/04 - 2009/03 Asahikawa medical college hospital Department of radiological technology Radiological technologist

Education

  • 2010/04 - 2013/03  Hokkaido University  Graduate School of Health Sciences
  • 2008/04 - 2010/03  The Open University of Japan  School of Graduate Studies Graduate School of Arts and Sciences
  • 1996/04 - 1999/03  北海道大学医療技術短期大学部
  •        - 1996/03  北海道富良野高等学校

Published Papers

  • Yanjun Li, Takaaki Yoshimura, Yuto Horima, Hiroyuki Sugimori
    Electronics 2024/09 [Refereed]
  • Yuya Hirano, Kinya Ishizaka, Hiroyuki Sugimori, Yo Taniguchi, Tomoki Amemiya, Yoshitaka Bito, Kohsuke Kudo
    Radiological Physics and Technology 1865-0333 2024/08/28 [Refereed]
     
    Abstract We aimed to evaluate the accuracy and repeatability of the T1, T2*, and proton density (PD) values obtained by quantitative parameter mapping (QPM) using the ISMRM/NIST MRI system phantom and compared them with computer simulations. We compared the relaxation times and PD obtained through QPM with the reference values of the ISMRM/NIST MRI system phantom and conventional methods. Furthermore, we evaluated the presence or absence of influences other than noise in T1 and T2* values obtained by QPM by comparing the obtained coefficient of variation (CV) with simulation results. The T1, T2*, and PD values by QPM showed a strong correlation with the measured values and the referenced values. The simulated CVs of QPM calculated for each sphere showed similar trends to those of the actual scans.
  • Taku Sugiyama, Hiroyuki Sugimori, Mighui Tang, Miki Fujimura
    JMA Journal 2024/08 [Refereed]
  • Miu Sakaida, Takaaki Yoshimura, Minghui Tang, Shota Ichikawa, Hiroyuki Sugimori, Kenji Hirata, Kohsuke Kudo
    Applied Sciences 14 (14) 5968 - 5968 2024/07/09 [Refereed]
     
    Identifying calcifications in mammograms is crucial for early breast cancer detection, and semi-supervised learning, which utilizes a small dataset for supervised learning combined with deep learning, is anticipated to be an effective approach for automating this identification process. This study explored the impact of semi-supervised learning on identifying mammographic calcifications by including 712 mammographic images from 252 patients in public datasets. Initially, 212 mammogram images were segmented into patches and classified visually for calcification presence. A subset of these patches, derived from 169 mammogram images, was used to train a ResNet50-based classifier. The classifier was evaluated using patches generated from 43 mammograms as a test data set. Additionally, 500 more mammogram images were processed into patches and analyzed using the trained ResNet50 model, with semi-supervised learning applied to patches exceeding certain classification probabilities. This process aimed to enhance the classifier’s accuracy and achieve improvements over the initial model. The findings indicated that semi-supervised learning significantly benefits the accuracy of calcification detection in mammography, underscoring its utility in enhancing diagnostic methodologies.
  • Shota Ichikawa, Makoto Ozaki, Hideki Itadani, Hiroyuki Sugimori, Yohan Kondo
    Radiological physics and technology 2024/06/11 [Refereed]
     
    Cerebral computed tomography perfusion (CTP) imaging requires complete acquisition of contrast bolus inflow and washout in the brain parenchyma; however, time truncation undoubtedly occurs in clinical practice. To overcome this issue, we proposed a three-dimensional (two-dimensional + time) convolutional neural network (CNN)-based approach to predict missing CTP image frames at the end of the series from earlier acquired image frames. Moreover, we evaluated three strategies for predicting multiple time points. Seventy-two CTP scans with 89 frames and eight slices from a publicly available dataset were used to train and test the CNN models capable of predicting the last 10 image frames. The prediction strategies were single-shot prediction, recursive multi-step prediction, and direct-recursive hybrid prediction.Single-shot prediction predicted all frames simultaneously, while recursive multi-step prediction used prior predictions as input for subsequent steps, and direct-recursive hybrid prediction employed separate models for each step with prior predictions as input for the next step. The accuracies of the predicted image frames were evaluated in terms of image quality, bolus shape, and clinical perfusion parameters. We found that the image quality metrics were superior when multiple CTP images were predicted simultaneously rather than recursively. The bolus shape also showed the highest correlation (r = 0.990, p < 0.001) and the lowest variance (95% confidence interval, -453.26-445.53) in the single-shot prediction. For all perfusion parameters, the single-shot prediction had the smallest absolute differences from ground truth. Our proposed approach can potentially minimize time truncation errors and support the accurate quantification of ischemic stroke.
  • Yijun Mao, Kiko Imahori, Wanxuan Fang, Hiroyuki Sugimori, Shinji Kiuch, Kenneth Sutherland, Tamotsu Kamishima
    Journal of magnetic resonance imaging : JMRI 2024/05/28 [Refereed]
     
    BACKGROUND: Challenges persist in achieving automatic and efficient inflammation quantification using dynamic contrast-enhanced (DCE) MRI in rheumatoid arthritis (RA) patients. PURPOSE: To investigate an automatic artificial intelligence (AI) approach and an optimized dynamic MRI protocol for quantifying disease activity in RA in whole hands while excluding arterial pixels. STUDY TYPE: Retrospective. SUBJECTS: Twelve RA patients underwent DCE-MRI with 27 phases for creating the AI model and tested on images with a variable number of phases from 35 RA patients. FIELD STRENGTH/SEQUENCE: 3.0 T/DCE T1-weighted gradient echo sequence (mDixon, water image). ASSESSMENT: The model was trained with various DCE-MRI time-intensity number of phases. Evaluations were conducted for similarity between AI segmentation and manual outlining in 51 ROIs with synovitis. The relationship between synovial volume via AI segmentation with rheumatoid arthritis magnetic resonance imaging scoring (RAMRIS) across whole hands was then evaluated. The reference standard was determined by an experienced musculoskeletal radiologist. STATISTICAL TEST: Area under the curve (AUC) of receiver operating characteristic (ROC), Dice and Spearman's rank correlation coefficients, and interclass correlation coefficient (ICC). A P-value <0.05 was considered statistically significant. RESULTS: A minimum of 15 phases (acquisition time at least 2.5 minutes) was found to be necessary. AUC ranged from 0.941 ± 0.009 to 0.965 ± 0.009. The Dice score was 0.557-0.615. Spearman's correlation coefficients between the AI model and ground truth were 0.884-0.927 and 0.736-0.831, for joint ROIs and whole hands, respectively. The Spearman's correlation coefficient for the additional test set between the model trained with 15 phases and RAMRIS was 0.768. CONCLUSION: The AI-based classification model effectively identified synovitis pixels while excluding arteries. The optimal performance was achieved with at least 15 phases, providing a quantitative assessment of inflammatory activity in RA while minimizing acquisition time. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.
  • Wanxuan Fang, Yijun Mao, Haolin Wang, Hiroyuki Sugimori, Shinji Kiuch, Kenneth Sutherland, Tamotsu Kamishima
    Japanese journal of radiology 2024/05/24 [Refereed]
     
    PURPOSE: A classification-based segmentation method is proposed to quantify synovium in rheumatoid arthritis (RA) patients using a deep learning (DL) method based on time-intensity curve (TIC) analysis in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). MATERIALS AND METHODS: This retrospective study analyzed a hand MR dataset of 28 RA patients (six males, mean age 53.7 years). A researcher, under expert guidance, used in-house software to delineate regions of interest (ROIs) for hand muscles, bones, and synovitis, generating a dataset with 27,255 pixels with corresponding TICs (muscle: 11,413, bone: 8502, synovitis: 7340). One experienced musculoskeletal radiologist performed ground truth segmentation of enhanced pannus in the joint bounding box on the 10th DCE phase, or around 5 min after contrast injection. Data preprocessing included median filtering for noise reduction, phase-only correlation algorithm for motion correction, and contrast-limited adaptive histogram equalization for improved image contrast and noise suppression. TIC intensity values were normalized using zero-mean normalization. A DL model with dilated causal convolution and SELU activation function was developed for enhanced pannus segmentation, tested using leave-one-out cross-validation. RESULTS: 407 joint bounding boxes were manually segmented, with 129 synovitis masks. On the pixel-based level, the DL model achieved sensitivity of 85%, specificity of 98%, accuracy of 99% and precision of 84% for enhanced pannus segmentation, with a mean Dice score of 0.73. The false-positive rate for predicting cases without synovitis was 0.8%. DL-measured enhanced pannus volume strongly correlated with ground truth at both pixel-based (r = 0.87, p < 0.001) and patient-based levels (r = 0.84, p < 0.001). Bland-Altman analysis showed the mean difference for hand joints at the pixel-based and patient-based levels were -9.46 mm3 and -50.87 mm3, respectively. CONCLUSION: Our DL-based DCE-MRI TIC shape analysis has the potential for automatic segmentation and quantification of enhanced synovium in the hands of RA patients.
  • Minghui Tang, Taku Sugiyama, Ren Takahari, Hiroyuki Sugimori, Takaaki Yoshimura, Katsuhiko Ogasawara, Kohsuke Kudo, Miki Fujimura
    Neurosurgical review 47 (1) 200 - 200 2024/05/09 [Refereed]
     
    Appropriate needle manipulation to avoid abrupt deformation of fragile vessels is a critical determinant of the success of microvascular anastomosis. However, no study has yet evaluated the area changes in surgical objects using surgical videos. The present study therefore aimed to develop a deep learning-based semantic segmentation algorithm to assess the area change of vessels during microvascular anastomosis for objective surgical skill assessment with regard to the "respect for tissue." The semantic segmentation algorithm was trained based on a ResNet-50 network using microvascular end-to-side anastomosis training videos with artificial blood vessels. Using the created model, video parameters during a single stitch completion task, including the coefficient of variation of vessel area (CV-VA), relative change in vessel area per unit time (ΔVA), and the number of tissue deformation errors (TDE), as defined by a ΔVA threshold, were compared between expert and novice surgeons. A high validation accuracy (99.1%) and Intersection over Union (0.93) were obtained for the auto-segmentation model. During the single-stitch task, the expert surgeons displayed lower values of CV-VA (p < 0.05) and ΔVA (p < 0.05). Additionally, experts committed significantly fewer TDEs than novices (p < 0.05), and completed the task in a shorter time (p < 0.01). Receiver operating curve analyses indicated relatively strong discriminative capabilities for each video parameter and task completion time, while the combined use of the task completion time and video parameters demonstrated complete discriminative power between experts and novices. In conclusion, the assessment of changes in the vessel area during microvascular anastomosis using a deep learning-based semantic segmentation algorithm is presented as a novel concept for evaluating microsurgical performance. This will be useful in future computer-aided devices to enhance surgical education and patient safety.
  • Ryuma Moriya, Takaaki Yoshimura, Minghui Tang, Shota Ichikawa, Hiroyuki Sugimori
    Applied Sciences 14 (9) 3794 - 3794 2024/04/29 [Refereed]
     
    Background and Objectives: In lumbar spine radiography, the oblique view is frequently utilized to assess the presence of spondylolysis and the morphology of facet joints. It is crucial to instantly determine whether the oblique angle is appropriate for the evaluation and the necessity of retakes after imaging. This study investigates the feasibility of using a convolutional neural network (CNN) to estimate the angle of lumbar oblique images. Since there are no existing lumbar oblique images with known angles, we aimed to generate synthetic lumbar X-ray images at arbitrary angles from computed tomography (CT) images and to estimate the angles of these images using a trained CNN. Methods: Synthetic lumbar spine X-ray images were created from CT images of 174 individuals by rotating the lumbar spine from 0° to 60° in 5° increments. A line connecting the center of the spinal canal and the spinous process was used as the baseline to define the shooting angle of the synthetic X-ray images based on how much they were tilted from the baseline. These images were divided into five subsets and trained using ResNet50, a CNN for image classification, implementing 5-fold cross-validation. The models were trained for angle estimation regression and image classification into 13 classes at 5° increments from 0° to 60°. For model evaluation, mean squared error (MSE), root mean squared error (RMSE), and the correlation coefficient (r) were calculated for regression analysis, and the area under the curve (AUC) was calculated for classification. Results: In the regression analysis for angles from 0° to 60°, the MSE was 14.833 degree2, the RMSE was 3.820 degrees, and r was 0.981. The average AUC for the 13-class classification was 0.953. Conclusion: The CNN developed in this study was able to estimate the angle of an lumbar oblique image with high accuracy, suggesting its usefulness.
  • Michito Murayama, Hiroyuki Sugimori, Takaaki Yoshimura, Sanae Kaga, Hideki Shima, Satonori Tsuneta, Aoi Mukai, Yui Nagai, Shinobu Yokoyama, Hisao Nishino, Junichi Nakamura, Takahiro Sato, Ichizo Tsujino
    Echocardiography (Mount Kisco, N.Y.) 41 (4) e15812  2024/04 [Refereed]
     
    BACKGROUND: Precapillary pulmonary hypertension (PH) is characterized by a sustained increase in right ventricular (RV) afterload, impairing systolic function. Two-dimensional (2D) echocardiography is the most performed cardiac imaging tool to assess RV systolic function; however, an accurate evaluation requires expertise. We aimed to develop a fully automated deep learning (DL)-based tool to estimate the RV ejection fraction (RVEF) from 2D echocardiographic videos of apical four-chamber views in patients with precapillary PH. METHODS: We identified 85 patients with suspected precapillary PH who underwent cardiac magnetic resonance imaging (MRI) and echocardiography. The data was divided into training (80%) and testing (20%) datasets, and a regression model was constructed using 3D-ResNet50. Accuracy was assessed using five-fold cross validation. RESULTS: The DL model predicted the cardiac MRI-derived RVEF with a mean absolute error of 7.67%. The DL model identified severe RV systolic dysfunction (defined as cardiac MRI-derived RVEF < 37%) with an area under the curve (AUC) of .84, which was comparable to the AUC of RV fractional area change (FAC) and tricuspid annular plane systolic excursion (TAPSE) measured by experienced sonographers (.87 and .72, respectively). To detect mild RV systolic dysfunction (defined as RVEF ≤ 45%), the AUC from the DL-predicted RVEF also demonstrated a high discriminatory power of .87, comparable to that of FAC (.90), and significantly higher than that of TAPSE (.67). CONCLUSION: The fully automated DL-based tool using 2D echocardiography could accurately estimate RVEF and exhibited a diagnostic performance for RV systolic dysfunction comparable to that of human readers.
  • Hiroyuki Kameda, Yumi Nakada, Yuta Urushibata, Hiroyuki Sugimori, Takaaki Fujii, Naoya Kinota, Daisuke Kato, Minghui Tang, Keita Sakamoto, Kohsuke Kudo
    Magnetic resonance in medical sciences : MRMS : an official journal of Japan Society of Magnetic Resonance in Medicine 2024/03/15 [Refereed]
     
    17O-labeled water is a T2-shortening contrast agent used in proton MRI and is a promising method for visualizing cerebrospinal fluid (CSF) dynamics because it provides long-term tracking of water molecules. However, various external factors reduce the accuracy of 17O-concentration measurements using conventional signal-intensity-based methods. In addition, T2 mapping, which is expected to provide a stable assessment, is generally limited to temporal-spatial resolution. We developed the T2-prepared based on T2 mapping used in cardiac imaging to adapt to long T2 values and tested whether it could accurately measure 17O-concentration in the CSF using a phantom. The results showed that 17O-concentration in a fluid mimicking CSF could be evaluated with an accuracy comparable to conventional T2-mapping (Carr-Purcell-Meiboom-Gill multi-echo spin-echo method). This method allows 17O-imaging with a high temporal resolution and stability in proton MRI. This imaging technique may be promising for visualizing CSF dynamics using 17O-labeled water.
  • Yanjun Li, Takaaki Yoshimura, Yuto Horima, Hiroyuki Sugimori
    Algorithms 17 (3) 119 - 119 2024/03/13 [Refereed]
     
    The detection of coronary artery stenosis is one of the most important indicators for the diagnosis of coronary artery disease. However, stenosis in branch vessels is often difficult to detect using computer-aided systems and even radiologists because of several factors, such as imaging angle and contrast agent inhomogeneity. Traditional coronary artery stenosis localization algorithms often only detect aortic stenosis and ignore branch vessels that may also cause major health threats. Therefore, improving the localization of branch vessel stenosis in coronary angiographic images is a potential development property. In this study, we propose a preprocessing approach that combines vessel enhancement and image fusion as a prerequisite for deep learning. The sensitivity of the neural network to stenosis features is improved by enhancing the blurry features in coronary angiographic images. By validating five neural networks, such as YOLOv4 and R-FCN-Inceptionresnetv2, our proposed method can improve the performance of deep learning network applications on the images from six common imaging angles. The results showed that the proposed method is suitable as a preprocessing method for coronary angiographic image processing based on deep learning and can be used to amend the recognition ability of the deep model for fine vessel stenosis.
  • Shota Ichikawa, Hiroyuki Sugimori
    Journal of computer assisted tomography 2024/02/27 [Refereed]
     
    OBJECTIVE: This study aimed to evaluate the correlation between the estimated body weight obtained from 2 easy-to-perform methods and the actual body weight at different computed tomography (CT) levels and determine the best reference site for estimating body weight. METHODS: A total of 862 patients from a public database of whole-body positron emission tomography/CT studies were retrospectively analyzed. Two methods for estimating body weight at 10 single-slice CT levels were evaluated: a linear regression model using total cross-sectional body area and a deep learning-based model. The accuracy of body weight estimation was evaluated using the mean absolute error (MAE), root mean square error (RMSE), and Spearman rank correlation coefficient (ρ). RESULTS: In the linear regression models, the estimated body weight at the T5 level correlated best with the actual body weight (MAE, 5.39 kg; RMSE, 7.01 kg; ρ = 0.912). The deep learning-based models showed the best accuracy at the L5 level (MAE, 6.72 kg; RMSE, 8.82 kg; ρ = 0.865). CONCLUSIONS: Although both methods were feasible for estimating body weight at different single-slice CT levels, the linear regression model using total cross-sectional body area at the T5 level as an input variable was the most favorable method for single-slice CT analysis for estimating body weight.
  • Taku Sugiyama, Hiroyuki Sugimori, Minghui Tang, Yasuhiro Ito, Masayuki Gekka, Haruto Uchino, Masaki Ito, Katsuhiko Ogasawara, Miki Fujimura
    Acta neurochirurgica 166 (1) 6 - 6 2024/01/12 [Refereed]
     
    PURPOSE: Attaining sufficient microsurgical skills is paramount for neurosurgical trainees. Kinematic analysis of surgical instruments using video offers the potential for an objective assessment of microsurgical proficiency, thereby enhancing surgical training and patient safety. The purposes of this study were to develop a deep-learning-based automated instrument tip-detection algorithm, and to validate its performance in microvascular anastomosis training. METHODS: An automated instrument tip-tracking algorithm was developed and trained using YOLOv2, based on clinical microsurgical videos and microvascular anastomosis practice videos. With this model, we measured motion economy (procedural time and path distance) and motion smoothness (normalized jerk index) during the task of suturing artificial blood vessels for end-to-side anastomosis. These parameters were validated using traditional criteria-based rating scales and were compared across surgeons with varying microsurgical experience (novice, intermediate, and expert). The suturing task was deconstructed into four distinct phases, and parameters within each phase were compared between novice and expert surgeons. RESULTS: The high accuracy of the developed model was indicated by a mean Dice similarity coefficient of 0.87. Deep learning-based parameters (procedural time, path distance, and normalized jerk index) exhibited correlations with traditional criteria-based rating scales and surgeons' years of experience. Experts completed the suturing task faster than novices. The total path distance for the right (dominant) side instrument movement was shorter for experts compared to novices. However, for the left (non-dominant) side, differences between the two groups were observed only in specific phases. The normalized jerk index for both the right and left sides was significantly lower in the expert than in the novice groups, and receiver operating characteristic analysis showed strong discriminative ability. CONCLUSION: The deep learning-based kinematic analytic approach for surgical instruments proves beneficial in assessing performance in microvascular anastomosis. Moreover, this methodology can be adapted for use in clinical settings.
  • Hiroyuki Kameda, Naoya Kinota, Daisuke Kato, Takaaki Fujii, Taisuke Harada, Yuji Komaki, Hiroyuki Sugimori, Tomohiro Onodera, Moyoko Tomiyasu, Takayuki Obata, Kohsuke Kudo
    Investigative radiology 59 (1) 92 - 103 2024/01/01 [Refereed]
     
    Magnetic resonance imaging (MRI) is a crucial imaging technique for visualizing water in living organisms. Besides proton MRI, which is widely available and enables direct visualization of intrinsic water distribution and dynamics in various environments, MR-WTI (MR water tracer imaging) using 17 O-labeled water has been developed, benefiting from the many advancements in MRI software and hardware that have substantially improved the signal-to-noise ratio and made possible faster imaging. This cutting-edge technique allows the generation of novel and valuable images for clinical use. This review elucidates the studies related to MRI water tracer techniques centered around 17 O-labeled water, explaining the fundamental principles of imaging and providing clinical application examples. Anticipating continued progress in studies involving isotope-labeled water, this review is expected to contribute to elucidating the pathophysiology of various diseases related to water dynamics abnormalities and establishing novel imaging diagnostic methods for associated diseases.
  • Joma Oikawa, Jun Sakai, Yusuke Fujiwara, Kota Tsurusawa, Daisuke Shimao, Hiroyuki Date, Hiroyuki Sugimori
    Radiation protection dosimetry 2023/11/30 [Refereed]
     
    With the increase of the number of interventional radiology (IVR) procedures, the occupational exposure of operators and medical staff has attracted keen attention. The energy of scattered radiation in medical clinical sites is important for estimating the biological effects of occupational exposure. Recent years have seen many reports on the dose of scattered radiation by IVR, but few on the energy spectrum. In this study, the energy spectrum of scattered X-rays was measured by using a cadmium telluride (CdTe) semiconductor detector during IVR on several neurosurgical and cardiovascular cases. The cumulated spectra in each case were compared. The spectra showed little changes among neurosurgical cases and relatively large changes among cardiovascular cases. This was assumed to be due to the change of X-ray tube voltage and tube angle was larger in cardiovascular cases. The resulting energy spectra will be essential for the assessment of detailed biological effects of occupational exposure.
  • Daisuke Oura, Masayuki Gekka, Hiroyuki Sugimori
    Radiological physics and technology 2023/11/07 [Refereed]
     
    This study investigated the usefulness of the montage method that combines four different magnetic resonance images into one images for automatic acute ischemic stroke (AIS) diagnosis with deep learning method. The montage image was consisted from diffusion weighted image (DWI), fluid attenuated inversion recovery (FLAIR), arterial spin labeling (ASL), and apparent diffusion coefficient (ASL). The montage method was compared with pseudo color map (pCM) which was consisted from FLAIR, ASL and ADC. 473 AIS patients were classified into four categories: mechanical thrombectomy, conservative therapy, hemorrhage, and other diseases. The results showed that the montage image significantly outperformed pCM in terms of accuracy (montage image = 0.76 ± 0.01, pCM = 0.54 ± 0.05) and the area under the curve (AUC) (montage image = 0.94 ± 0.01, pCM = 0.76 ± 0.01). This study demonstrates the usefulness of the montage method and its potential for overcoming the limitations of pCM.
  • Miu Sakaida, Takaaki Yoshimura, Minghui Tang, Shota Ichikawa, Hiroyuki Sugimori
    Algorithms 16 (10) 483 - 483 2023/10/18 [Refereed]
     
    Convolutional neural networks (CNNs) in deep learning have input pixel limitations, which leads to lost information regarding microcalcification when mammography images are compressed. Segmenting images into patches retains the original resolution when inputting them into the CNN and allows for identifying the location of calcification. This study aimed to develop a mammographic calcification detection method using deep learning by classifying the presence of calcification in the breast. Using publicly available data, 212 mammograms from 81 women were segmented into 224 × 224-pixel patches, producing 15,049 patches. These were visually classified for calcification and divided into five subsets for training and evaluation using fivefold cross-validation, ensuring image consistency. ResNet18, ResNet50, and ResNet101 were used for training, each of which created a two-class calcification classifier. The ResNet18 classifier achieved an overall accuracy of 96.0%, mammogram accuracy of 95.8%, an area under the curve (AUC) of 0.96, and a processing time of 0.07 s. The results of ResNet50 indicated 96.4% overall accuracy, 96.3% mammogram accuracy, an AUC of 0.96, and a processing time of 0.14 s. The results of ResNet101 indicated 96.3% overall accuracy, 96.1% mammogram accuracy, an AUC of 0.96, and a processing time of 0.20 s. This developed method offers quick, accurate calcification classification and efficient visualization of calcification locations.
  • Takahiro Matsui, Hiroyuki Sugimori, Shige Koseki, Kento Koyama
    Postharvest Biology and Technology 203 0925-5214 2023/09 [Refereed]
     
