吉村　高明 (ヨシムラ　タカアキ)

保健科学研究院講師
Last Updated :2025/01/11

■研究者基本情報

学位

  • 博士(医学), 北海道大学, 2017年03月

Researchmap個人ページ

■研究活動情報

受賞

  • 2024年11月, 日本放射線腫瘍学会, 学生・研修医賞　　　　　　　　　　　　　　　
    尿道同定精度向上に向けた治療計画用MR画像に対する超解像深層学習モデルの構築
    Sato K, Yoshimura T, Nishioka K, Sinbo G, Endo H, Fujisawa Y, Sugimori H, Hirata K, Kudo K, Hashimoto T, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2024年09月, 北海道大学, 第10回北海道大学部局横断シンポジウム研究助成採択 銅賞
    超低線量PET画像診断支援システムと生成AIの融合
    吉村高明;杉森博行;藤後廉;平田健司, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2024年04月, 日本医学物理学会, 学生奨励賞　　　　　　　　　　　　　　　
    Dosiomicsに基づく急性期放射線誘発口腔乾燥のリスク分類に関する検討
    Takagi S;Nakamoto T;Yasuda K;Yoshimura T;Tamura H;Aoyama H, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2024年04月, 日本放射線技術学会北海道支部, 優秀研究賞　　　　　　　　　　　　　　　
    マンモグラフィにおける石灰化識別のための半教師あり学習の適用と評価
    境田みう;吉村高明;唐明輝;市川翔太;杉森博行, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2024年03月, 令和5年度 北海道大学CLAP受講者による成果発表会, 北海道大学大学院医学研究院医療AI開発者養成プログラム(CLAP), 優秀賞（ポスター部門）　　　　　　　　　　　　　　　
    マンモグラフィ石灰化検出における半教師あり学習の適用と評価
    Sakaida M;Yoshimura T;Tang M;Ichikawa S;Sugimori H;Hirata K;Kudo K, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2024年03月, 令和5年度 北海道大学CLAP受講者による成果発表会, 北海道大学大学院医学研究院医療AI開発者養成プログラム(CLAP), 優秀賞（口演部門）
    SRCNNを用いた短時間収集PET画像の画質改善: 臨床画像における定量性の検証
    Endo H;Yoshimura T;Tang M;Sugimori H;Hasegawa A;Kogame S;Magota K;Kimura R;Watanabe S;Hirata K;Kudo K, 国内学会・会議・シンポジウム等の賞, 日本国, 42583404
  • 2023年11月, 日本放射線技術学会, 第51回日本放射線技術学会秋季学術大会 座長推薦優秀研究
    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, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2023年11月, 日本放射線技術学会, 第51回日本放射線技術学会秋季学術大会 座長推薦優秀研究
    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, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2023年10月, 北海道大学, 第9回北海道大学部局横断シンポジウムベストポスター賞
    超解像深層学習を用いた低投与線量PET検査:臨床画像における定量性の検証
    遠藤大輝;吉村高明;杉森博行;孫田恵一;藤後廉;平田健司;工藤與亮, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2023年10月, 北海道大学, 第9回北海道大学部局横断シンポジウム研究助成採択 銅賞
    超解像深層学習を用いた低投与線量PET検査の実現に向けたシステム開発
    吉村高明;杉森博行;平田健司;藤後廉, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2023年04月, 日本放射線技術学会北海道支部, 優秀研究賞
    cine-MRIを用いた3D-CNNによる左室駆出率と右室駆出率推定
    猪股壮一郎;吉村高明;唐明輝;杉森博行, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2023年03月, 北海道大学, 令和４年度北海道大学医学部保健学科卒業研究優秀発表賞　　　　　　　　　　　　　　　
    【学生・指導教員】人獣連携による高精度MR-CT画像変換技術開発～前立腺癌に対するMR画像誘導即時適応陽子線治療の実現に向けて～
    佐藤圭祐;吉村高明
  • 2022年11月, 第１回北大医療AIシンポジウム, 優秀研究賞　　　　　　　　　　　　　　　
    AIを用いた頭蓋内バイパス術の手術スキルの評価
    高張廉;杉森博行;吉村高明;小笠原克彦;杉山拓;唐明輝, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2022年10月, 日本放射線技術学会, 第50回日本放射線技術学会秋季学術大会 座長推薦優秀研究
    Cine-MRIを用いた3D-CNNによる左室駆出率と右室駆出率推定
    猪俣壮一郎;吉村高明;唐明輝;杉森博行, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2022年10月, 北海道大学, 第8回北海道大学部局横断シンポジウム研究助成採択 銅賞
    人獣連携によりMR画像-CT画像変換を高精度化する技術の開発~前立腺癌に対するMR画像誘導即時適応尿道線量低減陽子線治療の実現に向けて~
    吉村高明;新坊弦也;松浦妙子;橋本孝之;西岡健太郎;森崇;金平孝博;杉森博行, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2022年09月, 日本医学物理学会, 奨励賞
    PET検査における医療被ばく低減を目指したSRCNNの構築
    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
  • 2022年03月, 日本放射線技術学会北海道支部, 優秀研究賞　　　　　　　　　　　　　　　
    SSIMを用いたPET画像に対する再構成条件の最適化
    葛西悠平;名雲渓太;MANIAWSKI PJ;孫田惠一;平田健司;吉村高明;山品博子
  • 2022年03月, 公益財団法人 北海道科学技術総合振興センター, ノーステック財団理事長賞　　　　　　　　　　　　　　　
    人工知能を用いた前立腺がんに対する 動体追跡陽子線治療計画技術の開発
    吉村 高明, 出版社・新聞社・財団等の賞, 日本国
  • 2022年02月, 令和3年度 家畜診療等技術全国研究集会, 全国農業共済協会長賞　　　　　　　　　　　　　　　
    子牛の急性腹症における超音波検査の有用性
    吉村直彬;吉村高明;音井威重
  • 2021年10月, 日本放射線技術学会, 第49回日本放射線技術学会秋季学術大会 座長推薦優秀研究
    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, 国内学会・会議・シンポジウム等の賞, 日本国
  • 2021年03月, 北海道大学, 令和２年度北海道大学医学部保健学科卒業研究優秀賞　　　　　　　　　　　　　　　
    【学生・指導教員】Deep Learningを用いた放射線治療計画用MRIの画質改善に関する研究
    小亀 翔揮;吉村 高明
  • 2019年06月, Particle Therapy Co-Operative Group(PTCOG), PTCOG58 Travel Fellowship Award　　　　　　　　　　　　　　　
    吉村 高明