    Internal rot of avocado fruit (Persea americana), attributable to fungal infection, occurs at the end of the ripening process and causes only minor changes in the appearance and texture of the fruit surface. Manual inspection of rot by sight and touch commonly conducted in countries importing avocado fruit is time-consuming, labor-intensive, and subjective. In this context, X-ray line scanning has been proven as an advantageous method of fruit rot detection because of its speed of data acquisition and the indication of internal rot by bright regions in associated images. However, some fruit internal disorders exhibit only poor changes in contrast, resulting in low detectability by traditional image processing. This study aimed to test the effectiveness of a detection model using deep learning-based semantic segmentation in identifying two types of fruit rot, stem-end and body rot, in Hass avocados. Therefore, U-net+ + was trained and validated via 5-fold cross-validation to classify every pixel in an X-ray image as either infected or not. Then, each X-ray image was binarily classified based on either the presence or absence of internal fruit rots, achieving an accuracy of 0.98. Furthermore, the percentage of infected area was quantified with a root mean squared error (RMSE) of 3.15 %. Lastly, the proposed model detected both stem-end and body rot as well as rot along low-contrast fruit edges. The results of this study indicate that the proposed automatic inspection system using deep learning-based X-ray image analysis can effectively detect internal rot in Hass avocado fruit. This non-destructive, objective detection model can therefore increase efficiency and reduce misclassification in post-harvest avocado inspection. Furthermore, deep learning-based X-ray imaging has potential for applications in fruit inspection for internal cavities attributable to diseases or wounds.
  • Soichiro Inomata, Takaaki Yoshimura, Minghui Tang, Shota Ichikawa, Hiroyuki Sugimori
    Sensors 23 (14) 6580 - 6580 2023/07/21 [Refereed]
     
    Cardiac function indices must be calculated using tracing from short-axis images in cine-MRI. A 3D-CNN (convolutional neural network) that adds time series information to images can estimate cardiac function indices without tracing using images with known values and cardiac cycles as the input. Since the short-axis image depicts the left and right ventricles, it is unclear which motion feature is captured. This study aims to estimate the indices by learning the short-axis images and the known left and right ventricular ejection fractions and to confirm the accuracy and whether each index is captured as a feature. A total of 100 patients with publicly available short-axis cine images were used. The dataset was divided into training:test = 8:2, and a regression model was built by training with the 3D-ResNet50. Accuracy was assessed using a five-fold cross-validation. The correlation coefficient, MAE (mean absolute error), and RMSE (root mean squared error) were determined as indices of accuracy evaluation. The mean correlation coefficient of the left ventricular ejection fraction was 0.80, MAE was 9.41, and RMSE was 12.26. The mean correlation coefficient of the right ventricular ejection fraction was 0.56, MAE was 11.35, and RMSE was 14.95. The correlation coefficient was considerably higher for the left ventricular ejection fraction. Regression modeling using the 3D-CNN indicated that the left ventricular ejection fraction was estimated more accurately, and left ventricular systolic function was captured as a feature.
  • Takaaki Yoshimura, Keisuke Manabe, Hiroyuki Sugimori
    Applied Sciences 13 (14) 8028 - 8028 2023/07/09 [Refereed]
     
    The Gleason score (GS) is essential in categorizing prostate cancer risk using biopsy. The aim of this study was to propose a two-class GS classification (< and ≥GS 7) methodology using a three-dimensional convolutional neural network with semantic segmentation to predict GS non-invasively using multiparametric magnetic resonance images (MRIs). Four training datasets of T2-weighted images and apparent diffusion coefficient maps with and without semantic segmentation were used as test images. All images and lesion information were selected from a training cohort of the Society of Photographic Instrumentation Engineers, the American Association of Physicists in Medicine, and the National Cancer Institute (SPIE–AAPM–NCI) PROSTATEx Challenge dataset. Precision, recall, overall accuracy and area under the receiver operating characteristics curve (AUROC) were calculated from this dataset, which comprises publicly available prostate MRIs. Our data revealed that the GS ≥ 7 precision (0.73 ± 0.13) and GS < 7 recall (0.82 ± 0.06) were significantly higher using semantic segmentation (p < 0.05). Moreover, the AUROC in segmentation volume was higher than that in normal volume (ADCmap: 0.70 ± 0.05 and 0.69 ± 0.08, and T2WI: 0.71 ± 0.07 and 0.63 ± 0.08, respectively). However, there were no significant differences in overall accuracy between the segmentation and normal volume. This study generated a diagnostic method for non-invasive GS estimation from MRIs.
  • Taku Sugiyama, Masaki Ito, Hiroyuki Sugimori, Minghui Tang, Toshitaka Nakamura, Katsuhiko Ogasawara, Hitoshi Matsuzawa, Naoki Nakayama, Sanju Lama, Garnette R Sutherland, Miki Fujimura
    Operative neurosurgery (Hagerstown, Md.) 2023/07/04 [Refereed]
     
    BACKGROUND AND OBJECTIVES: Gentle tissue handling to avoid excessive motion of affected fragile vessels during surgical dissection is essential for both surgeon proficiency and patient safety during carotid endarterectomy (CEA). However, a void remains in the quantification of these aspects during surgery. The video-based measurement of tissue acceleration is presented as a novel metric for the objective assessment of surgical performance. This study aimed to evaluate whether such metrics correlate with both surgeons' skill proficiency and adverse events during CEA. METHODS: In a retrospective study including 117 patients who underwent CEA, acceleration of the carotid artery was measured during exposure through a video-based analysis. Tissue acceleration values and threshold violation error frequencies were analyzed and compared among the surgeon groups with different surgical experience (3 groups: novice, intermediate, and expert). Multiple patient-related variables, surgeon groups, and video-based surgical performance parameters were compared between the patients with and without adverse events during CEA. RESULTS: Eleven patients (9.4%) experienced adverse events after CEA, and the rate of adverse events significantly correlated with the surgeon group. The mean maximum tissue acceleration and number of errors during surgical tasks significantly decreased from novice, to intermediate, to expert surgeons, and stepwise discriminant analysis showed that the combined use of surgical performance factors could accurately discriminate between surgeon groups. The multivariate logistic regression analysis revealed that the number of errors and vulnerable carotid plaques were associated with adverse events. CONCLUSION: Tissue acceleration profiles can be a novel metric for the objective assessment of surgical performance and the prediction of adverse events during surgery. Thus, this concept can be introduced into futuristic computer-aided surgeries for both surgical education and patient safety.
  • Shota Ichikawa, Hideki Itadani, Hiroyuki Sugimori
    Journal of applied clinical medical physics 24 (8) e14080  2023/06/19 [Refereed]
     
    PURPOSE: Accurate body weight measurement is essential to promote computed tomography (CT) dose optimization; however, body weight cannot always be measured prior to CT examination, especially in the emergency setting. The aim of this study was to investigate whether deep learning-based body weight from chest CT scout images can be an alternative to actual body weight in CT radiation dose management. METHODS: Chest CT scout images and diagnostic images acquired for medical checkups were collected from 3601 patients. A deep learning model was developed to predict body weight from scout images. The correlation between actual and predicted body weight was analyzed. To validate the use of predicted body weight in radiation dose management, the volume CT dose index (CTDIvol ) and the dose-length product (DLP) were compared between the body weight subgroups based on actual and predicted body weight. Surrogate size-specific dose estimates (SSDEs) acquired from actual and predicted body weight were compared to the reference standard. RESULTS: The median actual and predicted body weight were 64.1 (interquartile range: 56.5-72.4) and 64.0 (56.3-72.2) kg, respectively. There was a strong correlation between actual and predicted body weight (ρ = 0.892, p < 0.001). The CTDIvol and DLP of the body weight subgroups were similar based on actual and predicted body weight (p < 0.001). Both surrogate SSDEs based on actual and predicted body weight were not significantly different from the reference standard (p = 0.447 and 0.410, respectively). CONCLUSION: Predicted body weight can be an alternative to actual body weight in managing dose metrics and simplifying SSDE calculation. Our proposed method can be useful for CT radiation dose management in adult patients with unknown body weight.
  • Daisuke Oura, Soichiro Takamiya, Riku Ihara, Yoshimasa Niiya, Hiroyuki Sugimori
    Diagnostics 2023/06 [Refereed]
  • Kousuke Usui, Takaaki Yoshimura, Shota Ichikawa, Hiroyuki Sugimori
    Applied Sciences 13 (11) 6695 - 6695 2023/05 [Refereed]
     
    Although the widespread use of digital imaging has enabled real-time image display, images in chest X-ray examinations can be confirmed by the radiologist’s eyes. Considering the development of deep learning (DL) technology, its application will make it possible to immediately determine the need for a retake, which is expected to further improve examination throughput. In this study, we developed software for evaluating chest X-ray images to determine whether a repeat radiographic examination is necessary, based on the combined application of DL technologies, and evaluated its accuracy. The target population was 4809 chest images from a public database. Three classification models (CLMs) for lung field defects, obstacle shadows, and the location of obstacle shadows and a semantic segmentation model (SSM) for the lung field regions were developed using a fivefold cross validation. The CLM was evaluated using the overall accuracy in the confusion matrix, the SSM was evaluated using the mean intersection over union (mIoU), and the DL technology-combined software was evaluated using the total response time on this software (RT) per image for each model. The results of each CLM with respect to lung field defects, obstacle shadows, and obstacle shadow location were 89.8%, 91.7%, and 91.2%, respectively. The mIoU of the SSM was 0.920, and the software RT was 3.64 × 10−2 s. These results indicate that the software can immediately and accurately determine whether a chest image needs to be re-scanned.
  • Moto Fukai, Hiroyuki Sugimori, Sodai Sakamoto, Kengo Shibata, Hiroyuki Kameda, Takahisa Ishikawa, Norio Kawamura, Masato Fujiyoshi, Sunao Fujiyoshi, Kohsuke Kudo, Tsuyoshi Shimamura, Akinobu Taketomi
    Transplantation proceedings 55 (4) 1032 - 1035 2023/04/10 [Refereed]
     
    Interventions for liver grafts with moderate macrovesicular steatosis have been important in enlarging donor pools. Here, we tested a high-fat and cholesterol (HFC) diet to create a steatosis model for cold hepatic preservation and reperfusion experiments. The aim of the present study was to assess the steatosis model's reliability and to show the resulting graft's quality for cold preservation and reperfusion experiment. Male SHRSP5-Dmcr rats were raised with an HFC diet for up to 2 weeks. The fat content was evaluated using magnetic resonance imaging (MRI) proton density fat fraction (PDFF). The nonalcoholic fatty liver disease activity score (NAS) was evaluated after excision. Steatosis created by 2 weeks of HFC diet was subjected to 24-hour cold storage in the University of Wisconsin and the original test solution (new sol.). Grafts were applied to isolated perfused rat livers for simulating reperfusion. The NAS were 2.2 (HFC 5 days), 3.3 (HFC 1 week), and 5.0 (HFC 2 weeks). Ballooning and fibrosis were not observed in any group. An MRI-PDFF showed 0.2 (HFC 0 days), 12.0 (HFC 1 week), and 18.9 (HFC 2 weeks). The NAS and MRI-PDFF values correlated. Many indices in the isolated perfused rat liver experiment tended to improve in the new sol. group but were insufficient. Although the new sol. failed to be effective, it acted at multiple sites under difficult conditions. In conclusion, the HFC diet for 2 weeks in SHRSP5-Dmcr rats, together with MRI-PDFF evaluation, is a reliable method for creating simple steatosis and provides good-quality cold preservation and reperfusion experiments.
  • Shota Ichikawa, Hiroyuki Sugimori, Koki Ichijiri, Takaaki Yoshimura, Akio Nagaki
    Journal of applied clinical medical physics 24 (6) e13978  2023/04/05 [Refereed]
     
    PURPOSE: Given the potential risk of motion artifacts, acquisition time reduction is desirable in pediatric 99m Tc-dimercaptosuccinic acid (DMSA) scintigraphy. The aim of this study was to evaluate the performance of predicted full-acquisition-time images from short-acquisition-time pediatric 99m Tc-DMSA planar images with only 1/5th acquisition time using deep learning in terms of image quality and quantitative renal uptake measurement accuracy. METHODS: One hundred and fifty-five cases that underwent pediatric 99m Tc-DMSA planar imaging as dynamic data for 10 min were retrospectively collected for the development of three deep learning models (DnCNN, Win5RB, and ResUnet), and the generation of full-time images from short-time images. We used the normalized mean squared error (NMSE), peak signal-to-noise ratio (PSNR), and structural similarity index metrics (SSIM) to evaluate the accuracy of the predicted full-time images. In addition, the renal uptake of 99m Tc-DMSA was calculated, and the difference in renal uptake from the reference full-time images was assessed using scatter plots with Pearson correlation and Bland-Altman plots. RESULTS: The predicted full-time images from the deep learning models showed a significant improvement in image quality compared to the short-time images with respect to the reference full-time images. In particular, the predicted full-time images obtained by ResUnet showed the lowest NMSE (0.4 [0.4-0.5] %) and the highest PSNR (55.4 [54.7-56.1] dB) and SSIM (0.997 [0.995-0.997]). For renal uptake, an extremely high correlation was achieved in all short-time and three predicted full-time images (R2  > 0.999 for all). The Bland-Altman plots showed the lowest bias (-0.10) of renal uptake in ResUnet, while short-time images showed the lowest variance (95% confidence interval: -0.14, 0.45) of renal uptake. CONCLUSIONS: Our proposed method is capable of producing images that are comparable to the original full-acquisition-time images, allowing for a reduction of acquisition time/injected dose in pediatric 99m Tc-DMSA planar imaging.
  • Daisuke Oura, Shinpe Sato, Yuto Honma, Shiho Kuwajima, Hiroyuki Sugimori
    Applied Sciences 2023/02 [Refereed]
  • Shota Ichikawa, Hideki Itadani, Hiroyuki Sugimori
    Radiological physics and technology 16 (1) 127 - 134 2023/01/13 [Refereed]
     
    Accurate body weights are not necessarily available in routine clinical practice. This study aimed to investigate whether body weight can be predicted from chest radiographs using deep learning. Deep-learning models with a convolutional neural network (CNN) were trained and tested using chest radiographs from 85,849 patients. The CNN models were evaluated by calculating the mean absolute error (MAE) and Spearman's rank correlation coefficient (ρ). The MAEs of the CNN models were 2.63 kg and 3.35 kg for female and male patients, respectively. The predicted body weight was significantly correlated with the actual body weight (ρ = 0.917, p < 0.001 for females; ρ = 0.915, p < 0.001 for males). The body weight was predicted using chest radiographs by applying deep learning. Our method is potentially useful for radiation dose management, determination of the contrast medium dose, and estimation of the specific absorption rate in patients with unknown body weights.
  • Kousuke Usui, Takaaki Yoshimura, Minghui Tang, Hiroyuki Sugimori
    Applied Sciences 13 (3) 1753 - 1753 2023/01 [Refereed]
     
    Estimation of human age is important in the fields of forensic medicine and the detection of neurodegenerative diseases of the brain. Particularly, the age estimation methods using brain magnetic resonance (MR) images are greatly significant because these methods not only are noninvasive but also do not lead to radiation exposure. Although several age estimation methods using brain MR images have already been investigated using deep learning, there are no reports involving younger subjects such as children. This study investigated the age estimation method using T1-weighted (sagittal plane) two-dimensional brain MR imaging (MRI) of 1000 subjects aged 5–79 (31.64 ± 18.04) years. This method uses a regression model based on ResNet-50, which estimates the chronological age (CA) of unknown brain MR images by training brain MR images corresponding to the CA. The correlation coefficient, coefficient of determination, mean absolute error, and root mean squared error were used as the evaluation indices of this model, and the results were 0.9643, 0.9299, 5.251, and 6.422, respectively. The present study showed the same degree of correlation as those of related studies, demonstrating that age estimation can be performed for a wide range of ages with higher estimation accuracy.
  • Takaaki Yoshimura, Kentaro Nishioka, Takayuki Hashimoto, Takashi Mori, Shoki Kogame, Kazuya Seki, Hiroyuki Sugimori, Hiroko Yamashina, Yusuke Nomura, Fumi Kato, Kohsuke Kudo, Shinichi Shimizu, Hidefumi Aoyama
    PloS one 18 (1) e0280076  2023 [Refereed]
     
    In urethra-sparing radiation therapy, prostatic urinary tract visualization is important in decreasing the urinary side effect. A methodology has been developed to visualize the prostatic urinary tract using post-urination magnetic resonance imaging (PU-MRI) without a urethral catheter. This study investigated whether the combination of PU-MRI and super-resolution (SR) deep learning models improves the visibility of the prostatic urinary tract. We enrolled 30 patients who had previously undergone real-time-image-gated spot scanning proton therapy by insertion of fiducial markers. PU-MRI was performed using a non-contrast high-resolution two-dimensional T2-weighted turbo spin-echo imaging sequence. Four different SR deep learning models were used: the enhanced deep SR network (EDSR), widely activated SR network (WDSR), SR generative adversarial network (SRGAN), and residual dense network (RDN). The complex wavelet structural similarity index measure (CW-SSIM) was used to quantitatively assess the performance of the proposed SR images compared to PU-MRI. Two radiation oncologists used a 1-to-5 scale to subjectively evaluate the visibility of the prostatic urinary tract. Cohen's weighted kappa (k) was used as a measure of agreement of inter-operator reliability. The mean CW-SSIM in EDSR, WDSR, SRGAN, and RDN was 99.86%, 99.89%, 99.30%, and 99.67%, respectively. The mean prostatic urinary tract visibility scores of the radiation oncologists were 3.70 and 3.53 for PU-MRI (k = 0.93), 3.67 and 2.70 for EDSR (k = 0.89), 3.70 and 2.73 for WDSR (k = 0.88), 3.67 and 2.73 for SRGAN (k = 0.88), and 4.37 and 3.73 for RDN (k = 0.93), respectively. The results suggest that SR images using RDN are similar to the original images, and the SR deep learning models subjectively improve the visibility of the prostatic urinary tract.
  • Keita Ninagawa, Masaru Kato, Yasuka Kikuchi, Hiroyuki Sugimori, Michihito Kono, Yuichiro Fujieda, Ichizo Tsujino, Tatsuya Atsumi
    Modern rheumatology 33 (4) 758 - 767 2022/09/02 [Refereed]
     
    OBJECTIVE: Systemic sclerosis (SSc) is associated with pulmonary vascular disease (PVD) and interstitial lung disease (ILD), making it difficult to differentiate pulmonary arterial hypertension and pulmonary hypertension (PH) due to lung diseases and/or hypoxia and to decide treatments. We aimed to predict the response to pulmonary vasodilators in patients with SSc and PH. METHODS: 84 SSc patients were included with 47 having PH. Chest CT was evaluated using a software to calculate abnormal lung volume (ALV). To define the response to vasodilators, Δ mean pulmonary artery pressure (mPAP)/basal mPAP was used (cut-off value: 10%). The predictive value was evaluated by using receiver operating characteristic curve. RESULTS: The mean (±SD) value of ALV was 26.8 (±32.2) %. A weak correlation was observed between ALV and forced vital capacity (FVC) (R = -0.46). The predictive value of ALV (area under curve; AUC = 0.74) was superior to that of FVC (AUC = 0.62) for the response to vasodilators. No hemodynamic parameters differed between patients with high and low ALV, whereas survival was worse in high ALV. CONCLUSION: Quantitative chest CT well predicted the response to vasodilators in patients with SSc and PH. Our results suggest its utility in differentiating the dominance of PVD or ILD.
  • Daisuke Oura, Masayuki Gekka, Yutaka Morishima, Yoshimasa Niiya, Riku Ihara, Thubasa Ebina, Hiroyuki Sugimori
    Magnetic resonance imaging 2022/08/14 [Refereed]
     
    [Background and Purpose] Clot location and range predict clinical outcomes for acute ischemic stroke (AIS). We developed a new technique for visualizing occlusion clots, namely, the DEpicting blood clot and MRA using Phase contrast angiography with Image Calculation for Thrombectomy (DEPICT) method. The purpose of this study was to assess the clinical usefulness of DEPICT. [Methods] We used DEPICT in 36 AIS patients to obtain MRA and black blood images with 1-min phase contrast angiography (PCA). We created the black blood images by subtracting the MRA from the T1WI using the source image of PCA. We evaluated the motion artifact, detectability of clot, and precision in location and range compared these to that of susceptibility vessel sign in T2*WI and measured contrast ration (CR) of clot between the cistern and brain tissue. Motion artifact was visually evaluated using a 3-point scale. Detectability and precision of the location and range of occlusion clots were assessed by comparison with findings from digital subtraction angiography (DSA). Gwet's AC1 and kappa statistic were used to assess inter-observer agreement. [Results] DEPICT showed significant robustness for motion artifact compared with T2*WI (p = 0.0026, Wilcoxon signed-rank test). DEPICT showed 100% detectability for the clot. Further, DEPICT showed higher Gwet's AC1 and kappa statistic values with DSA than T2*WI. CR demonstrated a positive value. [Conclusions] DEPICT technique based on 1-min PCA offers both MRA and black blood T1W images that can be used to accurately evaluate both location and range of the clot.
  • Shota Ichikawa, Hideki Itadani, Hiroyuki Sugimori
    Physical and engineering sciences in medicine 45 (3) 835 - 845 2022/07/06 [Refereed]
     
    Consistent cross-sectional imaging is desirable to accurately detect lesions and facilitate follow-up in head computed tomography (CT). However, manual reformation causes image variations among technologists and requires additional time. We therefore developed a system that reformats head CT images at the orbitomeatal (OM) line and evaluated the system performance using real-world clinical data. Retrospective data were obtained for 681 consecutive patients who underwent non-contrast head CT. The datasets were randomly divided into one of three sets for training, validation, or testing. Four landmarks (bilateral eyes and external auditory canal) were detected with the trained You Look Only Once (YOLO)v5 model, and the head CT images were reformatted at the OM line. The precision, recall, and mean average precision at the intersection over union threshold of 0.5 were computed in the validation sets. The reformation quality in testing sets was evaluated by three radiological technologists on a qualitative 4-point scale. The precision, recall, and mean average precision of the trained YOLOv5 model for all categories were 0.688, 0.949, and 0.827, respectively. In our environment, the mean implementation time was 23.5 ± 2.4 s for each case. The qualitative evaluation in the testing sets showed that post-processed images of automatic reformation had clinically useful quality with scores 3 and 4 in 86.8%, 91.2%, and 94.1% for observers 1, 2, and 3, respectively. Our system demonstrated acceptable quality in reformatting the head CT images at the OM line using an object detection algorithm and was highly time efficient.
  • Yoshiaki Hosokawa, Tomohiro Onodera, Kentaro Homan, Jun Yamaguchi, Kohsuke Kudo, Hiroyuki Kameda, Hiroyuki Sugimori, Norimasa Iwasaki
    CARTILAGE 13 (3) 1947-6035 2022/07 [Refereed]
     
    Objective In the early stages of cartilage damage, diagnostic methods focusing on the mechanism of maintaining the hydrostatic pressure of cartilage are thought to be useful. O-17-labeled water, which is a stable isotope of oxygen, has the advantage of no radiation exposure or allergic reactions and can be detected by magnetic resonance imaging (MRI). This study aimed to evaluate MRI images using O-17-labeled water in a rabbit model. Design Contrast MRI with O-17-labeled water and macroscopic and histological evaluations were performed 4 and 8 weeks after anterior cruciate ligament transection surgery in rabbits. A total of 18 T2-weighted images were acquired, and O-17-labeled water was manually administered on the third scan. The O-17 concentration in each phase was calculated from the signal intensity at the articular cartilage. Macroscopic and histological grades were evaluated and compared with the O-17 concentration. Results An increase in O-17 concentration in the macroscopic and histologically injured areas was observed by MRI. Macroscopic evaluation showed that the O-17 concentration significantly increased in the damaged site group. Histological evaluations also showed that O-17 concentrations significantly increased at 36 minutes 30 seconds after initiating MRI scanning in the Osteoarthritis Research Society International (OARSI) grade 3 (0.493 in grade 0, 0.659 in grade 1, 0.4651 in grade 2, and 0.9964 in grade 3, P < 0.05). Conclusion O-17-labeled water could visualize earlier articular cartilage damage, which is difficult to detect by conventional methods.
  • Kaori Tsutsumi, Keima Tokunaga, Shun Saito, Tatsuya Sasase, Hiroyuki Sugimori
    Endocrine, metabolic & immune disorders drug targets 2022/07/01 [Refereed]
     
    BACKGROUND: Mitochondrial morphology reversibly changes between division and fusion. As these changes (mitochondrial dynamics) reflect the cellular condition, they are one of the simplest indicators of cell state and predictors of cell fate. However, it is currently difficult to classify them using a simple and objective method. OBJECTIVE: The present study aimed to evaluate mitochondrial morphology using Deep Learning (DL) technique. METHODS: Mitochondrial images stained by MitoTracker were acquired from HeLa and MC3T3-E1 cells using fluorescent microscopy and visually classified into four groups based on fission or fusion. The intra- and inter-rater reliabilities for visual classification were excellent [(ICC(1,3), 0.961 for rater 1; and 0.981 for rater 2) and ICC(1,3), respectively]. The images were divided into test and train images, and a 50-layer ResNet CNN architecture (ResNet-50) using MATLAB software was used to train the images. The datasets were trained five times based on five-fold cross-validation. RESULT: The mean of the overall accuracy for classifying mitochondrial morphology was 0.73±0.10 in HeLa. For the classification of mixed images containing two types of cell lines, the overall accuracy using mixed images of both cell lines for training was higher (0.74±0.01) than that using different cell lines for training. CONCLUSION: We developed a classifier to categorize mitochondrial morphology using DL.
  • Takaaki Yoshimura, Atsushi Hasegawa, Shoki Kogame, Keiichi Magota, Rina Kimura, Shiro Watanabe, Kenji Hirata, Hiroyuki Sugimori
    Diagnostics (Basel, Switzerland) 12 (4) 2022/03/31 [Refereed]
     