論文

  • Automatic Aortic Valve Extraction Using Deep Learning with Contrast-Enhanced Cardiac CT Images
    Soichiro Inomata, Takaaki Yoshimura, Minghui Tang, Shota Ichikawa, Hiroyuki Sugimori
    Journal of Cardiovascular Development and Disease, 12, 1, 3, 3, MDPI AG, 2024年12月25日, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, Purpose: This study evaluates the use of deep learning techniques to automatically extract and delineate the aortic valve annulus region from contrast-enhanced cardiac CT images. Two approaches, namely, segmentation and object detection, were compared to determine their accuracy. Materials and Methods: A dataset of 32 contrast-enhanced cardiac CT scans was analyzed. The segmentation approach utilized the DeepLabv3+ model, while the object detection approach employed YOLOv2. The dataset was augmented through rotation and scaling, and five-fold cross-validation was applied. The accuracy of both methods was evaluated using the Dice similarity coefficient (DSC), and their performance in estimating the aortic valve annulus area was compared. Results: The object detection approach achieved a mean DSC of 0.809, significantly outperforming the segmentation approach, which had a mean DSC of 0.711. Object detection also demonstrated higher precision and recall, with fewer false positives and negatives. The aortic valve annulus area estimation had a mean error of 2.55 mm. Conclusions: Object detection showed superior performance in identifying the aortic valve annulus region, suggesting its potential for clinical application in cardiac imaging. The results highlight the promise of deep learning in improving the accuracy and efficiency of preoperative planning for cardiovascular interventions.
  • Cost-effectiveness analysis for multi adverse events of proton beam therapy for pediatric medulloblastoma in Japan
    Takaaki Yoshimura, Yasuhiro Morii, Honoka Tamori, Ryuki Kita, Takayuki Hashimoto, Hidefumi Aoyama, Katsuhiko Ogasawara
    Journal of Radiation Research, Oxford University Press (OUP), 2024年11月19日, ［査読有り］, ［筆頭著者］, ［国際誌］
    英語, 研究論文（学術雑誌）, Abstract

    Medulloblastomas are one of the most common malignant cancers of the central nervous system in children. Proton beam therapy (PBT) is expected to provide equivalent tumor control to photon therapy while reducing the various adverse events caused by irradiation. Few studies have considered the cost-effectiveness of PBT for pediatric medulloblastoma, considering the multiple adverse effects and reflecting on the latest treatment advancements. A cost-utility analysis of PBT for pediatric medulloblastoma was conducted in a Japanese setting and compared to conventional photon therapy. The analysis was conducted from the public healthcare payer’s perspective, and direct costs for the treatment of radiation therapy and radiation-induced adverse events were included. A Markov model was used, and the health states of secondary cancer, hypothyroidism and hearing loss were defined as adverse events. The time horizon was the lifetime. Incremental cost-effectiveness ratio (ICER) was used as a measurement of cost-effectiveness, with quality-adjusted life years (QALYs) used as an outcome. The costs were estimated from the national fee schedule, and the utility and transition probabilities were estimated from published literature. PBT incurred an additional 1387116 Japanese yen (JPY) and 1.56 QALYs to the comparator. The ICER was JPY 887053/QALY, indicating that PBT was cost-effective, based on the reference value of JPY 5 million/QALY used in the Japanese cost-effectiveness analysis. Deterministic sensitivity analysis showed that the ICER ranged from JPY 284782/QALY to JPY 1918603/QALY as a result of deterministic sensitivity analysis, and probabilistic sensitivity analysis showed that PBT was cost-effective, with a probability of 91.7%.
  • A Hessian-Based Deep Learning Preprocessing Method for Coronary Angiography Image Analysis
    Li Yanjun, Takaaki Yoshimura, Yuto Horima, Hiroyuki Sugimori
    Electronics, 13, 18, 3676, 3676, 2024年09月16日, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）
  • Geometric target margin strategy of proton craniospinal irradiation for pediatric medulloblastoma
    Takaaki Yoshimura, Keigo Kondo, Takayuki Hashimoto, Kentaro Nishioka, Takashi Mori, Takahiro Kanehira, Taeko Matsuura, Seishin Takao, Hiroshi Tamura, Takuya Matsumoto, Kenneth Sutherland, Hidefumi Aoyama
    Journal of Radiation Research, 65, 5, 676, 688, Oxford University Press (OUP), 2024年09月15日, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, Abstract

    In proton craniospinal irradiation (CSI) for skeletally immature pediatric patients, a treatment plan should be developed to ensure that the dose is uniformly delivered to all vertebrae, considering the effects on bone growth balance. The technical (t) clinical target volume (CTV) is conventionally set by manually expanding the CTV from the entire intracranial space and thecal sac, based on the physician’s experience. However, there are differences in contouring methods among physicians. Therefore, we aimed to propose a new geometric target margin strategy. Nine pediatric patients with medulloblastoma who underwent proton CSI were enrolled. We measured the following water equivalent lengths for each vertebra in each patient: body surface to the dorsal spinal canal, vertebral limbus, ventral spinal canal and spinous processes. A simulated tCTV (stCTV) was created by assigning geometric margins to the spinal canal using the measurement results such that the vertebral limb and dose distribution coincided with a margin assigned to account for the uncertainty of the proton beam range. The stCTV with a growth factor (correlation between body surface area and age) and tCTV were compared and evaluated. The median values of each index for cervical, thoracic and lumber spine were: the Hausdorff distance, 9.14, 9.84 and 9.77 mm; mean distance-to-agreement, 3.26, 2.65 and 2.64 mm; Dice coefficient, 0.84, 0.81 and 0.82 and Jaccard coefficient, 0.50, 0.60 and 0.62, respectively. The geometric target margin setting method used in this study was useful for creating an stCTV to ensure consistent and uniform planning., 38970405
  • The Effectiveness of Semi-Supervised Learning Techniques in Identifying Calcifications in X-ray Mammography and the Impact of Different Classification Probabilities
    Miu Sakaida, Takaaki Yoshimura, Minghui Tang, Shota Ichikawa, Hiroyuki Sugimori, Kenji Hirata, Kohsuke Kudo
    Applied Sciences, 14, 14, 5968, 5968, MDPI AG, 2024年07月09日, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, 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.
  • Assessment of changes in vessel area during needle manipulation in microvascular anastomosis using a deep learning-based semantic segmentation algorithm: A pilot study.
    Minghui Tang, Taku Sugiyama, Ren Takahari, Hiroyuki Sugimori, Takaaki Yoshimura, Katsuhiko Ogasawara, Kohsuke Kudo, Miki Fujimura
    Neurosurgical review, 47, 1, 200, 200, 2024年05月09日, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, 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.
  • Development of a Method for Estimating the Angle of Lumbar Spine X-ray Images Using Deep Learning with Pseudo X-ray Images Generated from Computed Tomography
    Ryuma Moriya, Takaaki Yoshimura, Minghui Tang, Shota Ichikawa, Hiroyuki Sugimori
    Applied Sciences, 14, 9, 3794, 3794, MDPI AG, 2024年04月29日, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, 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.
  • Deep learning to assess right ventricular ejection fraction from two-dimensional echocardiograms in precapillary pulmonary hypertension.
    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年04月, ［査読有り］, ［責任著者］, ［国際誌］
    英語, 研究論文（学術雑誌）, 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.
  • Probability of normal tissue complications for hematologic and gastrointestinal toxicity in postoperative whole pelvic radiotherapy for gynecologic malignancies using intensity-modulated proton therapy with robust optimization.
    Takaaki Yoshimura, Ryota Yamada, Rumiko Kinoshita, Taeko Matsuura, Takahiro Kanehira, Hiroshi Tamura, Kentaro Nishioka, Koichi Yasuda, Hiroshi Taguchi, Norio Katoh, Keiji Kobashi, Takayuki Hashimoto, Hidefumi Aoyama
    Journal of radiation research, 2024年03月17日, ［査読有り］, ［筆頭著者］, ［国際誌］
    英語, 研究論文（学術雑誌）, This retrospective treatment-planning study was conducted to determine whether intensity-modulated proton therapy with robust optimization (ro-IMPT) reduces the risk of acute hematologic toxicity (H-T) and acute and late gastrointestinal toxicity (GI-T) in postoperative whole pelvic radiotherapy for gynecologic malignancies when compared with three-dimensional conformal radiation therapy (3D-CRT), intensity-modulated X-ray (IMXT) and single-field optimization proton beam (SFO-PBT) therapies. All plans were created for 13 gynecologic-malignancy patients. The prescribed dose was 45 GyE in 25 fractions for 95% planning target volume in 3D-CRT, IMXT and SFO-PBT plans and for 99% clinical target volume (CTV) in ro-IMPT plans. The normal tissue complication probability (NTCP) of each toxicity was used as an in silico surrogate marker. Median estimated NTCP values for acute H-T and acute and late GI-T were 0.20, 0.94 and 0.58 × 10-1 in 3D-CRT; 0.19, 0.65 and 0.24 × 10-1 in IMXT; 0.04, 0.74 and 0.19 × 10-1 in SFO-PBT; and 0.06, 0.66 and 0.15 × 10-1 in ro-IMPT, respectively. Compared with 3D-CRT and IMXT plans, the ro-IMPT plan demonstrated significant reduction in acute H-T and late GI-T. The risk of acute GI-T in ro-IMPT plan is equivalent with IMXT plan. The ro-IMPT plan demonstrated potential clinical benefits for reducing the risk of acute H-T and late GI-T in the treatment of gynecologic malignances by reducing the dose to the bone marrow and bowel bag while maintaining adequate dose coverage to the CTV. Our results indicated that ro-IMPT may reduce acute H-T and late GI-T risk with potentially improving outcomes for postoperative gynecologic-malignancy patients with concurrent chemotherapy., 36844057
  • A Preprocessing Method for Coronary Artery Stenosis Detection Based on Deep Learning
    Yanjun Li, Takaaki Yoshimura, Yuto Horima, Hiroyuki Sugimori
    Algorithms, 17, 3, 119, 119, MDPI AG, 2024年03月13日, ［査読有り］
    英語, 研究論文（学術雑誌）, 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.
  • Development of a Mammography Calcification Detection Algorithm Using Deep Learning with Resolution-Preserved Image Patch Division
    Miu Sakaida, Takaaki Yoshimura, Minghui Tang, Shota Ichikawa, Hiroyuki Sugimori
    Algorithms, 16, 10, 483, 483, MDPI AG, 2023年10月18日, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, 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.
  • Estimation of Left and Right Ventricular Ejection Fractions from cine-MRI Using 3D-CNN
    Soichiro Inomata, Takaaki Yoshimura, Minghui Tang, Shota Ichikawa, Hiroyuki Sugimori
    Sensors, 23, 14, 6580, 6580, MDPI AG, 2023年07月21日, ［査読有り］
    英語, 研究論文（学術雑誌）, 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.
  • Non-Invasive Estimation of Gleason Score by Semantic Segmentation and Regression Tasks Using a Three-Dimensional Convolutional Neural Network
    Takaaki Yoshimura, Keisuke Manabe, Hiroyuki Sugimori
    Applied Sciences, 13, 14, 8028, 8028, MDPI AG, 2023年07月09日, ［査読有り］, ［筆頭著者］, ［国際誌］
    英語, 研究論文（学術雑誌）, 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., 36844057