    In positron emission tomography (PET) imaging, image quality correlates with the injected [18F]-fluorodeoxyglucose (FDG) dose and acquisition time. If image quality improves from short-acquisition PET images via the super-resolution (SR) deep learning technique, it is possible to reduce the injected FDG dose. Therefore, the aim of this study was to clarify whether the SR deep learning technique could improve the image quality of the 50%-acquisition-time image to the level of that of the 100%-acquisition-time image. One-hundred-and-eight adult patients were enrolled in this retrospective observational study. The supervised data were divided into nine subsets for nested cross-validation. The mean peak signal-to-noise ratio and structural similarity in the SR-PET image were 31.3 dB and 0.931, respectively. The mean opinion scores of the 50% PET image, SR-PET image, and 100% PET image were 3.41, 3.96, and 4.23 for the lung level, 3.31, 3.80, and 4.27 for the liver level, and 3.08, 3.67, and 3.94 for the bowel level, respectively. Thus, the SR-PET image was more similar to the 100% PET image and subjectively improved the image quality, as compared to the 50% PET image. The use of the SR deep-learning technique can reduce the injected FDG dose and thus lower radiation exposure.
  • Kenji Hirata, Hiroyuki Sugimori, Noriyuki Fujima, Takuya Toyonaga, Kohsuke Kudo
    Annals of nuclear medicine 36 (2) 123 - 132 2022/01/14 [Refereed]
     
    As in all other medical fields, artificial intelligence (AI) is increasingly being used in nuclear medicine for oncology. There are many articles that discuss AI from the viewpoint of nuclear medicine, but few focus on nuclear medicine from the viewpoint of AI. Nuclear medicine images are characterized by their low spatial resolution and high quantitativeness. It is noted that AI has been used since before the emergence of deep learning. AI can be divided into three categories by its purpose: (1) assisted interpretation, i.e., computer-aided detection (CADe) or computer-aided diagnosis (CADx). (2) Additional insight, i.e., AI provides information beyond the radiologist's eye, such as predicting genes and prognosis from images. It is also related to the field called radiomics/radiogenomics. (3) Augmented image, i.e., image generation tasks. To apply AI to practical use, harmonization between facilities and the possibility of black box explanations need to be resolved.
  • Hiroyuki Sugimori, Hiroyuki Kameda, Taisuke Harada, Kinya Ishizaka, Masayoshi Kajiyama, Tasuku Kimura, Niki Udo, Masaaki Matsushima, Azusa Nagai, Masahiro Wakita, Ichiro Kusumi, Ichiro Yabe, Kohsuke Kudo
    Magnetic resonance imaging 87 77 - 85 2021/12/27 [Refereed]
     
    The aim of this study was to evaluate the feasibility of kinetic analysis of cerebrospinal fluid (CSF) using 17O-labeled water tracer. Four subjects (two idiopathic normal pressure hydrocephalus (iNPH) and two possible AD dementia patients) were prospectively included. Injectable formulation of 17O-labeled water containing 10 mol% of H217O (PSO17), was intrathecally administered to the subjects with the lateral decubitus position between the 3rd and 4th lumbar vertebrae. MRI acquisitions were performed in four-time points, before PSO17 administration, 1, 8, and 24 h after PSO17 administration. The 3-dimensional fast spin echo sequence was used. After image registration for all four-time points data, polygonal regions of interest (ROIs) were set in the 14 regions to obtain the signal intensity of CSF. Each signal intensity within the ROI was converted to 17O concentration [%]. The peak concentration at one hour after administration, the slope of concentration changes after PSO17 administration [%/s], and the root mean square error (RMSE) for evaluating the performance of a fitting were calculated. There was no significant difference in peak concentration between the iNPH and AD group. The slope in the AD group (-2.25 ± 1.62 × 10-3 [%/h]) was significantly smaller than in the iNPH group (-1.21 ± 2.31 × 10-3 [%/h]), which suggests the speed of CSF clearance in the iNPH group was slower than AD group. The RMSE indicating the fit to the concentration change in the AD group (4.86 ± 4.74 × 10-3) was also significantly smaller than in the iNPH group (8.64 ± 7.56 × 10-3). The kinetic evaluation of CSF using 17O-labeled water was feasible, and this preliminary study suggests that the differentiation of iNPH and possible AD dementia can be achieved using this method.
  • Yusuke Asami, Takaaki Yoshimura, Keisuke Manabe, Tomonari Yamada, Hiroyuki Sugimori
    Applied Sciences 11 (24) 12006 - 12006 2021/12 [Refereed]
     
    Purpose: A deep learning technique was used to analyze the triceps surae muscle. The devised interpolation method was used to determine muscle’s volume and verify the usefulness of the method. Materials and Methods: Thirty-eight T1-weighted cross-sectional magnetic resonance images of the triceps of the lower leg were divided into three classes, i.e., gastrocnemius lateralis (GL), gastrocnemius medialis (GM), and soleus (SOL), and the regions of interest (ROIs) were manually defined. The supervised images were classified as per each patient. A total of 1199 images were prepared. Six different datasets separated patient-wise were prepared for K-fold cross-validation. A network model of the DeepLabv3+ was used for training. The images generated by the created model were divided as per each patient and classified into each muscle types. The model performance and the interpolation method were evaluated by calculating the Dice similarity coefficient (DSC) and error rates of the volume of the predicted and interpolated images, respectively. Results: The mean DSCs for the predicted images were >0.81 for GM and SOL and 0.71 for GL. The mean error rates for volume were approximately 11% for GL, SOL, and total error and 23% for GL. DSCs in the interpolated images were >0.8 for all muscles. The mean error rates of volume were <10% for GL, SOL, and total error and 18% for GM. There was no significant difference between the volumes obtained from the supervised images and interpolated images. Conclusions: Using the semantic segmentation of the deep learning technique, the triceps were detected with high accuracy and the interpolation method used in this study to find the volume was useful.
  • T. Yoshimura, K. Nishioka, T. Hashimoto, S. Kogame, K. Seki, H. Sugimori, H. Yamashina, F. Kato, H. Aoyama, K. Kudo, S. Shimizu
    International Journal of Radiation Oncology*Biology*Physics 111 (3) e121 - e122 0360-3016 2021/11 [Refereed]
  • Daisuke Oura, Riku Ihara, Eiichirou Myo, Shinpei Sato, Hiroyuki Sugimori
    Magnetic resonance imaging 85 193 - 201 2021/10/27 [Refereed]
     
    [Background] Magnetic resonance angiography (MRA) is one of the most important sequences to estimate a cerebrovascular disease. We often encounter poor image quality due to slow arterial flow related to aging and motion artifact caused by disturbance of consciousness. We focused on phase contrast angiography (PCA) to overcome these difficulties. PCA can reduce scan time drastically by combining transverse acquisition and partial slab setting covering entire brain arteries. However, transverse acquisition in PCA has a large difference in signal intensity between proximal and distal vessels. Therefore, we apply tilted optimized non-saturated excitation (TONE) to improve image quality. [Purpose] The purpose of this study to investigate the usefulness of TONE for PCA. [Method] We estimated the efficacy of TONE in transverse acquisition PCA using measurement of signal intensity in arteries. We compared image quality among 1 min PCA with/without TONE and time-of flight (TOF)-MRA, by visual. [Result] TONE improved the signal inhomogeneity in entire brain arteries. PCA with TONE (5°-9°) demonstrated the highest image quality. [Conclusion] Oblique transverse acquisition PCA with TONE provides superior image quality compared with TOF with similar scan time. TONE improved image quality by the homogenizing signal intensity of vessels from proximal to distal in oblique transvers acquisition PCA. Our MRA can be performed in about 1 min and provides sufficient quality to estimate brain vessels.
  • Shota Ichikawa, Misaki Hamada, Hiroyuki Sugimori
    Scientific reports 11 (1) 15627 - 15627 2021/08/02 [Refereed]
     
    Body weight is an indispensable parameter for determination of contrast medium dose, appropriate drug dosing, or management of radiation dose. However, we cannot always determine the accurate patient body weight at the time of computed tomography (CT) scanning, especially in emergency care. Time-efficient methods to estimate body weight with high accuracy before diagnostic CT scans currently do not exist. In this study, on the basis of 1831 chest and 519 abdominal CT scout images with the corresponding body weights, we developed and evaluated deep-learning models capable of automatically predicting body weight from CT scout images. In the model performance assessment, there were strong correlations between the actual and predicted body weights in both chest (ρ = 0.947, p < 0.001) and abdominal datasets (ρ = 0.869, p < 0.001). The mean absolute errors were 2.75 kg and 4.77 kg for the chest and abdominal datasets, respectively. Our proposed method with deep learning is useful for estimating body weights from CT scout images with clinically acceptable accuracy and potentially could be useful for determining the contrast medium dose and CT dose management in adult patients with unknown body weight.
  • Hiroyuki Sugimori, Kaoruko Shimizu, Hironi Makita, Masaru Suzuki, Satoshi Konno
    Diagnostics (Basel, Switzerland) 11 (6) 2021/05/21 [Refereed]
     
    Recently, deep learning applications in medical imaging have been widely applied. However, whether it is sufficient to simply input the entire image or whether it is necessary to preprocess the setting of the supervised image has not been sufficiently studied. This study aimed to create a classifier trained with and without preprocessing for the Global Initiative for Chronic Obstructive Lung Disease (GOLD) classification using CT images and to evaluate the classification accuracy of the GOLD classification by confusion matrix. According to former GOLD 0, GOLD 1, GOLD 2, and GOLD 3 or 4, eighty patients were divided into four groups (n = 20). The classification models were created by the transfer learning of the ResNet50 network architecture. The created models were evaluated by confusion matrix and AUC. Moreover, the rearranged confusion matrix for former stages 0 and ≥1 was evaluated by the same procedure. The AUCs of original and threshold images for the four-class analysis were 0.61 ± 0.13 and 0.64 ± 0.10, respectively, and the AUCs for the two classifications of former GOLD 0 and GOLD ≥ 1 were 0.64 ± 0.06 and 0.68 ± 0.12, respectively. In the two-class classification by threshold image, recall and precision were over 0.8 in GOLD ≥ 1, and in the McNemar-Bowker test, there was some symmetry. The results suggest that the preprocessed threshold image can be possibly used as a screening tool for GOLD classification without pulmonary function tests, rather than inputting the normal image into the convolutional neural network (CNN) for CT image learning.
  • Yuko Yoshida, Masuko Sumikawa, Hiroyuki Sugimori, rika yano
    Healthcare 9 (4) 2021/04 [Refereed]
     
    In Japan, skin disinfection is typically considered necessary before an insulin injection to prevent infection at the injection site. This cross-sectional study evaluated factors that influenced symptoms of injection site infection among 238 Japanese patients who self-injected insulin for diabetes between October 2015 and January 2016. A structured questionnaire was used to collect data regarding skin disinfection practices, infection symptoms at the injection site, frequency of injections, environment at the time of injection, and hygiene habits. The majority of patients (83.2%) performed skin disinfection before the self-injection. Logistic regression analysis revealed that infection at the injection site was positively associated with skin disinfection before injection, age, and performing injections outside home. It was speculated that omitting skin disinfection before administering subcutaneous insulin injection was not the factor that affected the symptoms of injection site infection. The greatest contributor to infection symptoms was injections performed outside the home. Future studies focusing on the environment, in which patients administer insulin injections, to assess its influence on symptoms of injection site infections are warranted.
  • Takaaki Yoshimura, Kentaro Nishioka, Takayuki Hashimoto, Taro Fujiwara, Kinya Ishizaka, Hiroyuki Sugimori, Shoki Kogame, Kazuya Seki, Hiroshi Tamura, Sodai Tanaka, Yuto Matsuo, Yasuhiro Dekura, Fumi Kato, Hidefumi Aoyama, Shinichi Shimizu
    Physics and Imaging in Radiation Oncology 18 1 - 4 2021/04 [Refereed]
     
    The urethra position may shift due to the presence/absence of the catheter. Our proposed post-urination-magnetic resonance imaging (PU-MRI) technique is possible to identify the urethra without catheter. We aimed to verify the inter-operator difference in contouring the urethra by PU-MRI. The mean values of the evaluation indices of dice similarity coefficient, mean slice-wise Hausdorff distance, and center coordinates were 0.93, 0.17 mm, and 0.36 mm for computed tomography, and 0.75, 0.44 mm, and 1.00 mm for PU-MRI. Therefore, PU-MRI might be useful for identifying the prostatic urinary tract without using a urethral catheter. Clinical trial registration: Hokkaido University Hospital for Clinical Research (018-0221).
  • Keisuke Manabe, Yusuke Asami, Tomonari Yamada, Hiroyuki Sugimori
    Applied Sciences 11 (4) 2076-3417 2021/02 [Refereed]
  • Hiroyuki Sugimori, Hiroyuki Hamaguchi, Taro Fujiwara, Kinya Ishizaka
    Magnetic resonance imaging 2020/12/21 [Refereed]
  • Hiroyuki Sugimori, Taku Sugiyama, Naoki Nakayama, Akemi Yamashita, Katsuhiko Ogasawara
    Applied Sciences 10 (12) 2076-3417 2020/06 [Refereed][Not invited]
  • Masashi Kawakami, Kenji Hirata, Sho Furuya, Kentaro Kobayashi, Hiroyuki Sugimori, Keiichi Magota, Chietsugu Katoh
    Frontiers in medicine 7 616746 - 616746 2020 [Refereed]
     
    Deep learning technology is now used for medical imaging. YOLOv2 is an object detection model using deep learning. Here, we applied YOLOv2 to FDG-PET images to detect the physiological uptake on the images. We also investigated the detection precision of abnormal uptake by a combined technique with YOLOv2. Using 3,500 maximum intensity projection (MIP) images of 500 cases of whole-body FDG-PET examinations, we manually drew rectangular regions of interest with the size of each physiological uptake to create a dataset. Using YOLOv2, we performed image training as transfer learning by initial weight. We evaluated YOLOv2's physiological uptake detection by determining the intersection over union (IoU), average precision (AP), mean average precision (mAP), and frames per second (FPS). We also developed a combination method for detecting abnormal uptake by subtracting the YOLOv2-detected physiological uptake. We calculated the coverage rate, false-positive rate, and false-negative rate by comparing the combination method-generated color map with the abnormal findings identified by experienced radiologists. The APs for physiological uptakes were: brain, 0.993; liver, 0.913; and bladder, 0.879. The mAP was 0.831 for all classes with the IoU threshold value 0.5. Each subset's average FPS was 31.60 ± 4.66. The combination method's coverage rate, false-positive rate, and false-negative rate for detecting abnormal uptake were 0.9205 ± 0.0312, 0.3704 ± 0.0213, and 0.1000 ± 0.0774, respectively. The physiological uptake of FDG-PET on MIP images was quickly and precisely detected using YOLOv2. The combination method, which can be utilized the characteristics of the detector by YOLOv2, detected the radiologist-identified abnormalities with a high coverage rate. The detectability and fast response would thus be useful as a diagnostic tool.
  • Yuki Tanaka, Motoshi Fujimori, Koichi Murakami, Hiroyuki Sugimori, Nozomi Oki, Takatoshi Aoki, Tamotsu Kamishima
    Rheumatology International 39 (12) 2111 - 2118 0172-8172 2019/12/01 [Refereed][Not invited]
     
    © 2019, Springer-Verlag GmbH Germany, part of Springer Nature. The objective of this study is to investigate computed DWI (cDWI) as an alternative method to contrast-enhanced MRI in comparison with directory measured DWI (mDWI) and apparent diffusion coefficient (ADC) for differentiating synovial proliferation from joint effusion. Nine patients suspected with RA (5 women) were included in this study. A radiologist identified region of interest (ROI) based on STIR, and evaluated using a 5-point grading scale of 0 (fluid) to 4 (synovial proliferation) according to the degree of contrast enhancement within the ROI. cDWI was synthesized for b values from 1000 to 2000 at 200 s/mm2 intervals using the combination of b values at mDWI. In addition to ADC values, contrast ratios were calculated using signal intensity for each ROI on the mDWI and cDWI. Visual assessment by a radiologist was conducted between pairs of STIR image and mDWI or cDWI. ROI grades were most significantly correlated with cDWI2000 based on b values of 400–1000 s/mm2 (rs = 0.405, p < 0.01). The area under the curve of cDWI2000 based on b values of 400–1000 s/mm2 (0.762) was larger than that of ADC values (0.570–0.608) when comparing low versus high contrast enhancement grades. Both cDWI1800 (200–1000) and cDWI2000 (400–1000) demonstrated high sensitivity and specificity in visual assessment (84.6% and 66.7%, respectively). The cDWI2000 based on b values of 400–1000 s/mm2 may be useful for noninvasive differentiation of synovial proliferation from joint effusion in hand arthritis.
  • Motoshi Fujimori, Koichi Murakami, Hiroyuki Sugimori, Yutong Lu, Kenneth Sutherland, Nozomi Oki, Takatoshi Aoki, Tamotsu Kamishima
    Journal of Magnetic Resonance Imaging 50 (4) 1199 - 1206 1053-1807 2019/10/01 [Refereed][Not invited]
     
    © 2019 International Society for Magnetic Resonance in Medicine Background: Postcontrast-enhanced MRI is currently the reference standard for synovial proliferation in rheumatoid arthritis (RA). However, the technique is somewhat invasive due to the use of gadolinium contrast agents, which may cause severe adverse/side effects. Intravoxel incoherent motion (IVIM) simultaneously permits quantification of perfusion as well as diffusion using a single imaging scan. Purpose/Hypothesis: To test the capability of IVIM MRI for noninvasive discrimination of synovial proliferation in hand arthritis. Study Type: Prospective. Subjects: Seven suspected RA patients (three women and four men; mean age, 61 years; range, 26–74 years). Field Strength/Sequence: 3 T/short tau inversion recovery (STIR), IVIM, postcontrast-enhanced MRI. Assessment: Region of interest (ROI) was identified based on STIR. Contrast-enhanced MRI was evaluated using a 5-point grading scale of 0 (water) to 4 (synovial proliferation) according to the degree of contrast enhancement within the ROI. For each ROI, we calculated the apparent diffusion coefficient (ADC) and IVIM parameters (molecular diffusion coefficient [D], perfusion fraction [f], and perfusion-related diffusion coefficient [D*]). These parameters were subsequently compared with ROI contrast enhancement grades. Statistical Tests: Spearman's rank correlation test and a receiver operating characteristic (ROC) curve. Results: A total of 90 ROIs of suspected synovial proliferation and/or joint effusion were identified. ROI grades were correlated with ADC and D values (rS = –0.385, P < 0.001, rS = –0.458, P < 0.0001, respectively), but not with the f and D* values (rS = –0.010, P = 0.936, rS = –0.084, P = 0.505, respectively). The area under the curves (AUCs) of D values (0.708–0.888, P = 0.002–0.0002) were slightly larger than those of ADC values (0.692–0.791, P = 0.013–0.001) when comparing low- vs. high-contrast enhancement grades. Data Conclusion: The IVIM parameter D and ADC may be useful for the noninvasive identification of synovial proliferation in hand arthritis. Level of Evidence: 2. Technical Efficacy Stage: 2. J. Magn. Reson. Imaging 2019;50:1199–1206.
  • Hiroyuki Sugimori, Masashi Kawakami
    Applied Sciences (Switzerland) 9 (18) 2019/09/01 [Refereed][Not invited]
     
    © 2019 by the authors. Recently, deep learning technology has been applied to medical images. This study aimed to create a detector able to automatically detect an anatomical structure presented in a brain magnetic resonance imaging (MRI) scan to draw a standard line. A total of 1200 brain sagittal MRI scans were used for training and validation. Two sizes of regions of interest (ROIs) were drawn on each anatomical structure measuring 64 × 64 pixels and 32 × 32 pixels, respectively. Data augmentation was applied to these ROIs. The faster region-based convolutional neural network was used as the network model for training. The detectors created were validated to evaluate the precision of detection. Anatomical structures detected by the model created were processed to draw the standard line. The average precision of anatomical detection, detection rate of the standard line, and accuracy rate of achieving a correct drawing were evaluated. For the 64 × 64-pixel ROI, the mean average precision achieved a result of 0.76 ± 0.04, which was higher than the outcome achieved with the 32 × 32-pixel ROI. Moreover, the detection and accuracy rates of the angle of difference at 10 degrees for the orbitomeatal line were 93.3 ± 5.2 and 76.7 ± 11.0, respectively. The automatic detection of a reference line for brain MRI can help technologists improve this examination.
  • Kaori Endo, Masahiko Takahata, Hiroyuki Sugimori, Satoshi Yamada, Shigeru Tadano, Jeffrey Wang, Masahiro Todoh, Yoichi M. Ito, Daisuke Takahashi, Kohsuke Kudo, Norimasa Iwasaki
    Clinical Biomechanics 65 13 - 18 0268-0033 2019/05 [Refereed][Not invited]
     
    © 2019 Elsevier Ltd Background: Since bone mass is not the only determinant of bone strength, there has been increasing interest in incorporating the bone quality into fracture risk assessments. We aimed to examine whether the magnetic resonance imaging (MRI) T1 or T2 mapping value could provide information that is complementary to bone mineral density for more accurate prediction of cancellous bone strength. Methods: Four postmenopausal women with hip osteoarthritis underwent 3.0-T MRI to acquire the T1 and T2 values of the cancellous bone of the femoral head before total hip arthroplasty. After the surgery, the excised femoral head was portioned into multiple cubic cancellous bone specimens with side of 5 mm, and the specimens were then subjected to microcomputed tomography followed by biomechanical testing. Findings: The T1 value positively correlated with the yield stress (σ y ) and collapsed stress (σ c ). The T2 value did not correlate with the yield stress, but it correlated with the collapsed stress and strength reduction ratio (σ c /σ y ), which reflects the progressive re-fracture risk. Partial correlation coefficient analyses, after adjusting for the bone mineral density, showed a statistically significant correlation between T1 value and yield stress. The use of multiple coefficients of determination by least squares analysis emphasizes the superiority of combining the bone mineral density and the MRI mapping values in predicting the cancellous bone strength compared with the bone mineral density-based prediction alone. Interpretation: The MRI T1 and T2 values predict cancellous bone strength including the change in bone quality.
  • Hiroyuki Sugimori
    Applied Sciences (Switzerland) 9 (4) 2019/02/17 [Refereed][Not invited]
     
    © 2019 by the authors. A large number of images that are usually registered images in a training dataset are required for creating classification models because training of images using a convolutional neural network is done using supervised learning. It takes a significant amount of time and effort to create a registered dataset because recently computed tomography (CT) and magnetic resonance imaging devices produce hundreds of images per examination. This study aims to evaluate the overall accuracy of the additional learning and automatic classification systems for CT images. The study involved 700 patients, who were subjected to contrast or non-contrast CT examination of brain, neck, chest, abdomen, or pelvis. The images were divided into 500 images per class. The 10-class dataset was prepared with 10 datasets including with 5000-50,000 images. The overall accuracy was calculated using a confusion matrix for evaluating the created models. The highest overall reference accuracy was 0.9033 when the model was trained with a dataset containing 50,000 images. The additional learning for manual training was effective when datasets with a large number of images were used. The additional learning for automatic training requires models with an inherent higher accuracy for the classification.
  • Osamu Manabe, Noriko Oyama-Manabe, Masanao Naya, Masahiko Obara, Yasuka Kikuchi, Tadao Aikawa, Yuuki Tomiyama, Hiroyuki Sugimori, Chietsugu Katoh, Nagara Tamaki, Toshihisa Anzai
    Cardiovascular Imaging Asia 3 (1) 8 - 8 2508-707X 2019
  • Yasuka Kikuchi, Masanao Naya, Noriko Oyama Manabe, Osamu Manabe, Hiroyuki Sugimori, Kohsuke Kudo, Fumi Kato, Tadao Aikawa, Hiroyuki Tsutsui, Nagara Tamaki, Hiroki Shirato
    Magnetic Resonance in Medical Sciences 18 (2) 134 - 141 1347-3182 2019 [Refereed][Not invited]
     