  • Development of Chest X-ray Image Evaluation Software Using the Deep Learning Techniques
    Kousuke Usui, Takaaki Yoshimura, Shota Ichikawa, Hiroyuki Sugimori
    Applied Sciences, 13, 11, 6695, 6695, MDPI AG, 2023年05月31日, ［査読有り］
    英語, 研究論文（学術雑誌）, 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.
  • Acquisition time reduction in pediatric 99m Tc-DMSA planar imaging using deep learning.
    Shota Ichikawa, Hiroyuki Sugimori, Koki Ichijiri, Takaaki Yoshimura, Akio Nagaki
    Journal of applied clinical medical physics, 24, 6, e13978, 2023年04月05日, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, 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.
  • Age Estimation from Brain Magnetic Resonance Images Using Deep Learning Techniques in Extensive Age Range
    Kousuke Usui, Takaaki Yoshimura, Minghui Tang, Hiroyuki Sugimori
    Applied Sciences, 13, 3, 1753, 1753, MDPI AG, 2023年01月30日, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, 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.
  • Prostatic urinary tract visualization with super-resolution deep learning models.
    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年01月, ［査読有り］, ［筆頭著者］, ［国際誌］
    英語, 研究論文（学術雑誌）, 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., 36844057
  • Efficacy of Abdominal Ultrasonography for Differentiation of Gastrointestinal Diseases in Calves
    Naoaki Yoshimura, Takeshi Tsuka, Takaaki Yoshimura, Takeshige Otoi
    Animals, 12, 19, 2489, 2489, MDPI AG, 2022年09月20日, ［査読有り］
    英語, 研究論文（学術雑誌）, This study investigated the clinical efficacy of abdominal ultrasonography for abomasal dilation in three calves, intestinal volvulus in five calves, intussusception in one calf, and internal hernia in one calf. In the abdominal ultrasonograms of the abomasal dilation cases, this disease was commonly characterized by severely extended lumens, including heterogeneously hyperechoic ingesta without intraluminal accumulations of gas. In the animals with intestinal volvulus and intussusception, a to-and-fro flow was observed to be a common ultrasonographic characteristic that led to suspicion of an intestinal obstruction. The use of abdominal ultrasonography for five cases with intestinal volvulus gave no reason to suspect this disease, despite its efficacy in one case, based on an acutely angled narrowing. Although three of five animals with intestinal volvulus had intestinal ruptures, no ultrasonographic evidence could be obtained. When abdominal ultrasonography was used for one case with intussusception, this pathological condition could be strongly suspected, as a “target” sign was observed. This finding supported surgical intervention for this case, followed by treatment with manual reduction, resulting in a favorable outcome. In terms of the differential and definitive diagnosis for various intestinal diseases, abdominal ultrasonography may be poor at providing indicative evidence, but very helpful for confirming intestinal obstruction.
  • Dosimetric advantages of daily adaptive strategy in IMPT for high‐risk prostate cancer
    Hiroshi Tamura, Keiji Kobashi, Kentaro Nishioka, Takaaki Yoshimura, Takayuki Hashimoto, Shinichi Shimizu, Yoichi M. Ito, Yoshikazu Maeda, Makoto Sasaki, Kazutaka Yamamoto, Hiroyasu Tamamura, Hidefumi Aoyama, Hiroki Shirato
    Journal of Applied Clinical Medical Physics, 23, 4, e13531, Wiley, 2022年04月, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, PURPOSE: To evaluate the dosimetric advantages of daily adaptive radiotherapy (DART) in intensity-modulated proton therapy (IMPT) for high-risk prostate cancer by comparing estimated doses of the conventional non-adaptive radiotherapy (NART) that irradiates according to an original treatment plan through the entire treatment and the DART that uses an adaptive treatment plan generated by using daily CT images acquired before each treatment. METHODS: Twenty-three patients with prostate cancer were included. A treatment plan with 63 Gy (relative biological effectiveness (RBE)) in 21 fractions was generated using treatment planning computed tomography (CT) images assuming that all patients had high-risk prostate cancer for which the clinical target volume (CTV) needs to include prostate and the seminal vesicle (SV) in our treatment protocol. Twenty-one adaptive treatment plans for each patient (total 483 data sets) were generated using daily CT images, and dose distributions were calculated. Using a 3 mm set-up uncertainty in the robust optimization, the doses to the CTV, prostate, SV, rectum, and bladder were compared. RESULTS: Estimated accumulated doses of NART and DART in the 23 patients were 60.81 ± 3.47 Gy (RBE) and 63.24 ± 1.04 Gy (RBE) for CTV D99 (p < 0.01), 62.99 ± 1.28 Gy (RBE) and 63.43 ± 1.33 Gy (RBE) for the prostate D99 (p = 0.2529), and 59.07 ± 5.19 Gy (RBE) and 63.17 ± 1.04 Gy (RBE) for SV D99 (p < 0.001). No significant differences were observed between NART and DART in the estimated accumulated dose for the rectum and bladder. CONCLUSION: Compared with the NART, DART was shown to be a useful approach that can maintain the dose coverage to the target without increasing the dose to the organs at risk (OAR) using the 3 mm set-up uncertainty in the robust optimization in patients with high-risk prostate cancer.
  • Medical Radiation Exposure Reduction in PET via Super-Resolution Deep Learning Model
    Takaaki Yoshimura, Atsushi Hasegawa, Shoki Kogame, Keiichi Magota, Rina Kimura, Shiro Watanabe, Kenji Hirata, Hiroyuki Sugimori
    Diagnostics, 12, 4, 872, 872, MDPI AG, 2022年03月31日, ［査読有り］, ［筆頭著者］, ［国際誌］
    英語, 研究論文（学術雑誌）, 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., 33179641
  • Development of Detection and Volumetric Methods for the Triceps of the Lower Leg Using Magnetic Resonance Images with Deep Learning
    Yusuke Asami, Takaaki Yoshimura, Keisuke Manabe, Tomonari Yamada, Hiroyuki Sugimori
    Applied Sciences, 11, 24, 12006, 12006, MDPI AG, 2021年12月16日, ［査読有り］
    英語, 研究論文（学術雑誌）, 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.
  • Are simple verbal instructions sufficient to ensure that bladder volume does not deteriorate prostate position reproducibility during spot scanning proton therapy?
    Kentaro Nishioka, Kento Gotoh, Takayuki Hashimoto, Takashige Abe, Takahiro Osawa, Ryuji Matsumoto, Isao Yokota, Norio Katoh, Rumiko Kinoshita, Koichi Yasuda, Toshiaki Yakabe, Takaaki Yoshimura, Seishin Takao, Nobuo Shinohara, Hidefumi Aoyama, Shinichi Shimizu, Hiroki Shirato
    BJR|Open, 3, 1, 20210064, 20210064, British Institute of Radiology, 2021年11月, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, Objectives: The purpose of this study is to investigate whether verbal instructions are sufficient for bladder volume (BV) control not to deteriorate prostate position reproducibility in image-guided spot scanning proton therapy (SSPT) for localized prostate cancer.