    © 2018 Japanese Society for Magnetic Resonance in Medicine. Purpose: The aim of this study was to verify coronary flow velocity reserve (CFVR) on the left main trunk (LMT) in comparison with myocardial flow reserve (MFR) by 15O-labeled water positron emission tomography (PET) (MFR-PET) in both the healthy adults and the patients with coronary artery disease (CAD), and to evaluate the feasibility of CFVR to detect CAD. Methods: Eighteen healthy adults and 13 patients with CAD were evaluated. CFVR in LMT was estimated by 3T magnetic resonance imaging (MRI) with phase contrast technique. MFR-PET in the LMT territory including anterior descending artery and circumflex artery was calculated as the ratio of myocardial blood flow (MBF)-PET at stress to MBF-PET at rest. Results: There was a significant positive relationship between CFVR and MFR-PET (R = 0.45, P < 0.0001). Inter-observer calculations of CFVR showed good correlation (R2 = 0.93, P < 0.0001). The CFVR in patients with CAD was significantly lower than that in healthy adults (1.90 ± 0.61 vs. 2.77 ± 1.03, respectively, P = 0.01), which were similar to the results of MFR-PET (2.23 ± 0.84 vs. 3.96 ± 1.04, respectively, P < 0.0001). For the detection of patients with CAD, the area under the curve was 0.78 (P = 0.01). The sensitivity was 0.77 and specificity was 0.72 when a cut-off of 2.15 was used. Conclusion: CFVR by 3T was validated with MFR-PET. CFVR could detect the patients with CAD. This method is a simple and reliable index without radiation or contrast material.
  • Suzuko Aoike, Hiroyuki Sugimori, Noriyuki Fujima, Yuriko Suzuki, Yukie Shimizu, Akira Suwa, Kinya Ishizaka, Kohsuke Kudo
    Magnetic Resonance in Medical Sciences 18 (2) 170 - 177 1347-3182 2019 [Refereed][Not invited]
     
    © 2018 Japanese Society for Magnetic Resonance in Medicine. We evaluated 3D pseudo-continuous arterial spin labeling (pCASL) using turbo spin echo with a pseudosteady- state (PSS) readout in comparison with the other major readout methods of 3D spiral and 2D echoplanar imaging (EPI). 3D-PSS produced cerebral blood flow (CBF) values well correlated to those of the 3D spiral readout. By visual evaluation, the image quality of 3D-PSS pCASL was superior to that of 2D-EPI. The 3D-PSS technique was suggested useful as pCASL readout.
  • Yuto Kobayashi, Tamotsu Kamishima, Hiroyuki Sugimori, Shota Ichikawa, Atsushi Noguchi, Michihito Kono, Toshitake Iiyama, Kenneth Sutherland, Tatsuya Atsumi
    Journal of Magnetic Resonance Imaging 48 (3) 687 - 694 1053-1807 2018/09 [Refereed][Not invited]
     
    © 2018 International Society for Magnetic Resonance in Medicine Background: Synovitis, which is a hallmark of rheumatoid arthritis (RA), needs to be precisely quantified to determine the treatment plan. Time–intensity curve (TIC) shape analysis is an objective assessment method for characterizing the pixels as artery, inflamed synovium, or other tissues using dynamic contrast-enhanced MRI (DCE-MRI). Purpose/Hypothesis: To assess the feasibility of our original arterial mask subtraction method (AMSM) with mutual information (MI) for quantification of synovitis in RA. Study Type: Prospective study. Subjects: Ten RA patients (nine women and one man; mean age, 56.8 years; range, 38–67 years). Field Strength/Sequence: 3T/DCE-MRI. Assessment: After optimization of TIC shape analysis to the hand region, a combination of TIC shape analysis and AMSM was applied to synovial quantification. The MI between pre- and postcontrast images was utilized to determine the arterial mask phase objectively, which was compared with human subjective selection. The volume of objectively measured synovitis by software was compared with that of manual outlining by an experienced radiologist. Simple TIC shape analysis and TIC shape analysis combined with AMSM were compared in slices without synovitis according to subjective evaluation. Statistical Tests: Pearson's correlation coefficient, paired t-test and intraclass correlation coefficient (ICC). Results: TIC shape analysis was successfully optimized in the hand region with a correlation coefficient of 0.725 (P < 0.01) with the results of manual assessment regarded as ground truth. Objective selection utilizing MI had substantial agreement (ICC = 0.734) with subjective selection. Correlation of synovial volumetry in combination with TIC shape analysis and AMSM with manual assessment was excellent (r = 0.922, P < 0.01). In addition, negative predictive ability in slices without synovitis pixels was significantly increased (P < 0.01). Data Conclusions: The combination of TIC shape analysis and image subtraction reinforced with MI can accurately quantify synovitis of RA in the hand by eliminating arterial pixels. Level of Evidence: 2. Technical Efficacy: Stage 2. J. Magn. Reson. Imaging 2018;48:687–694.
  • Hiroyuki Sugimori
    Journal of Healthcare Engineering 2018 1753480  2040-2295 2018 [Refereed][Not invited]
     
    © 2018 Hiroyuki Sugimori. This study aimed at elucidating the relationship between the number of computed tomography (CT) images, including data concerning the accuracy of models and contrast enhancement for classifying the images. We enrolled 1539 patients who underwent contrast or noncontrast CT imaging, followed by dividing the CT imaging dataset for creating classification models into 10 classes for brain, neck, chest, abdomen, and pelvis with contrast-enhanced and plain imaging. The number of images prepared in each class were 100, 500, 1000, 2000, 3000, 4000, 5000, 6000, 7000, 8000, 9000, and 10,000. Accordingly, the names of datasets were defined as 0.1K, 0.5K, 1K, 2K, 3K, 4K, 5K, 6K, 7K, 8K, 9K, and 10K, respectively. We subsequently created and evaluated the models and compared the convolutional neural network (CNN) architecture between AlexNet and GoogLeNet. The time required for training models of AlexNet was lesser than that for GoogLeNet. The best overall accuracy for the classification of 10 classes was 0.721 with the 10K dataset of GoogLeNet. Furthermore, the best overall accuracy for the classification of the slice position without contrast media was 0.862 with the 2K dataset of AlexNet.
  • Motoshi Fujimori, Tamotsu Kamishima, Masaru Kato, Yumika Seno, Kenneth Sutherland, Hiroyuki Sugimori, Mutsumi Nishida, Tatsuya Atsumi
    British Journal of Radiology 91 (1086) 20170748  0007-1285 2018 [Refereed][Not invited]
     
    © 2018 The Authors. Published by the British Institute of Radiology. Objective: Power Doppler ultrasonography (PDUS) and MRI are independently useful to predict structural damage in patients with rheumatoid arthritis (RA). We hypothesize that there is a complementary relationship between these modalities. The aim of this study is, therefore, to investigate the usefulness of the predictive value of composite assessment of PDUS and contrast-enhanced MRI in radiographic outcomes in patients with RA. Methods: 20 patients (17 females and 3 males) with RA on disease-modifying antirheumatic drugs underwent PDUS and MRI of both hands at baseline. Radiography of the bilateral hands was performed at baseline and at 1 year. Articular synovitis on PDUS was evaluated according to quantitative measurement. Synovitis, bone marrow edema and bone erosion were scored according to the RA MRI scoring method. The changes of joint space narrowing and bone erosion on radiograph were assessed by the Sharp/van der Heijde method. We applied t-statistics to combine the assessment of quantitative PDUS with semiquantitative MRI. Results: Structural damage progression for radiography was not correlated with any evaluations for MRI, while it showed significant correlation with synovitis on PDUS (rs = 0.597, p = 0.005). The composite assessment of both modalities (synovitis for PDUS and bone marrow edema for MRI) was correlated with structural damage progression on radiograph (rs = 0.792, p < 0.0001). Conclusion: Composite assessment of PDUS and MRI may have a stronger predictive value in radiographic progression than PDUS or MRI alone in RA. Advances in knowledge: Composite assessment of PDUS and MRI may be an effective predictor of structural damage in RA.
  • Yuriko Suzuki, Noriyuki Fujima, Tetsuo Ogino, James Alastair Meakin, Akira Suwa, Hiroyuki Sugimori, Marc Van Cauteren, Matthias J.P. van Osch
    Magnetic Resonance in Medicine 79 (1) 224 - 233 0740-3194 2018/01 [Refereed][Not invited]
     
    © 2017 International Society for Magnetic Resonance in Medicine Purpose: Noncontrast 4D-MR-angiography (MRA) using arterial spin labeling (ASL) is beneficial because high spatial and temporal resolution can be achieved. However, ASL requires acquisition of labeled and control images for each phase. The purpose of this study is to present a new accelerated 4D-MRA approach that requires only a single control acquisition, achieving similar image quality in approximately half the scan time. Methods: In a multi-phase Look-Locker sequence, the first phase was used as the control image and the labeling pulse was applied before the second phase. By acquiring the control and labeled images within a single Look-Locker cycle, 4D-MRA was generated in nearly half the scan time of conventional ASL. However, this approach potentially could be more sensitive to off-resonance and magnetization transfer (MT) effects. To counter this, careful optimizations of the labeling pulse were performed by Bloch simulations. In in-vivo studies arterial visualization was compared between the new and conventional ASL approaches. Results: Optimization of the labeling pulse successfully minimized off-resonance effects. Qualitative assessment showed that residual MT effects did not degrade visualization of the peripheral arteries. Conclusion: This study demonstrated that the proposed approach achieved similar image quality as conventional ASL-MRA approaches in just over half the scan time. Magn Reson Med 79:224–233, 2018. © 2017 International Society for Magnetic Resonance in Medicine.
  • Hiroyuki Sugimori, Noriyuki Fujima, Yuriko Suzuki, Hiroyuki Hamaguchi, Kinya Ishizaka, Kohsuke Kudo
    Magnetic Resonance Imaging 43 136 - 143 0730-725X 2017/11 [Refereed][Not invited]
     
    © 2017 Elsevier Inc. Purpose To establish an optimized sequence design for fast acceleration of arterial spin labeling (ASL)-based time-resolved magnetic resonance angiography (MRA) by acquisition of control and labeled images in the same shot (fast ACTRESS) and a scan time of < 1 min, for the evaluation of intracranial vessels. Materials and methods Ten healthy volunteers with no unilateral symptomatic arterial stenosis, who underwent 3-tesla MRI, were investigated. Imaging parameters for the fast ACTRESS sequence were set with an acquisition time of 45 s. During post-processing, the first phase in the multi-phase readout, which was defined as the control image, was subtracted from each of the other phases. Thus, four-dimensional (4D)-MRA images of each phase were obtained. The maximum intensity projection was used for the reconstruction of 4D-MRA images and time-to-signal intensity curves (TIC) obtained for each vessel. The area under the curve (AUC), peak time, and maximum signal intensity were obtained from TIC. The different labeling types were broadly divided into six groups: L1, L2, L3, L4, L5, and L6 according to the actual number of labeling pulse. Results A total of 5040 regions of interest were evaluated. The peak SI of L3, except for those in the A2 segment of the anterior cerebral artery, was significantly higher than that of L5. However, there were no significant differences between L4 and L5. Although the AUCs of L3 and L4 for anterior circulation were relatively higher than that of the other subgroups, the AUC of L3 was significantly higher than that of L4. Conclusion The fast ACTRESS was optimized and indicated that the labeling type of L3 was the most appropriate for the well visualization of intracranial arteries. The fast ACTRESS sequence was useful to acquire well-delineated images of intracranial vessels in ˂1 min.
  • Taro Sakashita, Tamotsu Kamishima, Hiroyuki Sugimori, Minghui Tang, Atsushi Noguchi, Michihito Kono, Kenneth Sutherland, Tatsuya Atsumi
    Magnetic Resonance in Medical Sciences 16 (1) 78 - 83 1347-3182 2017 [Refereed][Not invited]
     
    ©2016 Japanese Society for Magnetic Resonance in Medicine. We examined the capability of a gray-scale arterial spin labeling blood flow pattern variation (BFPV) map with two different post labeling delay (PLD) times to discriminate pannus in patients with rheumatoid arthritis (RA) at 3T. There was a statistically significant difference in the BFPV values between artery, pannus, and surrounding tissue. Furthermore, the color-coded BFPV map was able to accurately distinguish pannus from other tissues. These results suggest this approach may be capable of identifying pannus noninvasively.
  • Hiroyuki Hamaguchi, Khin Khin Tha, Hiroyuki Sugimori, Mitsuhiro Nakanishi, Shin Nakagawa, Taro Fujiwara, Hirokazu Yoshida, Sayaka Takamori, Hiroki Shirato
    Neuroradiology Journal 29 (4) 254 - 259 1971-4009 2016/08/01 [Refereed][Not invited]
     
    © SAGE Publications. The effect of respiratory gating on the major diffusion-imaging metrics and that of cardiac gating on mean kurtosis (MK) are not known. For evaluation of whether the major diffusion-imaging metrics - MK, fractional anisotropy (FA), and mean diffusivity (MD) of the brain - varied between gated and non-gated acquisitions, respiratory-gated, cardiac-gated, and non-gated diffusion-imaging of the brain were performed in 10 healthy volunteers. MK, FA, and MD maps were constructed for all acquisitions, and the histograms were constructed. The normalized peak height and location of the histograms were compared among the acquisitions by use of Friedman and post hoc Wilcoxon tests. The effect of the repetition time (TR) on the diffusion-imaging metrics was also tested, and we corrected for its variation among acquisitions, if necessary. The results showed a shift in the peak location of the MK and MD histograms to the right with an increase in TR (p ≤ 0.01). The corrected peak location of the MK histograms, the normalized peak height of the FA histograms, the normalized peak height and the corrected peak location of the MD histograms varied significantly between the gated and non-gated acquisitions (p < 0.05). These results imply an influence of respiration and cardiac pulsation on the major diffusion-imaging metrics. The gating conditions must be kept identical if reproducible results are to be achieved.
  • Taro Sakashita, Tamotsu Kamishima, Yuto Kobayashi, Hiroyuki Sugimori, Minghui Tang, Kenneth Sutherland, Atsushi Noguchi, Michihito Kono, Tatsuya Atsumi
    British Journal of Radiology 89 (1061) 0007-1285 2016 [Refereed][Not invited]
     
    © 2016 The Authors. Objective: To improve on the reproducibility and sensitivity of the assessment of patients with rheumatoid arthritis (RA), two semi-automated measurement methods of the area of enhancing pannus (AEP), based on thresholding (AEP-THRES) and pixel-by-pixel time-intensity curve analysis (AEP-TIC), were evaluated as an alternative for the gold-standard manual contouring method (AEP-MANUAL). Methods: 8 patients (7 females and 1 male) with RA of the wrist or finger joints participated in the study. A threedimensional contrast-enhanced dynamic sequence was used at 3 T. After identifying the most relevant time-intensity curve (TIC) shape in terms of synovitis by comparing with the synovitis score using the RA-MRI scoring system, three different approaches for measuring the AEP were performed. Spearman's test of rank correlation was used to compare AEPs via two semi-automated methods (AEP-THRES and AEP-TIC) against manual segmentation (AEP-MANUAL) in the entire hand region as well as thewrist and the finger regions. Results: The TIC shape of washout after fast initial enhancement had excellent correlation with synovitis score (r50.809). The correlation coefficient between AEP-TIC and AEP-MANUAL was evaluated to be better than that of AEP-THRES and AEP-MANUAL in the wrist region (AEP-THRES: r50.716, AEP-TIC: r50.815), whereas these were of comparable accuracy for the entire hand and the finger regions. Conclusion: This study suggests that TIC analysis may be an alternative to manual contouring for pannus quantification and provides important clinical information of the extent of the disease in patients with RA.
  • Hiroyuki Sugimori, Noriyuki Fujima, Yuriko Suzuki, Hiroyuki Hamaguchi, Motomichi Sakata, Kohsuke Kudo
    Magnetic Resonance Imaging 33 (10) 1338 - 1344 0730-725X 2015/12 [Refereed][Not invited]
     
    © 2015 Elsevier Inc.. Purpose: Arterial spin labeling (ASL) methods have been widely used for evaluation of cerebral blood flow (CBF) by magnetic resonance imaging. However, ASL methods require setting of the post labeling delay (PLD) time for obtaining images. As the hemodynamic status cannot be estimated in each patient, the resultant quantitative values of blood flow may not be accurate. The multi-phase pseudo continuous arterial spin labeling (pCASL) method can be used to obtain images at various time-points. The purpose of this study was to create the transit-time maps for correcting the delayed blood flow and evaluate CBF using the transit-time maps obtained by the multi-phase pCASL method. Materials and Methods: Twelve patients who underwent both 3.0-tesla magnetic resonance imaging (MRI) and single photon emission computed tomography with iodine-123-N-isopropyl-p-iodoamphetamine (123I-IMP) were investigated. This study was approved by the institutional review board of our institution. MRI acquisitions included PLD time-fixed (1525. ms) and multi-phase pCASL sequences. The transit-time maps were calculated from multi-phase pCASL images by software. The transit-time maps were applied to PLD-fixed pCASL images pixel by pixel, for calculating the CBF value corrected for peak blood transit time. Regions of interest were drawn on the brain. IMP-CBF, ASL-CBF (default and corrected) and transit time were measured for each segment. Results: Twelve patients and 264 segments were investigated. The mean IMP-CBF, ASL-CBF (default, corrected) and transit time were 28.4, 23.0, 29.6, [ml/min/100. g] and 1977.5 [ms], respectively. There were no significant differences between IMP-CBF and ASL-CBF (corrected). Conclusion: CBF values can be corrected by using the transit-time maps obtained using the multi-phase pCASL method.
  • Yuuki Tomiyama, Osamu Manabe, Noriko Oyama-Manabe, Masanao Naya, Hiroyuki Sugimori, Kenji Hirata, Yuki Mori, Hiroyuki Tsutsui, Kohsuke Kudo, Nagara Tamaki, Chietsugu Katoh
    Journal of Magnetic Resonance Imaging 42 (3) 754 - 762 1053-1807 2015/09/01 [Refereed][Not invited]
     
    © 2014 Wiley Periodicals, Inc. Background To develop and validate a method for quantifying myocardial blood flow (MBF) using dynamic perfusion magnetic resonance imaging (MBFMRI) at 3.0 Tesla (T) and compare the findings with those of 15O-water positron emission tomography (MBFPET). Methods Twenty healthy Male volunteers underwent magnetic resonance imaging (MRI) and 15O-water positron emission tomography (PET) at rest and during adenosine triphosphate infusion. The single-tissue compartment model was used to estimate the inflow rate constant (K1). We estimated the extraction fraction of Gd-DTPA using K1 and MBF values obtained from 15O-water PET for the first 10 subjects. For validation, we calculated MBFMRI values for the remaining 10 subjects and compared them with the MBFPET values. In addition, we compared MBFMRI values of 10 patients with coronary artery disease with those of healthy subjects. Results The mean resting and stress MBFMRI values were 0.76±0.10 and 3.04±0.82 mL/min/g, respectively, and showed excellent correlation with the mean MBFPET values (r=0.96, P<0.01). The mean stress MBFMRI value was significantly lower for the patients (1.92±0.37) than for the healthy subjects (P<0.001). Conclusion The use of dynamic perfusion MRI at 3T is useful for estimating MBF and can be applied for patients with coronary artery disease. J. Magn. Reson. Imaging 2015;42:754-762.
  • Satoko Sudo, Naoya Hattori, Osamu Manabe, Fumi Kato, Rie Mimura, Keiichi Magota, Hiroyuki Sugimori, Kenji Hirata, Noriaki Sakuragi, Nagara Tamaki
    European Journal of Nuclear Medicine and Molecular Imaging 42 (5) 676 - 684 1619-7070 2015/03/05 [Refereed][Not invited]
     
    © 2014, Springer-Verlag Berlin Heidelberg. Purpose: The staging of endometrial cancer requires surgery which carries the risk of morbidity. FDG PET/CT combined with anatomical imaging may reduce the number of unnecessary lymphadenectomies by demonstrating the risk of extrapelvic infiltration. The purpose of this study was to optimize FDG PET/CT diagnostic criteria for risk assessment in endometrial cancer after first-line risk triage with MRI.Conclusion: FDG PET/CT diagnostic criteria may need adjustment based on the anatomical information provided by MRI. The optimized criteria can predict the risk of pathology-proven LVSI correctly in 83.8 % of patients before surgery, and thus would improve presurgical treatment planning.Results: Presurgical assessment using MRI was positive for deep (>50 %) myometrial invasion in 17 patients. The optimal FDG PET/CT diagnostic criteria vary depending on the results of MRI. Specifically, SUVmax (≥16.0) was used to indicate LVSI risk with an overall diagnostic accuracy of 88.2 % in patients with MRI findings showing myometrial invasion. High-grade malignancy did not correlate with any of metabolic profiles in this patient group. In the remaining patients without myometrial invasion, lesion glycolysis (LG) or metabolic volume were better indicators of LVSI than SUVmax with the same diagnostic accuracy of 80.0 %. In addition, LG (≥26.9) predicted high-grade malignancy with an accuracy of 72.2 %. Using the optimized cut-off criteria for LVSI, glucose metabolic profiling of primary lesions correctly predicted lymph node metastasis with an accuracy of 73.0 %, which was comparable with the accuracy of visual assessment for lymph node metastasis using MRI and FDG PET/CT.Methods: The study population comprised 37 patients who underwent curative surgery for the treatment of endometrial cancer. First, the risk of extrapelvic infiltration was triaged using MRI. Second, multiple glucose metabolic profiles of the primary lesion were assessed with FDG PET/CT, and these were correlated with the histopathological risk of extrapelvic infiltration including lymphovascular space invasion (LVSI) and high-grade malignancy (grades 2 and 3). The results of histological correlation were used to adjust FDG PET/CT diagnostic criteria.
  • Kinya Ishizaka, Fumi Kato, Satoshi Terae, Suzuko Mito, Noriko Oyama-Manabe, Tamotsu Kamishima, Mitsuhiro Nakanishi, Hiroyuki Sugimori, Hiroyuki Hamaguchi, Hiroki Shirato
    Radiological Physics and Technology 8 (1) 4 - 12 1865-0333 2015 [Refereed][Not invited]
     
    © 2014, Japanese Society of Radiological Technology and Japan Society of Medical Physics. In this study, we aimed to compare fat-suppression homogeneity on breast MR imaging by using dual-source parallel radiofrequency excitation and image-based shimming (DS-IBS) with single-source radiofrequency excitation with volume shim (SS-Vol) at 3 Tesla. Twenty patients were included. Axial three-dimensional T1-weighted turbo-field-echo breast images with DS-IBS and SS-Vol were obtained. Fat suppression was scored with four grade points. The contrast of the pectoral muscle and the fat in each breast area was obtained in the head medial, head lateral, foot medial, and foot lateral areas. The axillary space was calculated and compared between DS-IBS and SS-Vol. The average DS-IBS score was significantly higher than that of SS-Vol. The mean contrasts of fat in the foot lateral areas and axillary spaces on DS-IBS images were significantly higher than on SS-Vol images.
  • Takahiro Sato, Ichizo Tsujino, Noriko Oyama-Manabe, Hiroshi Ohira, Yoichi M. Ito, Hiroyuki Sugimori, Asuka Yamada, Chisa Takashina, Taku Watanabe, Masaharu Nishimura
    International Journal of Cardiovascular Imaging 29 (8) 1799 - 1805 1569-5794 2013/12 [Refereed][Not invited]
     
    The present study examined whether tricuspid annular plane systolic excursion (TAPSE) can simply predict right ventricular ejection fraction (RVEF) in patients with pulmonary hypertension (PH). The TAPSE cut-off value to predict reduced RVEF was also evaluated. The association between TAPSE and cardiac magnetic resonance imaging (CMRI)-derived RVEF was examined in 53 PH patients. The accuracy of the prediction equation to calculate RVEF using TAPSE was also evaluated. In PH patients, TAPSE was strongly correlated with CMRI-derived RVEF in PH patients (r = 0.86, p < 0.0001). We then examined the accuracy of the two equations: the original regression equation (RVEF = 2.01 × TAPSE + 0.6) and the simplified prediction equation (RVEF = 2 × TAPSE). Bland-Altman plot showed that the mean difference ± limits of agreement was 0.0 ± 10.6 for the original equation and -0.6 ± 10.6 for the simplified equation. Intraclass correlation coefficient was 0.84 for the original and 0.82 for the simplified equation. Normal RVEF was considered to be ≥40 % based on the data from 53 matched controls, and the best TAPSE cut-off value to determine reduced RVEF (<40 %) was calculated to be 19.7 mm (sensitivity 88.9 %, specificity 84.6 %). A simple equation of RVEF = 2 × TAPSE enables easy prediction of RVEF using TAPSE, an easily measurable M-mode index of echocardiography. TAPSE of 19.7 mm predicts reduced RVEF in PH patients with clinically acceptable sensitivity and specificity. © 2013 Springer Science+Business Media Dordrecht.
  • Manami Nakamura, Takeshi Makabe, Masaki Ichikawa, Ryohei Hatakeyama, Hiroyuki Sugimori, Motomichi Sakata
    Nihon Hoshasen Gijutsu Gakkai zasshi 69 (11) 1261 - 1265 0369-4305 2013/11 [Refereed][Not invited]
     
    Vessel wall imaging using radial scanning does not use a blood flow suppression pulse with gated acquisition. It has been proposed that there may not be a flow void effect if the flow rate is slow; however, this has yet to be empirically tested. To clarify the relationship between the signal intensity of the vessel lumen and the blood flow rate in a flow phantom, we investigated the usefulness of vessel wall imaging at 3.0 tesla (T). We measured the signal intensity while changing the flow rate in the flow phantom. Radial scanning at 1.5 T showed sufficient flow voids at above medium flow rates. There was no significant difference in lumen signal intensity at the carotid artery flow rate. The signal intensity of the vessel lumen decreased sufficiently using the radial scan method at 3.0 T. We thus obtained sufficient flow void effects at the carotid artery flow rate. We conclude this technique to be useful for evaluating plaque if high contrast can be maintained for fixed tissue (such as plaque) and the vessel lumen.
  • Sato Takahiro, Tsujino Ichizo, Oyama-Manabe Noriko, Ohira Hiroshi, Ito Yoichi. M, Sugimori Hiroyuki, Yamada Asuka, Takashina Chisa, Watanabe Taku, Nishimura Masaharu
    RESPIROLOGY 18 20  1323-7799 2013/11 [Refereed][Not invited]
  • Hiroyuki Sugimori, Noriko Oyama-Manabe, Kinya Ishizaka, Hiroyuki Hamaguchi, Motomichi Sakata
    Magnetic Resonance in Medical Sciences 12 (1) 69 - 75 1347-3182 2013/03/25 [Refereed][Not invited]
     
    We compared peak circumferential strain (Ecc) values with spatial modulation of magnetization (SPAMM) and strain-encoded (SENC) magnetic resonance (MR) imaging at 3 tesla. Correlation coeffcients of the averaged peak Ecc values of the 2 methods were statistically significant. However, the average peak Ecc value was significantly lower with SPAMM (-13.5z±3.3z) than with SENC(- 21.6z±3.4z) (P<0.0001). The SENC method showed higher circumferential strain than the SPAMM method at 3T. © 2013 Japanese Society for Magnetic Resonance in Medicine.
  • Hiroyuki Sugimori, Mitsuhiro Nakanishi, Noriyuki Fujima, Kinya Ishizaka, Suzuko Mito, Hiroyuki Hamaguchi, Motomichi Sakata
    Radiological Physics and Technology 6 (1) 86 - 91 1865-0333 2013/01 [Refereed][Not invited]
     
    Most arterial spin labeling techniques apply the constant post-labeling delay time after the blood-labeling time point on the target artery. As the hemodynamic status cannot be estimated in each patient, quantitative values of the blood flow may not be accurate. To overcome this problem, we performed renal perfusion imaging of human kidneys using multi-phase echo-planar magnetic resonance imaging and signal targeting with an alternating radiofrequency (EPISTAR) sequence at 3-T magnetic resonance imaging. Multi-phase EPISTAR obtained 17 phases every 100 ms between 250 and 1850 ms from the arterial-labeling time point. The highest signal-intensity image obtained using multi-phase images was applied to renal blood flow (RBF) calculations. In five healthy volunteers, the mean cortical RBF was 286.6 ± 48.7 mL/100 g/min. This value was not significantly different from those in four previous studies. This technique was more useful than previous studies, in that multi-phase images could confirm the hemodynamic status on RBF calculations. © 2012 Japanese Society of Radiological Technology and Japan Society of Medical Physics.
  • Noriko Oyama-Manabe, Naoki Ishimori, Hiroyuki Sugimori, Marc Van Cauteren, Kohsuke Kudo, Osamu Manabe, Tomoyuki Okuaki, Tamotsu Kamishima, Yoichi M. Ito, Hiroyuki Tsutsui, Khin Khin Tha, Satoshi Terae, Hiroki Shirato
    European Radiology 21 (11) 2362 - 2368 0938-7994 2011/11 [Refereed][Not invited]
     
    Objectives: To investigate whether subendocardial and transmural myocardial infarction can be identified and differentiated using the peak circumferential and longitudinal strains measured by fast strain-encoded (SENC). Methods: Nineteen patients with ischemic heart diseases underwent imaging with fast SENC and late gadolinium enhancement (LGE) MRI at 3 T. Fast SENC measurements were performed in three short-axis slices (basal, mid-ventricular and apical levels) and one long-axis view (four-chamber) to assess peak longitudinal and circumferential systolic strains. Results: All patients showed myocardial infarction with an average of 7 positive LGE segments. A total of 304 segments for longitudinal strains (LS) and 114 segments for circumferential strains (CS) could be analysed. Positive LGE segments showed lower peak CS and LS compared with the no LGE segments (P<0.0001 for both). Segments with subendocardial infarction showed reduced CS and LS compared with the no LGE segments (P<0.0001 for both). There was a significant difference in CS between subendocardial and transmural infarct segments (P=0.03), but no significant difference in LS between them (P=0.64). Conclusions: Fast SENC can identify old myocardial infarction and differentiate subendocardial from transmural infarction. © 2011 European Society of Radiology.
  • Kinya Ishizaka, Noriko Oyama, Suzuko Mito, Hiroyuki Sugimori, Mitsuhiro Nakanishi, Tomoyuki Okuaki, Hiroki Shirato, Satoshi Terae
    Magnetic Resonance in Medical Sciences 10 (1) 41 - 48 1347-3182 2011 [Refereed][Not invited]
     
    Purpose: We evaluated and compared the reproducibility, diagnostic accuracy, and sequence dependency of the fat fraction (FF) determined by 3-point Dixon (DIXON) and multi-echo gradient-echo (MEGE) methods to those of the FF determined by magnetic resonance spectroscopy (MRS). Methods: Our study included 98 volunteers, ten of whom underwent scanning twice to evaluate sequence reproducibility. We compared the FFs determined by the DIXON and MEGE methods to that by MRS as the gold standard, calculated sensitivity and specificity for each image analysis method at a threshold value of 6.25z of spectroscopic value, and used Pearson's correlation coefficient and Bland-Altman analysis to compare agreement among the repeated measurements and FF values with the 3 methods, in 98 volunteers. Results: There was no significant difference in repeated scans in any sequence with Wilcoxon's t-test. Each correlation coefficient (r) exceeded 0.930 for the repeated measurements of all 3 sequences. Sensitivity of DIXON was 82z and specificity, 96z; sensitivity of MEGE was 70z and specificity, 99z. The FFs determined by DIXON and MEGE correlated well with that by MRS (r=0.920) but showed significant difference (paired t-test, P o0.001). The mean difference between the FF determined by DIXON and that by MEGE were 0.93 and -1.16, respectively. The slope of the regression lines as determined by DIXON was -0.655 (P o0.001) and that by MEGE was -0.527 (P o0.001). When the FF by MRS was less than 6.25z, the FF values by DIXON and MEGE were significantly higher; when the spectroscopic value was greater than 6.25z, their values were significantly lower. Conclusion: We demonstrated the high reproducibility of each FF measurement using MRS, DIXON, and MEGE. Compared to MRS, both DIXON and MEGE showed high sensitivity and specificity for determining FF. The FFs by DIXON and MEGE showed sequence dependency because DIXON had proportional and additional errors, and MEGE had a proportional error.
  • Suzuko Mito, Kinya Ishizaka, Mitsuhiro Nakanishi, Hiroyuki Sugimori, Hiroyuki Hamaguchi, Tomoyasu Tsuzuki
    Nihon Hoshasen Gijutsu Gakkai zasshi 67 (6) 654 - 660 0369-4305 2011 [Refereed][Not invited]
     
    The purposes of this study were to determine optimum flip angles (FAs) and to compare the effectiveness of fat suppression and signal homogeneity among three techniques, spectral attenuated with inversion recovery (SPAIR), principle of selective excitation technique (PROSET), and three-point DIXON technique (DIXON), of the bilateral breast dynamic sequence acquired using the optimum FA at 3.0 T. Using a homemade phantom that represented a tumor, fat, and a mammary gland, the optimum FAs were determined from the change of fat signal intensity, signal-to-noise ratio (SNR) of the mammary gland, and contrast ratio (CR) between the tumor and mammary gland. The effectiveness of fat suppression and signal homogeneity were compared in ten breast cancer cases, using the CR between fat and pectoralis muscle signal intensities and the standard deviation (SD) of fat signal intensity, respectively. The optimum FAs for SPAIR, PROSET, and DIXON were 10, 20, and 20 degrees, respectively. The mean CR between fat and pectoralis muscle signal intensities achieved using SPAIR, PROSET, and DIXON were 0.19, 0.30 and 0.40, respectively, and the mean SDs of the fat signal intensities were 90.2, 103.1, and 30.5, respectively. The DIXON technique provided better fat suppression and signal homogeneity than the other two techniques. The results of this study suggest the possible application of the DIXON technique in combination with the optimum FA setting as an effective fat suppression technique for the bilateral breast dynamic sequence at 3.0 T.
  • Hiroyuki Sugimori, Takahiro Uno, Akira Yanagisawa
    Nippon Hoshasen Gijutsu Gakkai zasshi 65 (5) 612 - 619 0369-4305 2009/05/20 [Refereed][Not invited]
     
    The evaluation of myocardium characterization is an important role in cardiac MRI. The dark-blood (DB) sequence is used for non-enhanced T2-weighted myocardial images. The purpose of this study was to evaluate and optimize the DB T2WI sequence in myocardium images. We changed the parameters TE, echo train length (ETL), inversion time (TI), and fat suppression method, respectively. Data acquisition with end-diastolic phase was effective for avoiding the blur that was caused by cardiac motion. Consequently, the optimal setting of ETL and TI was important for myocardial images. STIR was suitable for fat suppression in unstable susceptibility. Setting the parameters synchronized with the cardiac cycle provided optimal myocardial images in DB T2WI.
  • Tsutomu Inaoka, Hiroyuki Sugimori, Yoshihito Sasaki, Koji Takahashi, Kazuo Sengoku, Nobuhisa Takada, Tamio Aburano
    American Journal of Roentgenology 189 (6) 1316 - W308 0361-803X 2007/12 [Refereed][Not invited]
     
    OBJECTIVE. The great potential of MRI for assessing gastrointestinal abnormalities in fetuses has been described. T1-weighted images may add additional information to T2-weighted images in diagnosing fetal gastrointestinal abnormalities. The objective of this study was to assess the performance of a 3D volumetric interpolated breath-hold sequence (VIBE) in evaluating the normal and abnormal fetal gastrointestinal tract. CONCLUSION. VIBE provides high-quality T1-weighted and 3D MR colonography images for the evaluation of the normal and abnormal gastrointestinal tract in fetuses, and 3D MR colonography provides excellent delineation of the meconium.
  • Hiroyuki Sugimori, Naka Sakamoto, Shunsuke Natori, Akira Yanagisawa, Takahiro Uno, Makoto Kubota
    Nippon Hoshasen Gijutsu Gakkai zasshi 63 (6) 661 - 666 0369-4305 2007/06/20 [Refereed][Not invited]
     
    BACKGROUND: Delayed-enhancement MRI is a technique that has significant clinical usefulness, particularly for myocardial viability determination in ischemic heart disease. Delayed enhanced images have been acquired by using the inversion recovery(IR)method. It is necessary for the IR method to select optimal inversion time(TI). Recently, the phase-sensitive inversion recovery(PSIR)method has been developed to detect Gd-DTPA enhanced myocardium. PURPOSE: To compare the IR method with the PSIR method by acquiring Gd-DTPA solution phantoms A(0.05 mmol/l)and B(0.04 mmol/l)in various parameters. METHOD: Images were acquired using a turbo-fast low angle shot(t-flash)sequence in each method. RESULTS: The null point of signal intensity(SI)shortened as the flip angle(FA)and segments increased in the IR method. Excess segments also caused the duration of breath holding to be extended. The IR method might cause reversed SI between normal and Gd-DTPA enhanced myocardium if the optimal TI was not carefully selected. On the other hand, PSIR had no problem in obtaining phase-sensitive images that were converted into positive SI keeping inverse longitudinal magnetization. The PSIR method avoided the need to select optimal TI and loss of contrast. CONCLUSION: The PSIR method was a useful sequence for delayed-enhancement MRI to detect Gd-DTPA enhanced myocardium.
  • Tsutomu Inaoka, Koji Takahashi, Masayuki Mineta, Tomonori Yamada, Noriyuki Shuke, Atsutaka Okizaki, Kenichi Nagasawa, Hiroyuki Sugimori, Tamio Aburano
    Radiology 243 (3) 869 - 876 0033-8419 2007/06 [Refereed][Not invited]
     
    Purpose: To prospectively evaluate chemical shift magnetic resonance (MR) imaging for differentiating thymic hyperplasia from tumors of the thymus gland. Materials and Methods: The institutional review board approved this study; informed consent was obtained and patient confidentiality was protected. The authors assessed 41 patients (17 male, 24 female; age range, 16-78 years) in whom thymic lesions were seen at chest computed tomography. Patients were assigned to a hyperplasia group (n = 23) (18 patients with hyperplastic thymus associated with Graves disease and five with rebound thymic hyperplasia) and a tumor group (n = 18) (seven patients with thymomas, four with invasive thymomas, five with thymic cancers, and two with malignant lymphomas). T2-weighted fast spin-echo and T1-weighted in-phase and opposed-phase MR images were obtained in all patients and visually assessed. A chemical shift ratio (CSR), determined by comparing the signal intensity of the thymus gland with that of the paraspinal muscle, was calculated for quantitative analysis. Mean CSRs for the patient groups and subgroups were analyzed by using Welch t and Newman-Keuls tests. P < .05 indicated a significant difference. Results: The thymus gland had homogeneous signal intensity in all 23 patients in the hyperplasia group and in 12 of the 18 patients in the tumor group. The mean CSR (± standard deviation) was 0.614 ± 0.130 in the hyperplasia group and 1.026 ± 0.039 in the tumor group. Mean CSRs in the patients with a hyperplastic thymus and Graves disease, rebound thymic hyperplasia, thymoma, invasive thymoma, thymic cancer, and malignant lymphoma were 0.594 ± 0.120, 0.688 ± 0.154, 1.033 ± 0.043, 1.036 ± 0.040, 1.020 ± 0.044, and 0.997 ± 0.010, respectively. The difference in CSR between the hyperplasia and tumor groups was significant (P < .001). Mean CSRs in the hyperplasia subgroups were lower than those in the tumor subgroups (P < .001). All hyperplasia group patients had an apparent decrease in thymus gland signal intensity at chemical shift MR imaging; no tumor group patients had a decrease in thymus gland signal intensity. Conclusion: Chemical shift MR imaging can be used to differentiate thymic hyperplasia from thymic tumors. © RSNA, 2007.
  • Koji Takahashi, Brad Thompson, William Stanford, Yutaka Sato, Kenichi Nagasawa, Hiroaki Sato, Makoto Kubota, Ayako Kashiba, Hiroyuki Sugimori
    American Journal of Roentgenology 187 (2) 389 - 397 0361-803X 2006/08 [Refereed][Not invited]
     
    OBJECTIVE. Delineation of the interlobar fissures on multiplanar reconstruction (MPR) images is useful to assess masses at the fissures for invasion into adjacent lobes. We performed this study to determine the appropriate MDCT protocol to visualize the interlobar fissures on sagittal MPR images. MATERIALS AND METHODS. For the phantom studies, radiographic film was used to replicate the interlobar fissures. For the clinical studies, we obtained MDCT scans of 130 patients with normal interlobar fissures. Visualization of the interlobar fissures on sagittal MPR was assessed using the following scanning parameters: scan collimations of 0.5, 1, 2, and 3 mm with helical pitches of 1 and 1.5 for the phantom studies; and scan collimations of 0.5, 1, 2, and 3 mm with a helical pitch of 1.5 and a scan collimation of 2 mm with a helical pitch of 1 for the clinical studies. RESULTS. To visualize fissures as a sharp line, a 0.5- or 1-mm collimation was required for the major fissure and 0.5 mm for the minor fissure in the phantom studies. In the clinical studies, 0.5-mm-collimation MPR images depicted interlobar fissures as a sharp line in all cases. Fissures on MPR images using 1-, 2-, and 3-mm collimations appeared as a sharp line in 77.5-95.0%, 0-43.3%, and 0% of cases, respectively. CONCLUSION. Volume data obtained using a 1-mm collimation are required to visualize all the interlobar fissures as a sharp line on sagittal MPR images except the minor fissure and superior portion of the right major fissure, for which a 0.5-mm collimation is required. © American Roentgen Ray Society.
  • Yoshihito Sasaki, Toshinobu Miyamoto, Yasuhiro Hidaka, Hisashi Satoh, Naoyuki Takuma, Kazuo Sengoku, Hiroyuki Sugimori, Tsutomu Inaoka, Tamio Aburano
    Magnetic Resonance Imaging 24 (2) 201 - 203 0730-725X 2006/02 [Refereed][Not invited]
     
    A 24-year-old woman (Gravida I, Para I) at estimated 32 weeks of pregnancy was referred to our department for evaluation of a suspected fetal gastroschisis. Ultrasound scan revealed multiple loops of dilated bowel outside the fetal abdomen and absence of membrane surrounding the herniated loops of the intestines. Three-dimensional (3D) magnetic resonance imaging was performed to obtain more information on the bowel both outside and inside the abdomen. Images were constructed with T1-weighted fat-suppressed 3D fast low-angle shot sequences using a maximum intensity projection algorithm. The 3D images made possible the realization of fetal bowel conditions with greater definition and accuracy. © 2006 Elsevier Inc. All rights reserved.