    Methods: A total of 268 treatment sessions in 12 consecutive prostate cancer patients who were treated with image-guided SSPT with fiducial markers were retrospectively analyzed. In addition to strict rectal volume control procedures, simple verbal instructions to void urine one hour before the treatment were used here. The BV was measured by a Bladder Scan just before the treatment, and the prostate motion was measured by intraprostatic fiducial markers and two sets of X-ray fluoroscopy images. The correlation between the BV change and prostate motion was assessed by linear mixed-effects models and systematic and random errors according to the reproducibility of the BV.

    Results: The mean absolute BV change during treatment was from −98.7 to 86.3 ml (median 7.1 ml). The mean absolute prostate motion of the patients in the left-right direction was −1.46 to 1.85 mm; in the cranial-caudal direction it was −6.10 to 3.65 mm, and in the anteroposterior direction −1.90 to 5.23 mm. There was no significant relationship between the BV change and prostate motion during SSPT. The early and late genitourinary and gastrointestinal toxicity was minimal with a minimum follow up of 4.57 years.

    Conclusions: Simple verbal instructions about urination was suggested to be sufficient to control the BV not to impact on the prostate motion and clinical outcomes in image-guided SSPT. Careful attention to BV change is still needed when the seminal vesicle is to be treated.

    Advances in knowledge: Our data demonstrated that there was no apparent relationship between BV changes and prostate position reproducibility and simple verbal instruction about urination could be sufficient for image-guided SSPT.

  • A treatment planning study of urethra-sparing intensity-modulated proton therapy for localized prostate cancer
    Takaaki Yoshimura, Kentaro Nishioka, Takayuki Hashimoto, Kazuya Seki, Shouki Kogame, Sodai Tanaka, Takahiro Kanehira, Masaya Tamura, Seishin Takao, Taeko Matsuura, Keiji Kobashi, Fumi Kato, Hidefumi Aoyama, Shinichi Shimizu
    Physics and Imaging in Radiation Oncology, 20, 23, 29, Elsevier BV, 2021年10月, ［査読有り］, ［筆頭著者］, ［国際誌］
    英語, 研究論文（学術雑誌）, BACKGROUND AND PURPOSE: Urethra-sparing radiation therapy for localized prostate cancer can reduce the risk of radiation-induced genitourinary toxicity by intentionally underdosing the periurethral transitional zone. We aimed to compare the clinical impact of a urethra-sparing intensity-modulated proton therapy (US-IMPT) plan with that of conventional clinical plans without urethral dose reduction. MATERIALS AND METHODS: This study included 13 patients who had undergone proton beam therapy. The prescribed dose was 63 GyE in 21 fractions for 99% of the clinical target volume. To compare the clinical impact of the US-IMPT plan with that of the conventional clinical plan, tumor control probability (TCP) and normal tissue complication probability (NTCP) were calculated with a generalized equivalent uniform dose-based Lyman-Kutcher model using dose volume histograms. The endpoints of these model parameters for the rectum, bladder, and urethra were fistula, contraction, and urethral stricture, respectively. RESULTS: The mean NTCP value for the urethra in US-IMPT was significantly lower than that in the conventional clinical plan (0.6% vs. 1.2%, p < 0.05). There were no statistically significant differences between the conventional and US-IMPT plans regarding the mean minimum dose for the urethra with a 3-mm margin, TCP value, and NTCP value for the rectum and bladder. Additionally, the target dose coverage of all plans in the robustness analysis was within the clinically acceptable range. CONCLUSIONS: Compared with the conventional clinically applied plans, US-IMPT plans have potential clinical advantages and may reduce the risk of genitourinary toxicities, while maintaining the same TCP and NTCP in the rectum and bladder., 13099649
  • Cost-effectiveness analysis using lifetime attributable risk of proton beam therapy for pediatric medulloblastoma in Japan.
    Takaaki Yoshimura, Honoka Tamori, Yasuhiro Morii, Takayuki Hashimoto, Shinichi Shimizu, Katsuhiko Ogasawara
    Journal of radiation research, 2021年09月29日, ［査読有り］, ［筆頭著者］, ［国際誌］
    英語, 研究論文（学術雑誌）, Compared to conventional X-ray therapy, proton beam therapy (PBT) has more clinical and physical advantages such as irradiation dose reduction to normal tissues for pediatric medulloblastoma. However, PBT is expensive. We aimed to compare the cost-effectiveness of PBT for pediatric medulloblastoma with that of conventional X-ray therapy, while focusing on radiation-induced secondary cancers, which are rare, serious and negatively affect a patient's quality of life (QOL). Based on a systematic review, a decision tree model was used for the cost-effectiveness analysis. This analysis was performed from the perspective of health care payers; the cost was estimated from medical fees. The target population was pediatric patients with medulloblastoma below 14 years old. The time horizon was set at 7.7 years after medulloblastoma treatment. The primary outcome was the incremental cost-effectiveness ratio (ICER), which was defined as the ratio of the difference in cost and lifetime attributable risk (LAR) between conventional X-ray therapy and PBT. The discount rate was set at 2% annually. Sensitivity analyses were performed to model uncertainty. Cost and LAR in conventional X-ray therapy and PBT were Japanese yen (JPY) 1 067 608 and JPY 2436061 and 42% and 7%, respectively. The ICER was JPY 3856398/LAR. In conclusion, PBT is more cost-effective than conventional X-ray therapy in reducing the risk of radiation-induced secondary cancers in pediatric medulloblastoma. Thus, our constructed ICER using LAR is one of the valid indicators for cost-effectiveness analysis in radiation-induced secondary cancer.
  • Ophthalmic findings in a septic calf with the concurrent exhibition of meningitis and endophthalmitis.
    Naoaki Yoshimura, Takeshi Tsuka, Yuji Sunden, Takehito Morita, Md Shafiqul Islam, Osamu Yamato, Takaaki Yoshimura
    The Journal of veterinary medical science, 2021年09月14日, ［査読有り］, ［国内誌］
    英語, 研究論文（学術雑誌）, The aim of this study was to evaluate the impacts of ophthalmic findings obtained from both macroscopic examination and ocular ultrasonography when diagnosing bovine endophthalmitis. A newborn crossbreed (Japanese black and Holstein breeds) calf was suspected of visual impairment and central nervous system (CNS) symptoms, such as decreased activity and weak drinking performance. This calf was found to display macroscopic signs, such as clouded lens, convergent strabismus, and horizontal nystagmus, in both eyes. On ocular ultrasonography of both eyes, a V-shaped, thickened, hyperechoic structure was present in the anechoic vitreous humors, indicating retinal detachment. The animal died 4 days after the examination. Sepsis was evident in this case, as Escherichia coli was isolated from multiple organs. The autopsy and histological examination revealed meningitis, encephalitis, and secondary hydrocephalus in the CNS, and endophthalmitis and retinal detachment in both eyes. In this case, the ophthalmic findings did not provide definitive evidence for a diagnosis of endophthalmitis. However, this study indicated that retinal detachment might be an ultrasonographic finding that is suggestive of bovine endophthalmitis.
  • First experimental results of gated proton imaging using x-ray fluoroscopy to detect a fiducial marker.
    Sodai Tanaka, Naoki Miyamoto, Yuto Matsuo, Takaaki Yoshimura, Seishin Takao, Taeko Matsuura