MISC

  • 深層学習による体幹部X線CTのスライス位置を限定しない体重推定単一モデルの開発
    市川 翔太, 杉森 博行  日本放射線技術学会総会学術大会予稿集  80回-  232  -232  2024/03
  • 猪股 壮一郎, 吉村 高明, 唐 明輝, 市川 翔太, 杉森 博行  北海道放射線技術雑誌  95-  (95)  46  -46  2023/11
  • 境田 みう, 吉村 高明, 唐 明輝, 市川 翔太, 杉森 博行  北海道放射線技術雑誌  95-  (95)  48  -48  2023/11
  • 狩野 麻名美, 爰地 祐次, 中西 一彰, 川嶋 雄平, 川口 礼子, 佐々木 淳, 小野 雅子, 杉森 博行  函館医学誌  47-  (1)  12  -15  2023/09
  • 深層学習を用いた局所脳血流SPECT検査における撮像時間短縮の検討
    及川 青亮, 阪井 純, 安斉 公雄, 藤原 雄介, 杉森 博行  日本放射線技術学会雑誌  79-  (9)  1098  -1098  2023/09
  • Deep Learningを用いたマンモグラフィ石灰化検出方法の開発
    境田 みう, 吉村 高明, 唐 明輝, 杉森 博行  日本放射線技術学会雑誌  79-  (9)  1027  -1027  2023/09
  • 肋骨CR画像の撮影時情報の事後推定におけるVision TransformerとCNNの精度比較
    窪田 将也, 吉村 高明, 唐 明輝, 杉森 博行  日本放射線技術学会雑誌  79-  (9)  1078  -1078  2023/09
  • Deep Learningを用いた腰椎斜位像の角度推定における基礎的検討
    森谷 竜馬, 吉村 高明, 唐 明輝, 杉森 博行  日本放射線技術学会雑誌  79-  (9)  1078  -1078  2023/09
  • 心臓CT画像からの深層学習によるセグメンテーションを用いた大動脈弁自動推定法の検討
    猪股 壮一郎, 吉村 高明, 唐 明輝, 市川 翔太, 杉森 博行  日本放射線技術学会雑誌  79-  (9)  1028  -1029  2023/09
  • 【医療AIの普及拡大とさらなる展開 医療からヘルスケアサービスまで発展に向けた現状と展望】医療AIのための人材育成の現状と展望 北海道大学における医療AI開発者育成プログラムの活動と展望
    唐 明輝, 平田 健司, 杉森 博行, 吉村 高明, 小笠原 克彦, 中谷 純, 工藤 與亮  INNERVISION  38-  (7)  19  -20  2023/06  
    わが国においては高齢化,医療者の偏在,働き方改革など,多くの医療課題が山積みになっている。それらの課題を解決するため,医療AIの導入および展開が喫緊の課題となっている。そのような背景で,東北大学を主幹に,北海道大学と岡山大学が連携する医療AI人材育成プロジェクト「『Global×Localな医療課題解決を目指した最先端AI研究開発』人材育成教育拠点」が,文部科学省・大学教育再生戦略推進費「保健医療分野におけるAI研究開発加速に向けた人材養成産学協働プロジェクト」に採択された[2020(令和2)～2024(令和6)年度]。北海道大学では,大学院医学研究院連携研究センター医療AI教育研究分野を中心に,東北大学および岡山大学と連携し,協力校である北海道情報大学,北海道科学大学とともに,民間企業や自治体の支援を受けながら,多様性に富んだ事業推進体制による医療AI開発者養成プログラム(Clinical AI Human Resources Development Program:CLAP)を2021(令和3)年度から本格的に展開し始めた。(著者抄録)
  • Ammonia PETにおけるDeep Learningを用いた心外集積除去法の検討
    山田 佑介, 安藤 彰, 本間 仁, 吉村 高明, 唐 明輝, 杉森 博行  日本心臓核医学会ニュースレター  25-  (2)  85  -85  2023/05
  • Automatic Quantification of Enhancing Pannus of the Rheumatoid Hand using Machine Learning in DCE-MRI
    Fang Wanxuan, Mao Yijun, An Yujie, Sugimori Hiroyuki, Kiuch Shinji, Kamishima Tamotsu  日本医学放射線学会学術集会抄録集  82回-  S194  -S194  2023/03
  • Rheumatoid Arthritis Synovitis Segmentation Based on Unsupervised Learning and Time-intensity Curve Signal Data on Dynamic Contrast Enhaced MRI
    Mao Yijun, Fang Wanxuan, An Yujie, Sugimori Hiroyuki, Kiuch Shinji, Kamishima Tamotsu  日本放射線技術学会総会学術大会予稿集  79回-  322  -322  2023/03
  • MIP類似アルゴリズムによるFDG-PET体表画像の有用性
    平田 健司, 木村 理奈, 唐 明輝, 渡邊 史郎, 竹中 淳規, 若林 直人, 杉森 博行, 吉村 高明, 工藤 與亮  核医学  60-  (Suppl.)  S208  -S208  2023
  • SRCNNを用いた短時間収集PET画像の画質改善モデルの開発と定量性評価
    遠藤 大輝, 吉村 高明, 唐 明輝, 杉森 博行, 長谷川 淳, 小亀 翔揮, 孫田 惠一, 木村 理奈, 渡邊 史郎, 平田 健司, 工藤 與亮  核医学  60-  (Suppl.)  S209  -S209  2023
  • 遠藤大輝, 吉村高明, 唐明輝, 杉森博行, 長谷川淳, 小亀翔揮, 孫田惠一, 木村理奈, 渡邊史郎, 平田健司, 工藤與亮  核医学(Web)  60-  (Supplement)  2023
  • 平田健司, 木村理奈, 唐明輝, 渡邊史郎, 竹中淳規, 若林直人, 杉森博行, 吉村高明, 工藤與亮, 平田健司, 木村理奈, 唐明輝, 渡邊史郎, 竹中淳規, 若林直人, 杉森博行, 吉村高明, 工藤與亮, 平田健司, 唐明輝, 渡邊史郎, 杉森博行, 吉村高明, 工藤與亮, 平田健司, 杉森博行, 吉村高明, 工藤與亮, 平田健司, 工藤與亮  核医学(Web)  60-  (Supplement)  2023
  • MIP類似アルゴリズムによるFDG-PET体表画像の有用性
    平田 健司, 木村 理奈, 唐 明輝, 渡邊 史郎, 竹中 淳規, 若林 直人, 杉森 博行, 吉村 高明, 工藤 與亮  核医学  60-  (Suppl.)  S208  -S208  2023
  • SRCNNを用いた短時間収集PET画像の画質改善モデルの開発と定量性評価
    遠藤 大輝, 吉村 高明, 唐 明輝, 杉森 博行, 長谷川 淳, 小亀 翔揮, 孫田 惠一, 木村 理奈, 渡邊 史郎, 平田 健司, 工藤 與亮  核医学  60-  (Suppl.)  S209  -S209  2023
  • 森谷竜馬, 吉村高明, TANG Minghui, 杉森博行  北海道放射線技術雑誌(Web)  94-  2023
  • Deep Learning技術を用いた脳MRI画像によるヒトの年齢推定手法の検討
    薄井 康輔, 吉村 高明, 唐 明輝, 杉森 博行  日本放射線技術学会雑誌  78-  (9)  1086  -1086  2022/09
  • 3D-Convolutional Neural Network(CNN)による回帰を用いた左室駆出率予測に関する検討
    猪股 壮一郎, 吉村 高明, 唐 明輝, 杉森 博行  日本放射線技術学会雑誌  78-  (9)  1117  -1117  2022/09
  • Deep Learning技術を用いた脳MRI画像によるヒトの年齢推定手法の検討
    薄井 康輔, 吉村 高明, 唐 明輝, 杉森 博行  日本放射線技術学会雑誌  78-  (9)  1086  -1086  2022/09
  • 3D-Convolutional Neural Network(CNN)による回帰を用いた左室駆出率予測に関する検討
    猪股 壮一郎, 吉村 高明, 唐 明輝, 杉森 博行  日本放射線技術学会雑誌  78-  (9)  1117  -1117  2022/09
  • 核医学～近未来核医学の向かう道-診断・治療の精度をあげる最新手法～ 核医学におけるAIの活用と課題
    平田 健司, 杉森 博行, 藤間 憲幸, 豊永 拓哉, 工藤 與亮  日本医学放射線学会秋季臨床大会抄録集  58回-  S344  -S344  2022/08
  • 核医学〜近未来核医学の向かう道-診断・治療の精度をあげる最新手法〜 核医学におけるAIの活用と課題
    平田 健司, 杉森 博行, 藤間 憲幸, 豊永 拓哉, 工藤 與亮  日本医学放射線学会秋季臨床大会抄録集  58回-  S344  -S344  2022/08
  • 頭部単純CT撮影における物体検出技術を用いた多段面再構成画像の自動生成
    市川 翔太, 山本 浩之, 板谷 英樹, 杉森 博行  日本放射線技術学会総会学術大会予稿集  78回-  165  -166  2022/03
  • 関節リウマチ患者の滑膜炎を自動で抽出するソフトウエアの開発 手のダイナミックMRIを用いた検討(Toward Development of Software Application that can Automatically Demonstrate the Distribution of Pannus in Rheumatoid Hand using Dynamic MRI Dataset)
    Fang Wanxuan, An Yujie, Sugimori Hiroyuki, Kiuchi Shinji, Kamishima Tamotsu  日本医学放射線学会学術集会抄録集  81回-  S210  -S210  2022/03
  • 演繹法と帰納法の視点から見た医療AI
    平田 健司, 杉森 博行, 唐 明輝, 中谷 純, 小笠原 克彦, 豊永 拓哉, 工藤 與亮  北海道放射線医学雑誌  2-  1  -6  2022/03  
    医療AIが目覚ましい発達を続けている。AIに関する明確な定義はないため、今回、医療従事者等に対してAIに関する意識調査を行った結果、AIであるかどうかの境界線は、機械学習の有無にありそうだということがわかった。機械学習は帰納法に基づく考え方であり、あらかじめ多数のデータを学習させておくことで、明示的にルールを与えずとも未知の事例を正しく判断させる手法である。画像分類においては明示的ルールを与えることが困難であるため、機械学習が威力を発揮する。第3次AIブームの現在、AIといえば機械学習に基づくAIのことを指すことが多い。これに対して、第1次、第2次AIブームでは推論、探索、エキスパートシステムといった演繹法に基づくAIが盛んに研究されたが成功せず、冬の時代を経験した。我々は、帰納法のみのAIではいずれ限界に到達する可能性があり、演繹法の手法をいかに組み合わせていくかが今後の課題になっていくと考えている。(著者抄録)
  • 喘息・COPDにおける人工知能を用いた予後予測による疾患マネジメントの向上
    清水 薫子, 杉森 博行  大和証券ヘルス財団研究業績集  (45)  3  -6  2022/03
  • 頭部単純CT撮影における物体検出技術を用いた多段面再構成画像の自動生成
    市川 翔太, 山本 浩之, 板谷 英樹, 杉森 博行  日本放射線技術学会総会学術大会予稿集  78回-  165  -166  2022/03
  • Convolutional Neural Networkへの複数画像同時適用における有用性の検討
    大浦 大輔, 杉森 博行  日本放射線技術学会総会学術大会予稿集  78回-  205  -205  2022/03
  • 演繹法と帰納法の視点から見た医療AI
    平田 健司, 杉森 博行, 唐 明輝, 中谷 純, 小笠原 克彦, 豊永 拓哉, 工藤 與亮  北海道放射線医学雑誌  2-  1  -6  2022/03  
    医療AIが目覚ましい発達を続けている。AIに関する明確な定義はないため、今回、医療従事者等に対してAIに関する意識調査を行った結果、AIであるかどうかの境界線は、機械学習の有無にありそうだということがわかった。機械学習は帰納法に基づく考え方であり、あらかじめ多数のデータを学習させておくことで、明示的にルールを与えずとも未知の事例を正しく判断させる手法である。画像分類においては明示的ルールを与えることが困難であるため、機械学習が威力を発揮する。第3次AIブームの現在、AIといえば機械学習に基づくAIのことを指すことが多い。これに対して、第1次、第2次AIブームでは推論、探索、エキスパートシステムといった演繹法に基づくAIが盛んに研究されたが成功せず、冬の時代を経験した。我々は、帰納法のみのAIではいずれ限界に到達する可能性があり、演繹法の手法をいかに組み合わせていくかが今後の課題になっていくと考えている。(著者抄録)
  • 森谷竜馬, 吉村高明, 唐明輝, 杉森博行  北海道放射線技術雑誌(Web)  93-  2022
  • 猪股壮一郎, 吉村高明, 唐明輝, 杉森博行  北海道放射線技術雑誌(Web)  93-  2022
  • 細川吉暁, 小野寺智洋, 宝満健太郎, 工藤與亮, 亀田浩之, 杉森博行  北海道整形災害外科学会  141st-  2022
  • 浅見 祐輔, 山田 宝生, 真鍋 圭佑, 杉森 博行  北海道放射線技術雑誌  91-  (91)  51  -51  2021/10
  • 真鍋 圭佑, 山田 宝生, 浅見 祐輔, 杉森 博行  北海道放射線技術雑誌  91-  (91)  51  -51  2021/10
  • 薄井 康輔, 杉森 博行  北海道放射線技術雑誌  91-  (91)  57  -57  2021/10
  • 平田 健司, 藤間 憲幸, 杉森 博行, 工藤 與亮  INNERVISION  36-  (10)  17  -20  2021/09
  • Deep Learning技術を用いた胸部X線画像評価ソフトウェアの開発
    薄井 康輔, 泉 勇希, 杉森 博行  日本放射線技術学会雑誌  77-  (9)  1024  -1024  2021/09
  • 主幹動脈閉塞における短時間Phase Contrast Angiographyを用いたMRAと塞栓物質の同時描出
    大浦 大輔, 伊原 陸, 蛯名 翼, 月花 正幸, 杉森 博行  日本放射線技術学会雑誌  77-  (9)  1037  -1037  2021/09
  • Deep Learningを用いた前立腺がん検出の精度向上に関する基礎的検討
    真鍋 圭佑, 吉村 高明, 山田 宝生, 浅見 祐輔, 杉森 博行  日本放射線技術学会雑誌  77-  (9)  1089  -1089  2021/09
  • 背景情報の少ない医用画像における物体検出の学習最適化の基礎的検討
    山田 宝生, 真鍋 圭祐, 浅見 祐輔, 杉森 博行  日本放射線技術学会雑誌  77-  (9)  1106  -1106  2021/09
  • Deep Learningを用いた肝臓の自動抽出に関する基礎的研究
    泉 勇希, 薄井 康輔, 杉森 博行  日本放射線技術学会雑誌  77-  (9)  1106  -1106  2021/09
  • Semantic Segmentation技術を用いた単純CT画像におけるの血管検出の基礎的検討
    浅見 祐輔, 裴 梓言, 山田 宝生, 真鍋 圭佑, 杉森 博行  日本放射線技術学会雑誌  77-  (9)  1107  -1107  2021/09
  • 【Nuclear Medicine Today 2021 キーワードから展望する核医学の技術開発と臨床応用】人工知能(AI)の研究開発の現状と将来展望 1)腫瘍核医学におけるAI利用の動向
    平田 健司, 藤間 憲幸, 杉森 博行, 工藤 與亮  INNERVISION  36-  (10)  17  -20  2021/09
  • 胸部CTでの定量的手法による1群又は3群強皮症性肺高血圧症の評価
    蜷川 慶太, 加藤 将, 河野 通仁, 藤枝 雄一郎, 大平 洋, 奥 健志, 杉森 博行, 辻野 一三, 渥美 達也  日本肺高血圧・肺循環学会学術集会・日本小児肺循環研究会プログラム・抄録集  6回・27回-  41  -41  2021/05
  • 肝臓のMR弾性造影に関する半自動化定量ソフトウエアの結果の妥当性と再現性に関する研究(Validation and Reproducibility Study on Semi-automatic Quantification Software for MR Elastography of the Liver)
    Katsuumi Yuri, Kamishima Tamotsu, Sugimori Hiroyuki, Shimamura Tsuyoshi, Kawamura Norio, Takeda Hiroshi  日本放射線技術学会総会学術大会予稿集  77回-  248  -249  2021/03
  • 市川翔太, 市川翔太, 山本浩之, 杉森博行  中四国放射線医療技術フォーラムプログラム抄録集  17th-  2021
  • 河上 壮志, 杉森 博行, 平田 健司, 孫田 惠一, 加藤 千恵次  核医学技術  40-  (予稿集)  345  -345  2020/10
  • 狩野 麻名美, 畠山 遼兵, 柴崎 光咲, 小川 肇, 杉森 博行  函館医学誌  44-  (1)  28  -31  2020/09  
    乳腺MRIにおけるダイナミック検査では,造影剤注入後の血流評価が必須であるため,撮像時間の時間的な制約がある.乳腺MRIにおける撮像プロトコルの全体的な見直しを行い,プロトコル変更前と変更後の撮像条件におけるコントラストの比較をファントム実験と臨床画像評価にて行った.新プロトコルでは,旧プロトコルに比べ若干のCR低下があるものの,高分解能で撮像可能であり,診断上有益となる可能性がある.(著者抄録)
  • 敵対的生成ネットワークを用いた脳MR画像生成に関する検討
    小川 敬由樹, 真鍋 圭佑, 杉森 博行  北海道放射線技術雑誌  (88)  2  -3  2020/04
  • Deep learningによる物体検出技術を用いた脳動脈瘤検出の基礎的検討
    山田 宝生, 浅見 祐輔, 杉森 博行  北海道放射線技術雑誌  (88)  4  -5  2020/04
  • Deep learningによる超解像技術を用いたMR画像の高解像度化に関する研究
    真鍋 圭佑, 小川 敬由樹, 杉森 博行  北海道放射線技術雑誌  (88)  6  -7  2020/04
  • Deep Learningによる物体検出技術を用いた椎体位置自動同定の検討
    浅見 祐輔, 山田 宝生, 杉森 博行  北海道放射線技術雑誌  (88)  8  -9  2020/04
  • 内挿法を用いた心臓cine-MR画像における時相間平滑化の検討
    山内 桃花, 杉森 博行, 石坂 欣也  北海道放射線技術雑誌  (88)  16  -17  2020/04
  • Compressed SensingがLook Locker法のT1値測定に及ぼす影響の検討
    平野 裕也, 石坂 欣也, 青池 寿々子, 杉森 博行  北海道放射線技術雑誌  (88)  18  -19  2020/04
  • 肝臓のMRエラストグラフィにおける閾値によるSemi-automatic Quantification Softwareの検証研究(Validation Study on Semi-automatic Quantification Software by Threshold Value for MR Elastography of the Liver)
    Katsuumi Yuri, Kamishima Tamotsu, Sugimori Hiroyuki, Shimamura Tsuyoshi, Kawamura Norio, Takeda Hiroshi  日本放射線技術学会総会学術大会予稿集  76回-  318  -319  2020/03
  • マンモグラフィ装置におけるIntelligent AECの性能評価と位置依存性の検討
    狩野 麻名美, 高見 光咲, 藤田 佐智恵, 市川 昌樹, 畠山 遼兵, 竹田 亜由美, 伊藤 真理, 今野 祐治, 杉森 博行  日本放射線技術学会東北部会雑誌  (29)  158  -159  2020/01
  • 狩野麻名美, 畠山遼兵, 柴崎光咲, 小川肇, 杉森博行  函館医学誌  44-  (1)  28  -31  2020  
    乳腺MRIにおけるダイナミック検査では,造影剤注入後の血流評価が必須であるため,撮像時間の時間的な制約がある.乳腺MRIにおける撮像プロトコルの全体的な見直しを行い,プロトコル変更前と変更後の撮像条件におけるコントラストの比較をファントム実験と臨床画像評価にて行った.新プロトコルでは,旧プロトコルに比べ若干のCR低下があるものの,高分解能で撮像可能であり,診断上有益となる可能性がある.(著者抄録)
  • 携帯端末を通して得られたCT画像を用いた画像分類の精度評価の検討
    曹 瀛丹, 杉森 博行, 小笠原 克彦  医療情報学連合大会論文集  39回-  788  -789  2019/11
  • 携帯端末を通して得られたCT画像を用いた画像分類の精度評価の検討
    曹 瀛丹, 杉森 博行, 小笠原 克彦  医療情報学連合大会論文集  39回-  788  -789  2019/11
  • 携帯端末を通して得られたCT画像を用いた画像分類の精度評価の検討
    曹 瀛丹, 杉森 博行, 小笠原 克彦  医療情報学連合大会論文集  39回-  406  -406  2019/11
  • Compressed SensingがLook-Locker法のT1値測定に及ぼす影響の検討
    平野 裕也, 石坂 欣也, 青池 寿々子, 杉森 博行  北海道放射線技術雑誌  (87)  56  -56  2019/10
  • 内挿法を用いた心臓cine-MR画像における時相間平滑化の検討
    山内 桃花, 石坂 欣也, 杉森 博行  北海道放射線技術雑誌  (87)  67  -67  2019/10
  • Deep learningによる物体検出技術を用いた脳動脈瘤検出の基礎的検討
    山田 宝生, 杉森 博行, 浅見 祐輔  北海道放射線技術雑誌  (87)  75  -75  2019/10
  • Deep learningによる超解像技術を用いたMR画像の高解像度化に関する研究
    真鍋 圭佑, 杉森 博行, 小川 敬由樹  北海道放射線技術雑誌  (87)  76  -76  2019/10
  • Deep learningによる物体検出技術を用いた椎体位置自動同定の検討
    浅見 祐輔, 杉森 博行, 山田 宝生  北海道放射線技術雑誌  (87)  76  -76  2019/10
  • 敵対的生成ネットワークを用いた脳MR画像生成に関する検討
    小川 敬由樹, 真鍋 圭佑, 杉森 博行  北海道放射線技術雑誌  (87)  77  -77  2019/10
  • 河上 壮志, 平田 健司, 杉森 博行, 加藤 千恵次  核医学技術  39-  (予稿集)  346  -346  2019/10
  • 肺高血圧患者における2D-PC法を用いた主肺動脈Wall Shear Stress解析による検討
    山内 桃花, 杉森 博行, 石坂 欣也, 真鍋 徳子  日本放射線技術学会雑誌  75-  (9)  1035  -1035  2019/09
  • ステントグラフト内挿術におけるエンドリーク解析の検討
    三ツ井 貴博, 杉森 博行, 西田 純, 花輪 真  日本放射線技術学会雑誌  75-  (9)  1053  -1053  2019/09
  • 肝臓のMR Elastography検査におけるスライス位置の検討
    勝海 友里, 神島 保, 杉森 博行, 嶋村 剛, 川村 典生, 武田 宏司  日本放射線技術学会雑誌  75-  (9)  1056  -1056  2019/09
  • 施設倫理委員会への書類提出への手引き
    杉森 博行  北海道放射線技術雑誌  (86)  80  -80  2019/04
  • Phase contrast法による位相画像を用いた主肺動脈血管壁剪断応力の評価
    山内 桃花, 杉森 博行, 川崎 智博, 石坂 欣也, 真鍋 徳子  北海道放射線技術雑誌  (86)  32  -33  2019/04
  • 3T両側乳腺ダイナミックにおけるCAIPIRINHA法による高分解能撮像の検討
    狩野 麻名美, 畠山 遼兵, 三浦 喬弘, 宇野 弘幸, 高見 光咲, 永田 健悟, 杉森 博行  北海道放射線技術雑誌  (86)  46  -47  2019/04
  • 肝MRエラストグラフィーの半自動定量化ソフトウェアに関する検証研究(Validation Study on Semi-Automatic Quantification Software for MR Elastography of the Liver)
    Katsuumi Yuri, Kamishima Tamotsu, Sugimori Hiroyuki, Shimamura Tsuyoshi, Kawamura Norio, Takeda Hiroshi  日本放射線技術学会総会学術大会予稿集  75回-  211  -212  2019/03
  • 田川義晃, 大口剛司, 杉森博行, KHIN Tha Khin, 木嶋理紀, 岩田大樹, 田川義継, 石田晋  日本眼科学会雑誌  123-  2019
  • 狩野麻名美, 畠山遼兵, 永田健悟, 宇野弘幸, 高見光咲, 杉森博行  日本乳癌画像研究会プログラム・抄録集  28th-  2019
  • CAO Yingdan, 杉森博行, 小笠原克彦  医療情報学連合大会論文集(CD-ROM)  39th-  2019
  • 仕事から研究へ繋げる一歩とは? 大学の教育者として思うところ
    杉森 博行  北海道放射線技術雑誌  (85)  23  -24  2018/11
  • 眼痛を有する患者の安静時機能的MRIによる検討
    田川 義晃, 杉森 博行, Tha Khin Khin, 石田 晋  PAIN RESEARCH  33-  (2)  146  -146  2018/06  [Not refereed][Not invited]
  • Convolution neural networkを用いたMRIの分類(Classification of Magnetic Resonance Images by Using Convolutional Neural Networks)
    Sugimori Hiroyuki, Hamaguchi Hiroyuki, Fujiwara Taro, Ishizaka Kinya  日本放射線技術学会総会学術大会予稿集  74回-  211  -211  2018/03
  • 超音波とMRIの複合的評価は生物学的疾患修飾性抗リウマチ薬(bDMARDs)を投与中の関節リウマチにおけるX線上の関節破壊の予測能を改善する(Composite Assessment of Ultrasonography and MRI Improves the Prognostic Power of Joint Destruction on Radiograph in Rheumatoid Arthritis on Biological Disease-modifying Antirheumatic Drugs(bDMARDs))
    Fujimori Motoshi, Kamishima Tamotsu, Seno Yumika, Sugimori Hiroyuki, Nishida Mutsumi, Atsumi Tatsuya  日本放射線技術学会総会学術大会予稿集  74回-  231  -232  2018/03
  • MOLLI法を用いたT1値測定に関する検討
    平野 裕也, 藤原 太郎, 杉森 博行, 平山 博之, 堀江 達則, 石坂 欣也  北海道放射線技術雑誌  (84)  8  -9  2018/03  [Not refereed][Not invited]
  • ドライアイ症状を有する患者の安静時機能的MRIによる検討
    田川 義晃, 大口 剛司, 杉森 博行, タ・キンキン, 木嶋 理紀, 岩田 大樹, 田川 義継, 石田 晋  日本眼科学会雑誌  122-  (臨増)  156  -156  2018/03  [Not refereed][Not invited]
  • 小林 勇渡, 市川 翔太, 神島 保, 杉森 博行, 野口 淳史, 河野 通仁, 渥美 達也  北海道医学雑誌  92-  (2)  108  -109  2017/11  [Not refereed][Not invited]
  • 下肢静脈造影CT検査における造影方法の現状
    狩野 麻名美, 宇野 弘幸, 小林 匡, 守山 亮, 本庄 俊一, 安井 太一, 小川 肇, 杉森 博行  函館医学誌  41-  (1)  67  -69  2017/10  [Not refereed][Not invited]
     
    深部静脈血栓症(DVT)63例(男23例、女41例、平均年齢71.9歳)を対象に、下肢静脈CT検査と下肢静脈エコーによるDVTの検出率を比較検討した。その結果、下肢静脈エコーを実施していたのは46例(73.0%)と比較的多かった。一方、下肢静脈造影CTを実施していたのは12例(19.0%)、その他CT検査を実施していたのは11例(17.5%)であった。DVTの検出率は、下肢静脈エコーが41症例(89.1%)と最も高かった。一方、下肢静脈CT検査は12例(33.3%)、その他のCT検査は1症例(9.0%)であった。今回の検討では、下肢静脈CTにおける診断能を向上させるためには、CT装置の性能や撮像条件、CTを撮影する診療放射線技師教育などの検討が必要であると考えられた。
  • Ultra-short Echo Timeシーケンスにおけるスポーク数が画質に与える影響の検討
    濱口 裕行, 杉森 博行, 藤原 太郎, 沼田 直人, 石坂 欣也  日本放射線技術学会雑誌  73-  (9)  808  -808  2017/09  [Not refereed][Not invited]
  • Intravoxel Incoherent Motion解析手法が算出パラメータに与える影響の検討
    沼田 直人, 杉森 博行, 石坂 欣也  日本放射線技術学会雑誌  73-  (9)  857  -857  2017/09  [Not refereed][Not invited]
  • Zonally Magnified Oblique Multislice(ZOOM)EPI-DTI法を用いた腕神経叢の描出における至適撮像条件の検討
    野畑 圭亮, Khin Khin Tha, 藤原 太郎, 杉森 博行, 石坂 欣也, 奥秋 知幸, 工藤 興亮  日本放射線技術学会雑誌  73-  (9)  918  -918  2017/09  [Not refereed][Not invited]
  • 関節リウマチにおける手の滑膜炎定量のためのダイナミック造影強調MRIを用いた簡易的なアプローチ 完全自動化した全画素の分析(Simplified Approach to Quantification for Hand Synovitis in Rheumatoid Arthritis Using Dynamic Contrast Enhanced MRI: Full-Automatic Pixel-By-Pixel Analysis)
    Kobayashi Yuto, Kamishima Tamotsu, Ichikawa Shota, Sugimori Hiroyuki, Noguchi Atsushi, Kono Michihito, Atsumi Tatsuya  日本放射線技術学会総会学術大会予稿集  73回-  178  -179  2017/03
  • Phase-contrast法を用いた腎動脈血流解析における基礎的検討
    沼田 直人, 杉森 博行, 石坂 欣也  北海道放射線技術雑誌  (82)  11  -12  2017/03  [Not refereed][Not invited]
  • 2D-Phase contrast法におけるVENC(velocity encoding)の違いによる頸部血管のWSS(Wall Shear Stress)評価
    川崎 智博, 杉森 博行, 石坂 欣也  北海道放射線技術雑誌  (82)  41  -42  2017/03  [Not refereed][Not invited]
  • 小児股関節撮影におけるExposure Indexの検討
    宮本 佳史子, 森 静香, 坂野 稜典, 杉森 博行, 小田 まこと  北海道放射線技術雑誌  (82)  63  -64  2017/03  [Not refereed][Not invited]
  • 頭部の1H-MR spectroscopyにおける解析ソフトウェアの違いによる結果への影響の検討
    濱口 裕行, 杉森 博行, 高森 清華, 藤原 太郎, 葛西 克彦  北海道放射線技術雑誌  (82)  73  -74  2017/03  [Not refereed][Not invited]
  • DW-ASLを用いた脳虚血領域におけるwater permeabilityの評価
    藤間 憲幸, 奥秋 知幸, 青池 拓哉, 青池 寿々子, 杉森 博行, 工藤 與亮  日本磁気共鳴医学会雑誌  37-  (1)  15  -17  2017/02  [Not refereed][Not invited]
     