    Physics in medicine and biology, 66, 18, 2021年09月09日, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, Increasing numbers of proton imaging research studies are being conducted for accurate proton range determination in proton therapy treatment planning. However, there is no proton imaging system that deals with motion artifacts. In this study, a gated proton imaging system was developed and the first experimental results of proton radiography were obtained for a moving object without motion artifacts. A motion management system using dual x-ray fluoroscopy for detecting a spherical gold fiducial marker was introduced and the proton beam was gated in accordance with the motion of the object. To demonstrate the performance of the gated proton imaging system, gated proton radiography images of a moving phantom were acquired experimentally, and the motion artifacts clearly were diminished. Also, the factors causing image deteriorations were evaluated focusing on the new gating system developed here, and the main factor was identified as the latency (with a maximum value of 93 ms) between the ideal gating signal according to the actual marker position and the actual gating signal. The possible deterioration due to the latency of the proton imaging system and proton beam irradiation was small owing to appropriate setting of the time structure.
  • Visualizing the urethra by magnetic resonance imaging without usage of a catheter for radiotherapy of prostate cancer
    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年04月, ［査読有り］, ［筆頭著者］
    研究論文（学術雑誌）, 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)., 13099649
  • Construction of a detachable artificial trachea model for three age groups for use in an endotracheal suctioning training environment simulator.
    Takaaki Yoshimura, Noriyo Colley, Shunsuke Komizunai, Shinji Ninomiya, Satoshi Kanai, Atsushi Konno, Koichi Yasuda, Hiroshi Taguchi, Takayuki Hashimoto, Shinichi Shimizu
    PloS one, 16, 3, e0249010, 2021年, ［査読有り］, ［筆頭著者］, ［国際誌］
    英語, 研究論文（学術雑誌）, Tracheal suctioning is an important procedure to maintain airway patency by removing secretions. Today, suctioning operators include not only medical staff, but also family caregivers. The use of a simulation system has been noted to be the most effective way to learn the tracheal suctioning technique for operators. While the size of the trachea varies across different age groups, the artificial trachea model in the simulation system has only one fixed model. Thus, this study aimed to construct multiple removable trachea models according to different age groups. We enrolled 20 patients who had previously received proton beam therapy in our institution and acquired the treatment planning computed tomography (CT) image data. To construct the artificial trachea model for three age groups (children, adolescents and young adults, and adults), we analyzed the three-dimensional coordinates of the entire trachea, tracheal carina, and the end of the main bronchus. We also analyzed the diameter of the trachea and main bronchus. Finally, we evaluated the accuracy of the model by analyzing the difference between the constructed model and actual measurements. The trachea model was 8 cm long for children and 12 cm for adolescents and young adults, and for adults. The angle between the trachea and bed was about 20 degrees, regardless of age. The mean model accuracy was less than 0.4 cm. We constructed detachable artificial trachea models for three age groups for implementation in the endotracheal suctioning training environment simulator (ESTE-SIM) based on the treatment planning CT image. Our constructed artificial trachea models will be able to provide a simulation environment for various age groups in the ESTE-SIM.
  • Potential benefits of adaptive intensity-modulated proton therapy in nasopharyngeal carcinomas.
    Hideki Minatogawa, Koichi Yasuda, Yasuhiro Dekura, Seishin Takao, Taeko Matsuura, Takaaki Yoshimura, Ryusuke Suzuki, Isao Yokota, Noriyuki Fujima, Rikiya Onimaru, Shinichi Shimizu, Hidefumi Aoyama, Hiroki Shirato
    Journal of applied clinical medical physics, 22, 1, 174, 183, 2021年01月, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, PURPOSE: To investigate potential advantages of adaptive intensity-modulated proton beam therapy (A-IMPT) by comparing it to adaptive intensity-modulated X-ray therapy (A-IMXT) for nasopharyngeal carcinomas (NPC). METHODS: Ten patients with NPC treated with A-IMXT (step and shoot approach) and concomitant chemotherapy between 2014 and 2016 were selected. In the actual treatment, 46 Gy in 23 fractions (46Gy/23Fx.) was prescribed using the initial plan and 24Gy/12Fx was prescribed using an adapted plan thereafter. New treatment planning of A-IMPT was made for the same patients using equivalent dose fractionation schedule and dose constraints. The dose volume statistics based on deformable images and dose accumulation was used in the comparison of A-IMXT with A-IMPT. RESULTS: The means of the Dmean of the right parotid gland (P < 0.001), right TM joint (P < 0.001), left TM joint (P < 0.001), oral cavity (P < 0.001), supraglottic larynx (P = 0.001), glottic larynx (P < 0.001), , middle PCM (P = 0.0371), interior PCM (P < 0.001), cricopharyngeal muscle (P = 0.03643), and thyroid gland (P = 0.00216), in A-IMPT are lower than those of A-IMXT, with statistical significance. The means of, D0.03cc , and Dmean of each sub portion of auditory apparatus and D30% for Eustachian tube and D0.5cc for mastoid volume in A-IMPT are significantly lower than those of A-IMXT. The mean doses to the oral cavity, supraglottic larynx, and glottic larynx were all reduced by more than 20 Gy (RBE = 1.1). CONCLUSIONS: An adaptive approach is suggested to enhance the potential benefit of IMPT compared to IMXT to reduce adverse effects for patients with NPC.
  • Proton dose calculation based on converting dual-energy CT data to stopping power ratio (DEEDZ-SPR): a beam-hardening assessment.
    Sodai Tanaka, Yoshiyuki Noto, Satoru Utsunomiya, Takaaki Yoshimura, Taeko Matsuura, Masatoshi Saito