    脳虚血性病変を有する8例(男性7名、女性1名、53〜73歳)を対象とした。5例はdiffusion-weighted arterial spin labelingの撮像日の3年前に全脳のT2強調像、FLAIR像での評価を行った。それぞれのROIごとにT2強調像、FLAIR像で虚血の程度に応じて、3段階のグレード評価を行い、殆ど虚血を認めないNI群、虚血性変化が軽度のMI群、虚血性変化が中等度ないし高度のSI群に分けた。それぞれのROIごとに虚血の変化を比較して虚血の変化に応じて二つのグレードに分割した(NP群;3年間で虚血が殆ど変化なし、P群;3年間で虚血が拡大)。DW-ASLの撮像は問題なく施行可能であった。104個のROIによる3段階の虚血の程度の評価に関してKw値を算出し、SI群はMI群、NI群と比較して有意に高かった。3年間の虚血の進行の程度に関しては、5例における65個のROIの評価の結果、P群はNP群と比較して、有意にKwの値が高かった。視覚的にはT2強調像やFLAIR像で認める高信号域よりやや広い領域でwater permeabilityの変化がみられる領域が観察される傾向があった。
  • 骨髄MRI T1 map値は海綿骨強度予測のための間接的骨質指標となる
    遠藤香織, 高畑雅彦, 杉森博行, Wang Jeffrey, 山田悟史, 伊藤陽一, 高橋大介, 清水智弘, 東藤正浩, 但野茂, 工藤與亮, 岩崎倫政  日本整形外科学会雑誌  90-  (8)  S1732  -S1732  2016/08  [Not refereed][Not invited]
  • 骨髄MRI T1 map値は海綿骨強度予測のための間接的骨質指標となる
    遠藤 香織, 高畑 雅彦, 杉森 博行, Wang Jeffrey, 山田 悟史, 伊藤 陽一, 高橋 大介, 清水 智弘, 東藤 正浩, 但野 茂, 工藤 與亮, 岩崎 倫政  日本整形外科学会雑誌  90-  (8)  S1732  -S1732  2016/08  [Not refereed][Not invited]
  • 3T乳腺MRIにおける拡散尖度画像を用いた浸潤性乳癌の評価 バイオマーカーおよび腋窩リンパ節転移との比較
    加藤 扶美, 工藤 與亮, 藤原 太郎, Wang Jeff, 杉森 博行, 山下 啓子, 細田 充主, 真鍋 徳子, 三村 理恵, 白土 博樹  日本乳癌学会総会プログラム抄録集  24回-  250  -250  2016/06  [Not refereed][Not invited]
  • 拡散強調画像におけるreadout方法の違いがADC値に与える影響
    藤原 太郎, 石坂 欣也, 平山 博之, 吉富 敬祐, 坂本 悠輔, 野畑 圭亮, 杉森 博行  北海道放射線技術雑誌  (80)  4  -5  2016/04  [Not refereed][Not invited]
  • 3T-MRIにおける胸腰椎撮像時の両腕固定位置の違いがCNRおよびB1不均一に与える影響
    石坂 欣也, 原田 邦明, 白猪 亨, 藤原 太郎, 杉森 博行  北海道放射線技術雑誌  (80)  8  -9  2016/04  [Not refereed][Not invited]
  • 2D-Phase contrast法による頸部血管のWSS(Wall Shear Stress)評価
    川崎 智博, 杉森 博行  北海道放射線技術雑誌  (80)  10  -11  2016/04  [Not refereed][Not invited]
  • 乳腺ダイナミックMRIにおけるParametric Mappingによる血流解析ソフトウェアPMViewの有用性
    長谷川 佳菜, 水戸 寿々子, 加藤 扶美, 石坂 欣也, 杉森 博行, 森 祐生, 海谷 佳孝  北海道放射線技術雑誌  (80)  12  -13  2016/04  [Not refereed][Not invited]
  • 肩腱板の拡散テンソル解析 撮像シーケンスの比較
    青野 聡, 石坂 欣也, 高森 清華, 藤原 太郎, 水戸 寿々子, 杉森 博行  北海道放射線技術雑誌  (80)  14  -15  2016/04  [Not refereed][Not invited]
  • DSIにおけるパラメータ変化による神経束角度への影響についての検討
    吉富 敬祐, 石坂 欣也, 押野見 一哉, 河口 蒼, Khin Khin Tha, 山本 徹, 杉森 博行  北海道放射線技術雑誌  (80)  16  -17  2016/04  [Not refereed][Not invited]
  • 頭部非造影4D-MRAにおける早期描出能が改善された時相間可変flip angle法と固定flip angle法の比較と検討
    川角 恵里奈, 杉森 博行, 石坂 欣也, 藤間 憲幸, 小原 真  北海道放射線技術雑誌  (80)  18  -19  2016/04  [Not refereed][Not invited]
  • 3D GraSE pCASLにおける至適条件の基礎的検討
    青池 拓哉, 水戸 寿々子, 吉富 敬祐, 高森 清華, 藤原 太郎, 石坂 欣也, 杉森 博行  北海道放射線技術雑誌  (80)  24  -25  2016/04  [Not refereed][Not invited]
  • Pencil beam型飽和パルスに関する基礎的検討
    一宇 佑太, 杉森 博行, 藤原 太郎, 石坂 欣也  北海道放射線技術雑誌  (80)  30  -31  2016/04  [Not refereed][Not invited]
  • Spin labeling法を用いた脳脊髄液動態イメージング法の検討 背景信号抑制の試み
    平山 博之, 杉森 博行, 藤間 憲幸, 奥秋 知幸  北海道放射線技術雑誌  (80)  32  -33  2016/04  [Not refereed][Not invited]
  • 頭部領域におけるdouble inversion recovery法とphase sensitive inversion recovery法の白質描出能の比較検討
    野畑 圭亮, 藤原 太郎, 杉森 博行, 平山 博之, 青池 拓哉, 石坂 欣也  北海道放射線技術雑誌  (80)  36  -37  2016/04  [Not refereed][Not invited]
  • 呼吸同期用ナビゲータパルスが1H-MRSpectroscopyの解析値に及ぼす影響の検討
    高森 清華, 石坂 欣也, 藪崎 哲史, 川角 恵里奈, 杉森 博行  北海道放射線技術雑誌  (80)  40  -41  2016/04  [Not refereed][Not invited]
  • 頭部領域におけるisoFSE T1WIの再収束フリップアングルが画質に与える影響
    坂本 悠輔, 石坂 欣也, 青池 拓哉, 浅野 有加里, 佐藤 泰彦, 藤原 太郎, 杉森 博行  北海道放射線技術雑誌  (80)  42  -43  2016/04  [Not refereed][Not invited]
  • 心筋におけるIntravoxel incoherent motion(IVIM)-DWIの基礎的検討
    杉森 博行, Wang Jeffery, 真鍋 徳子, 水戸 寿々子, 高森 清華, 藤原 太郎, 石坂 欣也, 坂田 元道  北海道放射線技術雑誌  (80)  54  -55  2016/04  [Not refereed][Not invited]
  • 3T乳腺MRIにおける拡散尖度画像の検討
    加藤 扶美, 工藤 與亮, 三村 理恵, 藪崎 哲史, 坂本 圭太, 宮本 憲幸, 真鍋 徳子, 藤原 太郎, 杉森 博行, 山下 啓子, 細田 充主, Wang Jeff, 白土 博樹  Japanese Journal of Radiology  34-  (Suppl.)  13  -13  2016/02  [Not refereed][Not invited]
  • 3Tesla胸腰椎撮像 腕位置の変更による画質改善
    石坂 欣也, 原田 邦明, 白猪 亨, 藤原 太郎, 杉森 博行, 工藤 興亮  日本放射線技術学会総会学術大会予稿集  72回-  295  -295  2016/02  [Not refereed][Not invited]
  • 頭部非造影4D-MRAにおける早期描出能が改善された時相間可変flip angle法と固定flip angle法の比較と検討
    川角 恵里奈, 杉森 博行, 石坂 欣也, 水戸 寿々子, 高森 清華, 藤間 憲幸, 小原 真  北海道放射線技術雑誌  (79)  88  -88  2015/10
  • Spin labeling法を用いた脳脊髄液動態イメージングにおける背景脳脊髄液信号抑制の試み
    平山 博之, 杉森 博行, 藤間 憲幸, 石坂 欣也, 水戸 寿々子, 高森 清華, 奥秋 知幸  北海道放射線技術雑誌  (79)  103  -103  2015/10
  • Phase-sensitive inversion recovery(PSIR)法の撮像パラメータが白質・灰白質の信号強度に与える影響の検討
    野畑 圭亮, 藤原 太郎, 杉森 博行, 石坂 欣也, 青池 拓哉, Wang Jeff, 藤間 憲幸  日本放射線技術学会雑誌  71-  (9)  855  -856  2015/09
  • 肩腱板の拡散テンソル解析 固定肢位の違いが与える影響
    青野 聡, 石坂 欣也, 高森 清華, 藤原 太郎, 水戸 寿々子, 杉森 博行  日本放射線技術学会雑誌  71-  (9)  861  -861  2015/09  [Not refereed][Not invited]
  • MRI T2 mappingによる移植骨の骨強度評価の可能性
    遠藤 香織, 高畑 雅彦, 高橋 大介, 岩崎 倫政, 杉森 博行, Wang Jeffery Kuo-Chen, 山田 悟史, 東藤 正浩, 但野 茂  北海道外科雑誌  60-  (1)  98  -98  2015/06  [Not refereed][Not invited]
  • 解剖学的2束ACL再建術における遺残組織の温存が移植腱の成熟過程に与える効果 MRIを用いた臨床研究
    小野寺 純, 近藤 英司, 北村 信人, 坂本 圭太, 杉森 博行, 岩崎 倫政, 安田 和則  日本整形外科学会雑誌  89-  (3)  S1041  -S1041  2015/03  [Not refereed][Not invited]
  • KAWASAKI TOMOHIRO, SUGIMORI HIROYUKI, MANABE TOKUKO, FUJIWARA TARO, ISHIZAKA KIN'YA  日本放射線技術学会総会学術大会予稿集  71st-  227  2015/02/28  [Not refereed][Not invited]
  • リウマチ性滑膜炎の描出 従来型のコントラスト造影MRIに対する二重標識後待ち時間(PLD)測定を利用したASL画像分析法の利点(Depiction of Rheumatoid Synovitis: Advantage of ASL Imaging Analysis Using Dual Post Labeling Delay(PLD) Settings Over Conventional Contrast Enhanced MRI)
    Sakashita Taro, Kamishima Tamotsu, Sugimori Hiroyuki, Tou Meiki, Noguchi Atsushi, Kono Michihito, Atsumi Tatsuya  日本放射線技術学会総会学術大会予稿集  71回-  185  -185  2015/02
  • 画素間演算と時間強度曲線の形状分析を用いた関節リウマチにおける滑膜炎の正確な定量評価(Accurate Quantitative Assessment of Synovitis in Rheumatoid Arthritis Using Pixel by Pixel, Time-intensity Curve Shape Analysis)
    Sugimori Hiroyuki, Tou Meiki, Noguchi Atsushi, Kono Michihito, Atsumi Tatsuya  日本放射線技術学会総会学術大会予稿集  71回-  185  -185  2015/02
  • 3T MRIを用いた浸潤性乳癌の拡散尖度画像の検討 腋窩リンパ節転移予測における有用性(Diffusion kurtosis imaging at 3T MRI for invasive breast cancer: prediction of axillary lymph node metastasis)
    Kato Fumi, Kudo Kohsuke, Fujiwara Taro, Wang Jeff, Sugimori Hiroyuki, Yamashita Hiroko, Hosoda Mitsuchika, Mimura Rie, Miyamoto Noriyuki, Manabe Noriko  日本医学放射線学会学術集会抄録集  74回-  S190  -S191  2015/02
  • 3T心臓パーフュージョンMRIを用いた心筋血流定量法の確立(How to quantify cardiac perfusion MRI at 3 tesla in comparison with water PET)
    Manabe Noriko, Tomiyama Yuuki, Manabe Osamu, Katoh Chietsugu, Sugimori Hiroyuki, Kikuchi Yasuka, Kato Fumi, Kudo Kohsuke, Miyamoto Noriyuki, Nagara Tamaki  日本医学放射線学会学術集会抄録集  74回-  S289  -S289  2015/02
  • Spin labeling法を用いた脳脊髄液動態イメージングの検討
    平山 博之, 杉森 博行, 藤間 憲幸, 奥秋 知幸  日本放射線技術学会総会学術大会予稿集  71回-  174  -174  2015/02
  • 頭頸部領域におけるflip angleの至適化及び、撮像角度による脂肪抑制効果の検討
    川角 恵里奈, 水戸 寿々子, 藤間 憲幸, 石坂 欣也, 藤原 太郎, 高森 清華, 杉森 博行  日本放射線技術学会総会学術大会予稿集  71回-  225  -225  2015/02
  • AOIKE TAKUYA, SUGIMORI HIROYUKI, MANABE TOKUKO, OKUAKI TOMOYUKI, ISHIZAKA KIN'YA, FUJIWARA TARO, MITO SUZUKO, TAKAMORI SEIKA  日本放射線技術学会雑誌  70-  (9)  957  2014/09/20  [Not refereed][Not invited]
  • MRI申込書記述内容と撮影プロトコルの関係の調査
    谷川原 綾子, 辻 真太朗, 潟端 純也, 濱口 裕行, 杉森 博行, 仲 知保  北海道放射線技術雑誌  (77)  26  -27  2014/09
  • 頭部double inversion recovery法における撮像パラメータが白質・脳脊髄液の信号強度に与える影響の検討
    野畑 圭亮, 藤原 太郎, 藤間 憲幸, 杉森 博行, 高森 清華, 石坂 欣也, 青池 拓哉  日本放射線技術学会雑誌  70-  (9)  1046  -1046  2014/09
  • 頭部拡散強調画像における生理的変動が各種拡散指標に与える影響の検討
    濱口 裕行, Tha Khin Khin, 杉森 博行, 中西 光広, 中川 伸, 吉田 博一, 大野 誠一郎, 田原 誠司  日本放射線技術学会雑誌  70-  (9)  1044  -1044  2014/09  [Not refereed][Not invited]
  • F. Kato, R. Mimura, K. Kudo, N. Manabe, T. Fujiwara, H. Sugimori, M. Hosoda, H. Yamashita, H. Shirato  Japanese Journal of Clinical Radiology  59-  (4)  558  -562  2014/04  [Refereed][Not invited]
     
    We investigated usefulness of the slice selection gradient reversal (SSGR) method in diffusion weighed imaging (DWI) using 3-tesla breast MRI. Thirty-four women with 42 breast tumors were studied. Image quality and lesion detectability were compared between DWI with and without SSGR. DWI with SSGR had higher image quality with little artifact and higher detectability of the lesions than DWI without SSGR. Image quality and lesion detectability were improved on DWI using SSGR.
  • 多列検出器CTによるcanal of posterior ampullary nerve(singular nerve canal)の検出 1症例報告と文献考察(The Canal of Posterior Ampullary Nerve(Singular nerve canal) with Multi-Detector Row CT: A case report and review of literature)
    福屋 香菜子, 長谷川 佳菜, 天羽 浩太, 青野 聡, 杉森 博行, 中村 麻名美, 舛田 玲香, 坂田 元道  北海道放射線技術雑誌  (76)  34  -35  2014/03  [Not refereed][Not invited]
  • 3.0T Radial scan法による頸動脈プラーク評価
    中村 麻名美, 真壁 武司, 本庄 俊一, 畠山 遼兵, 爰地 祐次, 杉森 博行, 坂田 元道  北海道放射線技術雑誌  (76)  36  -37  2014/03  [Not refereed][Not invited]
  • 頸動脈black blood imageにおけるMotion Sensitized Driven Equilibrium(MSDE)を用いた時の血液抑制効果の検討
    田村 弘詞, 杉森 博行, 吉田 博一, 高森 清華, 濱口 裕行, 藤原 太郎, 野畑 圭亮  北海道放射線技術雑誌  (76)  40  -41  2014/03  [Not refereed][Not invited]
  • 頭部3D-DIR法における適正delay timeの検討
    野畑 圭亮, 藤原 太郎, 藤間 憲幸, 杉森 博行, 濱口 裕行, 吉田 博一, 平山 博之  北海道放射線技術雑誌  (76)  46  -47  2014/03  [Not refereed][Not invited]
  • Ultra short echo time法を用いた脊髄靱帯評価の基礎的検討
    濱口 裕行, 杉森 博行, Tha Khin Khin, 吉田 博一, 藤原 太郎, 高森 清華, 野畑 圭亮  北海道放射線技術雑誌  (76)  56  -57  2014/03  [Not refereed][Not invited]
  • 飽和パルスを用いた4-dimensional magnetic resonance angiography(4D-MRA)最適化の検討
    杉森 博行, 藤間 憲幸, 濱口 裕行, 藤原 太郎, 吉田 博一, 中村 麻名美, 坂田 元道  北海道放射線技術雑誌  (76)  64  -65  2014/03  [Not refereed][Not invited]
  • FID充填型Radial scanにおけるTrajectory Delay Timeが画質に及ぼす影響
    吉田 博一, 杉森 博行, 濱口 裕行, 高森 清華, 藤原 太郎, 田村 弘詞, 野畑 圭祐  北海道放射線技術雑誌  (76)  68  -69  2014/03  [Not refereed][Not invited]
  • 膝関節軟骨のT1ρ値に関する基礎的検討
    平山 博之, 杉森 博行  北海道放射線技術雑誌  (76)  74  -75  2014/03  [Not refereed][Not invited]
  • KATO FUMI, MANABE TOKUKO, MIMURA RIE, HARADA TAISUKE, TERAE SATOSHI, FUJIWARA TARO, SUGIMORI HIROYUKI, HOSODA MICHITSUKA, TAGUCHI KAZUNORI, YAMASHITA HIROKO, SHIRATO HIROKI  Jpn J Radiol  32-  (Supplement)  10  2014/02/25  [Not refereed][Not invited]
  • 15O-水PETを用いて検証したダイナミック灌流3テスラMRIによる心筋血流量の定量 領域分析への応用(Quantification of myocardial blood flow with dynamic perfusion 3.0 Tesla MRI using validation with 15O-water PET: Application to regional analysis)
    Tomiyama Yuuki, Manabe Osamu, Oyama-Manabe Noriko, Kikuchi Yasuka, Sugimori Hiroyuki, Katoh Chietsugu, Tamaki Nagara  日本放射線技術学会総会学術大会予稿集  70回-  134  -135  2014/02
  • 坂下太郎, 神島保, 杉森博行, 唐明輝, 河野通仁, 渥美達也  日本放射線技術学会雑誌  70-  (9)  2014
  • 小野雅人, 神島保, 杉森博行, 唐明輝, 河野通仁, 渥美達也  北海道医学雑誌  89-  (1)  2014
  • KATO FUMI, SUGIMORI HIROYUKI, MANABE NORIKO, KUDO KOSUKE  臨床画像  29-  (11)  1312  -1322  2013/11/26  [Not refereed][Not invited]
  • 頸動脈プラークイメージにおけるMotion Sensitized Driven Equilibrium(MSDE)を用いた時の血液信号抑制効果の検討
    田村 弘詞, 杉森 博行, 吉田 博一, 高森 清華, 濱口 裕行, 藤原 太郎, 野畑 圭亮  北海道放射線技術雑誌  (75)  98  -98  2013/10  [Not refereed][Not invited]
  • テキストマイニングによるMRI申込書記述内容と撮影プロトコルの関係の調査
    谷川原 綾子, 辻 真太朗, 潟端 純也, 濱口 裕行, 杉森 博行, 仲 知保  北海道放射線技術雑誌  (75)  109  -109  2013/10
  • 飽和パルスを用いた4-dimensional magnetic resonance angiography(4D-MRA)最適化の検討
    杉森 博行, 濱口 裕行, 藤原 太郎, 吉田 博一, 藤間 憲幸, 中村 麻名美, 坂田 元道  北海道放射線技術雑誌  (75)  99  -99  2013/10
  • 頭部3D-DIR法における適正delay timeの検討
    野畑 圭亮, 藤原 太郎, 杉森 博行, 濱口 裕行, 吉田 博一, 平山 博之, 藤間 憲幸  北海道放射線技術雑誌  (75)  101  -101  2013/10
  • 寺本 大翼, 潮田 悠一, 佐々木 絢加, 櫻井 佑樹, 長濱 宏史, 中村 麻名美, 杉森 博行, 坂田 元道  日本放射線技術学会雑誌  69-  (10)  1146  -1152  2013/10  [Refereed][Not invited]
     
    MRIにおいて果実・野菜が人体脳組織ファントムになり得るか検討した。ボランティアの頭部を測定し、T1WIにおいて灰白質のSIは305±12、白質のSIは363±11であった。頭部側ファントムで灰白質と白質のSIを含むことができたのは11th(541±22)と12th(195±20)の間であった。T2WIでは、灰白質のSIは356±16、白質のSIは256±15となった。頭部側ファントムで灰白質と白質のSIを含むことができたのは5th(357±13)と6th(226±14)の間となった。8種類の果実・野菜のSIを測定し、T1WI、T2WIの両方にてすべてのROI位置でSIを含むことが可能であった果実・野菜はバナナであった。
  • Daisuke Teramoto, Yuichi Ushioda, Ayaka Sasaki, Yuki Sakurai, Hiroshi Nagahama, Manami Nakamura, Hiroyuki Sugimori, Motomichi Sakata  Nihon Hoshasen Gijutsu Gakkai zasshi  69-  (10)  1146  -1152  2013/10  [Refereed][Not invited]
     
    Various custom-made phantoms designed to optimize magnetic resonance imaging (MRI) sequences have been created and subsequently reported in JSRT. However, custom-made phantoms that correctly match the T1-value and T2-values of human brain tissue (gray matter and white matter) cannot be made easily or quickly. The aim of this project was to search for alternative materials, such as fruits and vegetables, for optimizing MRI sequences. The following eight fruits and vegetables were investigated: apple, tomato, melon, apple mango (Mangifera indica), banana, avocado, peach, and eggplant. Their potential was studied for use in modeling phantoms of normal human brain tissues. MRI (T1- and T2-weighted sequences) was performed on the human brain and the fruits and vegetables using various concentrations of contrast medium (gadolinium) in the same size tubes as the custom-made phantom. The authors compared the signal intensity (SI) in human brain tissue (gray matter and white matter) with that of the fruits and the custom-made phantom. The T1 and T2 values were measured for banana tissue and compared with those for human brain tissue in the literature. Our results indicated that banana tissue is similar to human brain tissue (both gray matter and white matter). Banana tissue can thus be employed as an alternative phantom for the human brain for the purpose of MRI.
  • 多列検出器CTを用いたcanal of posterior ampullary nerve(singular nerve canal)の検出(The Canal of Posterior Ampullary Nerve(Singular nerve canal) with Multi-Detector Row CT: A case report and review of literature)
    福屋 香菜子, 長谷川 佳菜, 青野 聡, 天羽 浩太, 中村 麻名美, 杉森 博行, 坂田 元道  北海道放射線技術雑誌  (75)  111  -111  2013/10  [Not refereed][Not invited]
  • 3.0T乳腺MRIにおけるB1均一性に関する検討
    藤原 太郎, 吉田 博一, 高森 清華, 濱口 裕行, 杉森 博行, 水戸 寿々子, 加藤 扶美  北海道放射線技術雑誌  (75)  125  -125  2013/10  [Not refereed][Not invited]
  • FID充填型Radial scanにおけるTrajectory Delay Timeが画質に及ぼす影響
    吉田 博一, 杉森 博行, 濱口 裕行, 高森 清華, 藤原 太郎, 田村 弘詞, 野畑 圭亮  北海道放射線技術雑誌  (75)  130  -130  2013/10  [Not refereed][Not invited]
  • SUGIMORI HIROYUKI, WANG JEFF, OKUAKI TOMOYUKI, HAMAGUCHI HIROYUKI, YOSHIDA HIROKAZU, FUJIWARA TARO, SAKATA MOTOMICHI, MANABE NORIKO  日本放射線技術学会雑誌  69-  (9)  1105  2013/09/20  [Not refereed][Not invited]
  • 膝関節靱帯におけるUltra short TEを用いた定量的評価の検討
    吉田 博一, 杉森 博行, Wang Jeff, 奥秋 知幸, 谷川原 綾子, 濱口 裕行, 藤原 太郎, 坂本 圭太  日本放射線技術学会雑誌  69-  (9)  1040  -1040  2013/09
  • Manami Nakamura, Takeshi Makabe, Hideomi Tezuka, Takahiro Miura, Takuma Umemura, Hiroyuki Sugimori, Motomichi Sakata  Nihon Hoshasen Gijutsu Gakkai zasshi  69-  (4)  407  -412  2013/04  [Refereed][Not invited]
     
    The purpose of this study was to optimize scan parameters for evaluation of carotid plaque characteristics by k-space trajectory (radial scan method), using a custom-made carotid plaque phantom. The phantom was composed of simulated sternocleidomastoid muscle and four types of carotid plaque. The effect of chemical shift artifact was compared using T1 weighted images (T1WI) of the phantom obtained with and without fat suppression, and using two types of k-space trajectory (the radial scan method and the Cartesian method). The ratio of signal intensity of simulated sternocleidomastoid muscle to the signal intensity of hematoma, blood (including heparin), lard, and mayonnaise was compared among various repetition times (TR) using T1WI and T2 weighted imaging (T2WI). In terms of chemical shift artifacts, image quality was improved using fat suppression for both the radial scan and Cartesian methods. In terms of signal ratio, the highest values were obtained for the radial scan method with TR of 500 ms for T1WI, and TR of 3000 ms for T2WI. For evaluation of carotid plaque characteristics using the radial scan method, chemical shift artifacts were reduced with fat suppression. Signal ratio was improved by optimizing the TR settings for T1WI and T2WI. These results suggest the potential for using magnetic resonance imaging for detailed evaluation of carotid plaque.
  • SUGIMORI HIROYUKI, YOSHIDA HIROKAZU, YAGAHARA AYAKO, HAMAGUCHI HIROYUKI, FUJIWARA TARO, MANABE TOKUKO, SAKATA MOTOMICHI  北海道放射線技術雑誌  74-  (74)  22  -23  2013/03/29  [Not refereed][Not invited]
  • DTI撮像における撮像体位の影響
    濱口 裕行, 高森 清華, 谷川原 綾子, 水戸 寿々子, 杉森 博行, 石坂 欣也, Tha Khin Khin  北海道放射線技術雑誌  (74)  26  -27  2013/03
  • Direct-coronal拡散強調画像における画像歪みについての基礎的検討
    田村 弘詞, 高森 清華, 石坂 香織, 濱口 裕行, 藤原 太郎, 谷川原 綾子, 杉森 博行  北海道放射線技術雑誌  (74)  30  -31  2013/03
  • KATO FUMI, MIMURA RIE, FUJIWARA TARO, MANABE NORIKO, SUGIMORI HIROYUKI, HOSODA MICHITSUKA, TAGUCHI KAZUNORI, YAMASHITA HIROKO, TERAE SATOSHI, SHIRATO HIROKI  日本医学放射線学会総会抄録集  72nd-  S356  2013/02/28  [Not refereed][Not invited]
  • THA Khin Khin, TERAE Satoshi, HAMAGUCHI Hiroyuki, ISHIZAKA Kinya, POPY Kawser Akter, HIROTANI Makoto, SUGIMORI Hiroyuki, FUJIMA Noriyuki, YOSHIDA Atsushi, MINOWA Kazuyuki, SUZUKI Yuriko, SHIRATO Hiroki  日本磁気共鳴医学会雑誌  33-  (1)  33  -34  2013/02/15
  • 頸動脈血管壁画像における並行画像を利用したradial scan法のためのflow void現象の評価(Evaluation of the flow void effect for radial scan method with parallel imaging in carotid vessel wall imaging)
    Nakamura Manami, Makabe Takeshi, Kobayashi Masami, Tezuka Hideomi, Sugimori Hiroyuki, Sakata Motomichi  日本放射線技術学会総会学術大会予稿集  69回-  165  -165  2013/02
  • Gd-EOB-DTPA造影剤を用いた肝臓のT1短縮効果と肝機能指標との比較
    高森 清華, 杉森 博行, 濱口 裕行, 谷川原 綾子, 石坂 香織, 藤原 太郎, 田村 弘詞  日本放射線技術学会総会学術大会予稿集  69回-  141  -141  2013/02
  • Small FOV Imagingにおける画質の基礎的検討
    濱口 裕行, 杉森 博行, キンキンタ, 高森 清華, 谷川原 綾子, 藤原 太郎, 吉田 博一  日本放射線技術学会総会学術大会予稿集  69回-  300  -300  2013/02
  • Gd造影剤および塩化マンギン四水和物を用いたファントム作成における基礎的検討
    吉田 博一, 田村 弘詞, 石坂 香織, 杉森 博行  北海道放射線技術雑誌  (73)  123  -123  2012/11  [Not refereed][Not invited]
  • DTI撮像における撮像本位の影響
    濱口 裕行, 高森 清華, 谷川原 綾子, 杉森 博行, 石坂 欣也, 水戸 寿々子, Tha Khin Khin  北海道放射線技術雑誌  (73)  105  -105  2012/11
  • Direct-coronal収集での拡散強調画像における画像歪みについての基礎的検討
    田村 弘詞, 高森 清華, 石坂 香織, 濱口 裕行, 藤原 太郎, 谷川原 綾子, 杉森 博行  北海道放射線技術雑誌  (73)  124  -124  2012/11
  • 3.0T装置を用いた乳腺DWIにおけるSSGR法の基礎的検討
    藤原 太郎, 田村 弘詞, 谷川原 綾子, 濱口 裕行, 杉森 博行, 加藤 扶美  北海道放射線技術雑誌  (73)  129  -129  2012/11
  • 負荷心筋perfusion時の造影剤が心筋T1値に及ぼす影響の検討
    杉森 博行, 吉田 博一, 谷川原 綾子, 濱口 裕行, 藤原 太郎, 真鍋 徳子, 坂田 元道  北海道放射線技術雑誌  (73)  130  -130  2012/11
  • TOMIYAMA YUKI, KATO CHIETSUGU, MANABE OSAMU, MANABE NORIKO, SUGIMORI HIROYUKI, YOSHINAGA KEIICHIRO  日本放射線技術学会総会学術大会予稿集  68th-  181  2012/02/29  [Not refereed][Not invited]
  • 真鍋治, 大山徳子, 杉森博行, 吉永恵一郎, 寺江聡, 玉木長良  日独医報  56-  (2)  261  -261  2011/12/20  [Not refereed][Not invited]
  • 大山徳子, 杉森博行, 佐藤隆博, 大平洋, 辻野一三, 後藤大祐, 玉木長良, 寺江聡  日独医報  56-  (2)  260  -260  2011/12/20  [Not refereed][Not invited]
  • 杉森博行, 大山徳子, 真鍋治, 小原真, 玉木長良, 坂田元道, 寺江聡  日独医報  56-  (2)  261  2011/12/20  [Not refereed][Not invited]
  • 杉森博行, 中西光広, 石坂欣也, 濱口裕行, 水戸寿々子, 藤原太郎, 坂田元道  北海道放射線技術雑誌  71-  119  2011/10/25  [Not refereed][Not invited]
  • 濱口裕行, 杉森博行, 中西光広, 石坂欣也, 水戸寿々子, 藤原太郎, 仲知保  北海道放射線技術雑誌  71-  119  2011/10/25  [Not refereed][Not invited]
  • SASAKI KOJI, KIKUCHI MASANORI, TAKAHASHI TOSHIMITSU, ONO NAOMI, SUGIMORI HIROYUKI, SAKATA MOTOMICHI  北海道放射線技術雑誌  71-  23  -25  2011/10/25  [Not refereed][Not invited]
  • SAKATA MOTOMICHI, SUGIMORI HIROYUKI, KAWASUMI ERINA, NAGAHAMA HIROSHI, SAKURAI YUKI  北海道放射線技術雑誌  71-  19  -22  2011/10/25  [Not refereed][Not invited]
  • 水戸寿々子, 石坂欣也, 中西光広, 杉森博行, 濱口裕行, 藤原太郎  北海道放射線技術雑誌  71-  120  2011/10/25  [Not refereed][Not invited]
  • EHARA KENSUKE, IKUTA YASUTAKA, SHIRAI NOBUMASA, ONO HAJIME, SUGIMORI HIROYUKI, SAKATA MOTOMICHI  北海道放射線技術雑誌  71-  11  -14  2011/10/25  [Not refereed][Not invited]
  • SAKATA MOTOMICHI, SUGIMORI HIROYUKI, KAWASUMI ERINA  北海道放射線技術雑誌  71-  15  -17  2011/10/25  [Not refereed][Not invited]
  • 中西光広, 杉森博行, 石坂欣也, 濱口裕行, 水戸寿々子, 藤原太郎  北海道放射線技術雑誌  71-  114  2011/10/25  [Not refereed][Not invited]
  • 杉森博行, 真鍋徳子, 中西光広, 石坂欣也, 水戸寿々子, 濱口裕行, 坂田元道  日本放射線技術学会雑誌  67-  (9)  1086  2011/09/20  [Not refereed][Not invited]
  • 杉森博行, 大山徳子, 中西光広, 石坂欣也, 水戸寿々子, 濱口裕行, 坂田元道  日本放射線技術学会総会学術大会予稿集  67th-  166  -167  2011/02/25  [Not refereed][Not invited]
  • 水戸寿々子, 石坂欣也, 加藤扶美, 杉森博行, 中西光宏, 白土博樹, 寺江聡  日本放射線技術学会総会学術大会予稿集  67th-  244  2011/02/25  [Not refereed][Not invited]
  • MITO SUZUKO, ISHIZAKA KIN'YA, NAKANISHI MITSUHIRO, SUGIMORI HIROYUKI, HAMAGUCHI HIROYUKI, TSUZUKI TOMOYASU  日本放射線技術学会雑誌  67-  (6)  654  -660  2011  [Not refereed][Not invited]
  • 杉森博行, 中西光広, 濱口裕行, 石坂欣也, 水戸寿々子, 坂田元道  日本放射線技術学会雑誌  66-  (9)  1057  -1058  2010/09/20  [Not refereed][Not invited]
  • 濱口裕行, 中西光広, 杉森博行, 石坂欣也, 水戸寿々子, 田村弘詞, 横山英辰, 仲知保  日本放射線技術学会雑誌  66-  (9)  1123  2010/09/20  [Not refereed][Not invited]
  • 中西光広, 大山徳子, 杉森博行, 石坂欣也, 濱口裕行, 水戸寿々子  日本放射線技術学会総会学術大会予稿集  66th-  108  2010/02/26  [Not refereed][Not invited]
  • 杉森博行, 大山徳子, 石坂欣也, 中西光広, 水戸寿々子, 濱口裕行, 坂田元道  日本放射線技術学会総会学術大会予稿集  66th-  125  2010/02/26  [Not refereed][Not invited]
  • 石坂欣也, 中西光広, 杉森博行, 濱口裕行, 水戸寿々子, 佐賀和高, 仲知保  日本放射線技術学会雑誌  65-  (9)  1222  -1223  2009/09/20  [Not refereed][Not invited]
  • 杉森博行, 石坂欣也, 中西光広, 濱口裕行, 坂田元道  日本放射線技術学会雑誌  65-  (9)  1271  2009/09/20  [Not refereed][Not invited]
  • SUGIMORI Hiroyuki, UNO Takahiro, YANAGISAWA Akira  Japanese Journal of Radiological Technology  65-  (5)  612  -619  2009/05/20  [Not refereed][Not invited]
     
    The evaluation of myocardium characterization is an important role in cardiac MRI. The dark-blood (DB) sequence is used for non-enhanced T2-weighted myocardial images. The purpose of this study was to evaluate and optimize the DB T2WI sequence in myocardium images. We changed the parameters TE, echo train length (ETL), inversion time (TI), and fat suppression method, respectively. Data acquisition with end-diastolic phase was effective for avoiding the blur that was caused by cardiac motion. Consequently, the optimal setting of ETL and TI was important for myocardial images. STIR was suitab...
  • 宇野 貴寛, 佐藤 順一, 杉森 博行, 高橋 敬一  旭川放射線技師会会誌  30-  41  -44  2008  
    雑誌掲載版
  • 宇野 貴寛, 佐藤 順一, 杉森 博行, 高橋 敬一  日本放射線技術學會雜誌  63-  (9)  1074  -1074  2007/09/20
  • 佐藤 順一, 宇野 貴寛, 杉森 博行, 高橋 敬一, 秀毛 範至, 沖崎 琢貴, 佐々木 智章, 油野 民雄  日本放射線技術學會雜誌  63-  (9)  1045  -1045  2007/09/20
  • 杉森 博行, 佐藤 順一, 宇野 貴寛  日本放射線技術學會雜誌  63-  (9)  1049  -1050  2007/09/20
  • Sugimori Hiroyuki, Sakamoto Naka, Natori Shunsuke, Yanagisawa Akira, Uno Takahiro, Kubota Makoto  Japanese Journal of Radiological Technology  63-  (6)  661  -666  2007/06/20  [Not refereed][Not invited]
     
    [Background] Delayed-enhancement MRI is a technique that has significant clinical usefulness, particularly for myocardial viability determination in ischemic heart disease. Delayed enhanced images have been acquired by using the inversion recovery (IR) method. It is necessary for the IR method to select optimal inversion time (TI). Recently, the phase-sensitive inversion recovery (PSIR) method has been developed to detect Gd-DTPA enhanced myocardium. [Purpose] To compare the IR method with the PSIR method by acquiring Gd-DTPA solution phantoms A (0.05 mmol/l) and B (0.04 mmol/l) in various ...
  • SATO Hiroaki, INAOKA Tsutomu, TAKAHASHI Koji, YAMADA Tomonori, NAGASAWA Kenichi, HIRANUMA Hatsune, YAMAKI Toshihiro, SUGIMORI Hiroyuki, SASAKI Yoshihito, NAKAMURA Eiki, ABURANO Tamio  日本小児放射線学会雑誌 = Journal of Japanese Society of Pediatric Radiology  23-  (1)  19  -24  2007/02/15  [Not refereed][Not invited]
  • 宇野 貴寛, 杉森 博行, 柳澤 亨, 増田 憲昭  旭川放射線技師会会誌  29-  38  -40  2007  
    雑誌掲載版
  • 佐藤 順一, 杉森 博行, 高橋 敬一, 秀毛 範至, 沖崎 貴琢, 油野 民雄, 吉岡 克則, 横井 孝司  日本放射線技術學會雜誌  62-  (9)  1198  -1198  2006/09/20
  • 杉森 博行, 宇野 貴寛, 柳澤 亨, 窪田 誠, 佐藤 宏朗, 稲岡 努  日本放射線技術學會雜誌  62-  (9)  1217  -1218  2006/09/20
  • 杉森 博行, 柳澤 亨, 山田 裕樹, 窪田 誠  北海道放射線技術雑誌  (66)  7  -12  2006/07  
    出版社版心筋遅延造影MRI用シーケンスとしてInversion Recovery付加Turbo Flash(IR-Turbo Flash)とInversion Recovery付加True FISP(IR-True FISP)の2種類を用い撮像を行っている.今回,自作ファントムを作成し,2種類のシーケンスを用いて撮像を行い,それぞれのシーケンスにおける有用性について検討した.心筋遅延造影MRIにおいて,IR-Turbo Flashを用いて撮像することによりCNRの高い画像を得ることができた.IR-Turbo Flashの方がIR-TrueFISPよりCNRが高くなったが,性質が異なるシーケンスを用いているため,パラメータの検討および使い分けの検討を行った.IR-True FISPはSegment数の変化によって正常心筋のNullポイントおよびコントラストに変化がないため,息止め困難な患者において有用であることが示唆された
  • 坂本 央, 菅野 貴康, 田代 直彦, 八巻 多, 藤野 貴行, 竹原 有史, 田邊 康子, 竹内 利治, 佐藤 伸之, 川村 祐一郎, 長谷部 直幸, 菊池 健次郎, 名取 俊介, 長沢 研一, 油野 民雄, 杉森 博行  Circulation journal : official journal of the Japanese Circulation Society  69-  947  -947  2005/10/20
  • 稲岡 努, 高橋 康二, 杉森 博行, 油野 民雄, 後山 恒範, 松野 丈夫  臨床スポーツ医学 = The journal of clinical sports medicine  21-  (6)  666  -675  2004/06/01

Books etc

Teaching Experience

  • Practical medical imagingPractical medical imaging Hokkaido University
  • Magnetic Resonance in Medicine ⅠMagnetic Resonance in Medicine Ⅰ Hokkaido University

Association Memberships

  • THE JAPANESE SOCIETY FOR ARTIFICIAL INTELLIGENCE   JAPANESE SOCIETY FOR MAGNETIC RESONANCE IN MEDICINE   JAPANESE SOCIETY OF RADIOLOGICAL TECHNOLOGY   Japanese Association for Medical Artificial Intelligence   医用画像情報学会   日本医用画像工学会   

Research Projects

  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research
    Date (from‐to) : 2024/04 -2027/03 
    Author : 工藤 與亮, 小畠 隆行, 小牧 裕司, 杉森 博行, 亀田 浩之, 安井 正人
  • 日本学術振興会：科学研究費助成事業
    Date (from‐to) : 2024/04 -2027/03 
    Author : 杉森 博行
  • 日本学術振興会：科学研究費助成事業
    Date (from‐to) : 2023/04 -2027/03 
    Author : 吉田 祐子, 杉森 博行, 中村 典雄, 冨澤 登志子
  • 日本学術振興会：科学研究費助成事業
    Date (from‐to) : 2024/04 -2027/03 
    Author : 伊藤 康裕, 杉山 拓, 杉森 博行, 唐 明輝, 伊東 雅基, 小笠原 克彦
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research
    Date (from‐to) : 2023/04 -2026/03 
    Author : 今野 哲, 村上 正晃, 鈴木 雅, 杉森 博行, 清水 薫子, 木村 孔一
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)
    Date (from‐to) : 2021/04 -2026/03 
    Author : 杉山 拓, 杉森 博行, 松澤 等, 小笠原 克彦, 藤村 幹, 伊東 雅基
     
    本研究の目的は、外科手術の機能や安全性、術者スキルに関わる重要な要素を探索することであり、この先にアウトカム予測、有害イベント予測、術者スキル評価AIなどを目指すものである。 令和3年度は、頚動脈狭窄症に対する動脈内膜剥離術に焦点を当て、手術映像の解析に着手した。頚動脈を剥離する際の、頚動脈の動き（加速度）に着目し、これを手術映像から測定することで、“組織に対する愛護的な手術操作”の新たな指標と仮定した。１１７例の頚動脈内膜剥離術中映像の網羅的解析により、この新たな指標が、手術スキルおよび手術合併症に相関することが証明された。また、この指標を用いることにより、どの様な手術剥離法が客観的に有用であるか（組織に対して愛護的であるか）を示すことが可能になった。さらには、このような手術パフォーマンスの指標が、従来の研究で多く用いられてきた患者側の指標と同等以上に、治療成績にも相関することが多変量解析の結果からも証明し得た。本研究結果を、現在英語論文として投稿準備中である。 また、微小脳血管吻合のトレーニング映像を用いて、術具の先端を自動追跡する深層学習アルゴリズム、手術操作の対象となる微小血管をセグメンテーションするアルゴリズムの作成を開始し、おおむね精度の高いアルゴリズムが形成されてきている。これらを用いて、術具の軌道分析や、患者組織の変形分析などを行い、術者レベルや血管吻合成否に関与する因子の網羅的探索を継続している。
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)
    Date (from‐to) : 2022/04 -2025/03 
    Author : 永井 礼子, 武田 充人, 正木 直樹, 高桑 恵美, 杉森 博行, 平田 健司, 齋木 佳克
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (B)
    Date (from‐to) : 2021/04 -2024/03 
    Author : 工藤 與亮, 亀田 浩之, 杉森 博行, 村上 正晃, 坂本 直哉, 小牧 裕司, 小畠 隆行, 安井 正人
     
    ①MRI撮像法開発：O-17標識水の存在によるT2値の短縮を定量的に計測してO-17濃度を定量解析するため、プリパルスを利用した高速T2 mapping法を開発して最適化を行った。異なる濃度のO-17標識水を含有した濃度ファントムを作成し、高速T2 mapping法と従来のFSE法によるT2 mapping法の精度を比較した。従来法と比較して高精度のT2値測定が可能となった。 ②正常動物・疾患モデル動物でのMRI撮像：正常マウスやラットにてO-17標識水の静脈内投与法や髄腔内投与法、頸動脈内投与法、腹腔内投与法などを確立した。静脈内投与や頸動脈内投与によって脳内の有意なMRI信号変化を確認した。水中毒モデルラットにO-17標識水を腹腔内投与してMRI撮像を行い、AQP4欠損ラットとの比較を行った。AQP4欠損によって脳内の水貯留が増加することが明らかになった。ALSモデルマウス・ラットにてO-17標識水を静脈内投与してMRI撮像を行った。野生型と比較して錐体路での水漏出が増加していることが明らかとなった。 ③同位体顕微鏡による水分子イメージング：新たに導入した多機能コーティング装置を用いて凍結下での標本作成から同位体顕微鏡によるイメージングまでの解析手順を確立した。ラット脳にO-18標識水を直接注入し、注入部位でのO-18濃度の上昇を確認した。摘出したラット肝の門脈内にO-18標識水を注入し、血管内や類洞内のO-18濃度の上昇を確認した。 ④ヒトでのMRI撮像：認知症患者を対象にしたO-17標識水の髄腔内投与研究にて、特発性正常圧水頭症患者とアルツハイマー型認知症患者で、髄腔内の水吸収速度に差があることを見出した。
  • 日本学術振興会：科学研究費助成事業 基盤研究(C)
    Date (from‐to) : 2021/04 -2024/03 
    Author : 菊地 実, 永瀬 晃正, 吉田 祐子, 杉森 博行
     
    当該年度の研究成果は、コロナ禍の影響で計画どおりには進まなかったが、AIによるエコー画像の判読システムに使用するハードウェアの選定とその性能評価、研究テーマの関連疾患についての学会報告を行った。本研究に必要な主なハードウェアは、超音波診断装置とAIを起動させ画像判読を行うためのパソコンが対象である。超音波診断装置については、携帯性、拡張性に優れ、皮膚領域における画像表示能力も高いものを基準に選定した。表在組織が観察可能なタブレット画像表示が可能なG社とP者の２機種を候補としカタログによる性能と拡張面を比較評価し、画像表示性能は超音波精度評価用ファントムにて評価した。総合的に評価した結果、G社の機器が本研究目的を果たすに適すると判断した。G社機器の納入見積を取り寄せ研究計画の経費内であることも確認した。 AIを起動させ超音波画像を取り込みするパソコンは、携帯性に優れるものを基準に選定したが、ノート型やタブレット型など該当すると思われる機種が多数あるためカタログ収集とかカタログ記載事項による性能評価を行った。AIシステムの起動条件としてOSがWINDOWSに限られること、画像を扱うためメモリーが比較的容量の大きいもの基準に選定を進めているところである。 学会報告については、日本超音波医学会北海道地方会において研究テーマと関連するインスリン由来アミロイドーシスのエラストグラフィーによる評価を発表し、この病態における超音波画像診断の有用性についてを認識してもらうための活動を行った。
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research
    Date (from‐to) : 2021/04 -2024/03 
    Author : 杉森 博行
     
    虚血性脳血管障害における画像データに対し人工知能技術を用いて検出しRadiomics解析による高次元特徴量を複合した予後予測を行うという目的において、当該年度は「脳虚血病変検出処理方法の確立」と「機械学習エンジン構築手法の確立」に取り組んだ。画像診断補助の基礎となる脳虚血病変の検出に関しては拡散強調画像とFLAIR画像を用い、病変断面の検出と病変領域の特定方法について検討を行った。 複数断面ある脳画像からまず脳虚血病変の有無を判別させるため、拡散強調画像とFLAIR画像のそれぞれにおいて、画像分類器を作成し病変有無を判別した。また、セマンティックセグメンテーション技術を用いて脳虚血病変のみを領域分割し抽出する検出モデルを作成した。次に検出された病変の信号強度を評価するためにセマンティックセグメンテーションで検出された領域に対して対側の脳領域に同サイズの関心を自動設定する仕組みを実装し、拡散強調画像・FLAIR画像および拡散強調画像収集過程で生成されたADC－mapにおいて病変と対側の脳領域の信号値ならびにADC値を比較することで超急性期・急性期・慢性期を判断することのできる統合ソフトウェアを開発した。画像分類器での病変有無判断をセマンティックセグメンテーションにおける病変領域抽出と組み合わせることで、誤検出された病変領域を除外する機能を実装した。 人工知能技術によって得られた脳虚血領域のRadiomics解析に必要なデータは得られたものの経時的データ解析における変化量の抽出まで至らなかったため、次年度前半でこの点の解析と評価および次年度計画にある脳虚血性病変の予後予測に必要な解析を進める。
  • 日本学術振興会：科学研究費助成事業 基盤研究(B)
    Date (from‐to) : 2020/04 -2023/03 
    Author : 嶋村 剛, 深井 原, 藤好 真人, 暮地本 宙己, 杉森 博行, 木村 太一
     
    本研究の目的はラットExpanded Criteria Donor (脂肪肝、心停止肝) を用いた肝移植の術後成績を向上させるグラフト灌流法、コンディショニング法を開発し、術後成績を予測できる移植前グラフト機能評価法を確立することである。その実現のために、メタボローム解析とタンパク質機能解析が不可欠であり、前処理の条件検討を行った。トリクロロ酢酸 (TCA) によりタンパク質解析(沈殿)とメタボローム解析用(上清)の試料を同時に取得した。メタボローム解析用の試料は、LC-MS/MS、NMR、ラマン分光解析に供する目的でそれぞれに至適な条件を検討した。特にNMR、ラマン分光解析は試料のpHが測定結果に影響するため、ジエチルエーテルとの混和によるTCAの除去を繰り返し、安定した測定条件を見出した。これにより、NMR解析は600円/試料、LC-MS/MS解析は6000円/試料程度の費用で測定できる目処が立った (外注では約12万円/試料)。本課題におけるもっとも重要な評価系の一部が確立された。脂肪肝モデルも検討し、肝移植のグラフトとしての検討に資する30-60%の大滴性脂肪肝を安定して作成する方法を確立した。灌流液中のFMN濃度がグラフトのミトコンドリアComplex1の傷害マーカーになることが報告されているが、多くは灌流液の蛍光強度のみの測定であり、同じ蛍光を発するリボフラビン (RF)、フラビンアデニンジモノヌクレオチド (FMN)、フラビンアデニンジヌクレオチド (FAD)由来の蛍光の合算を"FMN"と称している。われわれはこれらの分子をHPLCで分離し、蛍光検出することにより、肝冷保存や体外灌流中のRF, FMN, FAD の漏出を5分以内で定量できるシステムを確立した。
  • Japan Society for the Promotion of Science：Grants-in-Aid for Scientific Research Grant-in-Aid for Scientific Research (C)
    Date (from‐to) : 2017/04 -2020/03 
    Author : Tha Khin Khin
     
    Electrical conductivity is a property of materials to conduct electric current. Different materials have different electrical conductivity values, ranging from almost zero (insulators) to several million siemens per meter (S/m) (conductors). Living tissues are also reported to have variable electrical conductivity values - fat and bone have lower values, whereas the cerebrospinal fluid (CSF) and blood have higher values. Tumors, especially malignant ones, are reported to have higher values than the normal tissues. This study aimed at the establishment of an MRI technique to noninvasively measure electrical conductivity of lung lesions and to evaluate the accuracy of this technique in distinguishing lung tumors. We established an MRI technique for noninvasive electrical conductivity measurement for lung lesions. Tumor contrast, which is a texture characteristic of electrical conductivity distribution, can be useful in distinguishing between benign and malignant lung tumors.
  • 人工知能が自分で学習を進める画像診断システムの開発
    北海道科学技術総合振興センター（略称：ノーステック財団）：札幌ライフサイエンス産業活性化事業 研究シーズ発掘補助金（札幌タレント補助金）
    Date (from‐to) : 2018/08 -2019/03 
    Author : 杉森 博行
  • Arterial spin labeling法を用いたMRIでの腎血流量評価
    日本放射線技術学会 北海道部会：北海道放射線技術研究助成金
    Date (from‐to) : 2010/04 -2012/03 
    Author : 杉森 博行

Industrial Property Rights


Copyright © MEDIA FUSION Co.,Ltd. All rights reserved.