    Physics in medicine and biology, 65, 23, 235046, 235046, IOP Publishing, 2020年12月18日, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, To achieve an accurate stopping power ratio (SPR) prediction in particle therapy treatment planning, we previously proposed a simple conversion to the SPR from dual-energy (DE) computed tomography (CT) data via electron density and effective atomic number (Z eff) calibration (DEEDZ-SPR). This study was conducted to carry out an initial implementation of the DEEDZ-SPR conversion method with a clinical treatment planning system (TPS; VQA, Hitachi Ltd., Tokyo) for proton beam therapy. Consequently, this paper presents a proton therapy plan for an anthropomorphic phantom to evaluate the stability of the dose calculations obtained by the DEEDZ-SPR conversion against the variation of the calibration phantom size. Dual-energy x-ray CT images were acquired using a dual-source CT (DSCT) scanner. A single-energy CT (SECT) scan using the same DSCT scanner was also performed to compare the DEEDZ-SPR conversion with the SECT-based SPR (SECT-SPR) conversion. The scanner-specific parameters necessary for the SPR calibration were obtained from the CT images of tissue substitutes in a calibration phantom. Two calibration phantoms with different sizes (a 33 cm diameter phantom and an 18 cm diameter phantom) were used for the SPR calibrations to investigate the beam-hardening effect on dosimetric uncertainties. Each set of calibrated SPR data was applied to the proton therapy plan designed using the VQA TPS with a pencil beam algorithm for the anthropomorphic phantom. The treatment plans with the SECT-SPR conversion exhibited discrepancies between the dose distributions and the dose-volume histograms (DVHs) of the 33 cm and 18 cm phantom calibrations. In contrast, the corresponding dose distributions and the DVHs obtained using the DEEDZ-SPR conversion method coincided almost perfectly with each other. The DEEDZ-SPR conversion appears to be a promising method for providing proton dose plans that are stable against the size variations of the calibration phantom and the patient.
  • Quantitative analysis of treatments using real-time image gated spot-scanning with synchrotron-based proton beam therapy system log data.
    Takaaki Yoshimura, Shinichi Shimizu, Takayuki Hashimoto, Kentaro Nishioka, Norio Katoh, Hiroshi Taguchi, Koichi Yasuda, Taeko Matsuura, Seishin Takao, Masaya Tamura, Sodai Tanaka, Yoichi M Ito, Yuto Matsuo, Hiroshi Tamura, Kenji Horita, Kikuo Umegaki, Hiroki Shirato
    Journal of applied clinical medical physics, 21, 12, 10, 19, 2020年12月, ［査読有り］, ［筆頭著者］, ［国際誌］
    英語, 研究論文（学術雑誌）, A synchrotron-based real-time image gated spot-scanning proton beam therapy (RGPT) system with inserted fiducial markers can irradiate a moving tumor with high accuracy. As gated treatments increase the beam delivery time, this study aimed to investigate the frequency of intra-field adjustments corresponding to the baseline shift or drift and the beam delivery efficiency of a synchrotron-based RGPT system. Data from 118 patients corresponding to 127 treatment plans and 2810 sessions between October 2016 and March 2019 were collected. We quantitatively analyzed the proton beam delivery time, the difference between the ideal beam delivery time based on a simulated synchrotron magnetic excitation pattern and the actual treatment beam delivery time, frequency corresponding to the baseline shift or drift, and the gating efficiency of the synchrotron-based RGPT system according to the proton beam delivery machine log data. The mean actual beam delivery time was 7.1 min, and the simulated beam delivery time in an ideal environment with the same treatment plan was 2.9 min. The average difference between the actual and simulated beam delivery time per session was 4.3 min. The average frequency of intra-field adjustments corresponding to baseline shift or drift and beam delivery efficiency were 21.7% and 61.8%, respectively. Based on our clinical experience with a synchrotron-based RGPT system, we determined the frequency corresponding to baseline shift or drift and the beam delivery efficiency using the beam delivery machine log data. To maintain treatment accuracy within ± 2.0 mm, intra-field adjustments corresponding to baseline shift or drift were required in approximately 20% of cases. Further improvements in beam delivery efficiency may be realized by shortening the beam delivery time., 13099649
  • Analysis of treatment process time for real-time-image gated-spot-scanning proton-beam therapy (RGPT) system.
    Takaaki Yoshimura, Shinichi Shimizu, Takayuki Hashimoto, Kentaro Nishioka, Norio Katoh, Tetsuya Inoue, Hiroshi Taguchi, Koichi Yasuda, Taeko Matsuura, Seishin Takao, Masaya Tamura, Yoichi M Ito, Yuto Matsuo, Hiroshi Tamura, Kenji Horita, Kikuo Umegaki, Hiroki Shirato
    Journal of applied clinical medical physics, 21, 2, 38, 49, 2020年02月, ［査読有り］, ［筆頭著者］, ［国際誌］
    英語, 研究論文（学術雑誌）, We developed a synchrotron-based real-time-image gated-spot-scanning proton-beam therapy (RGPT) system and utilized it to clinically operate on moving tumors in the liver, pancreas, lung, and prostate. When the spot-scanning technique is linked to gating, the beam delivery time with gating can increase, compared to that without gating. We aim to clarify whether the total treatment process can be performed within approximately 30 min (the general time per session in several proton therapy facilities), even for gated-spot-scanning proton-beam delivery with implanted fiducial markers. Data from 152 patients, corresponding to 201 treatment plans and 3577 sessions executed from October 2016 to June 2018, were included in this study. To estimate the treatment process time, we utilized data from proton beam delivery logs during the treatment for each patient. We retrieved data, such as the disease site, total target volume, field size at the isocenter, and the number of layers and spots for each field, from the treatment plans. We quantitatively analyzed the treatment process, which includes the patient load (or setup), bone matching, marker matching, beam delivery, patient unload, and equipment setup, using the data obtained from the log data. Among all the cases, 90 patients used the RGPT system (liver: n = 34; pancreas: n = 5; lung: n = 4; and prostate: n = 47). The mean and standard deviation (SD) of the total treatment process time for the RGPT system was 30.3 ± 7.4 min, while it was 25.9 ± 7.5 min for those without gating treatment, excluding craniospinal irradiation (CSI; head and neck: n = 16, pediatric: n = 31, others: n = 15); for CSI (n = 11) with two or three isocenters, the process time was 59.9 ± 13.9 min. Our results demonstrate that spot-scanning proton therapy with a gating function can be achieved in approximately 30-min time slots., 13099649
  • The urethral position may shift due to urethral catheter placement in the treatment planning for prostate radiation therapy.
    Yasuhiro Dekura, Kentaro Nishioka, Takayuki Hashimoto, Naoki Miyamoto, Ryusuke Suzuki, Takaaki Yoshimura, Ryuji Matsumoto, Takahiro Osawa, Takashige Abe, Yoichi M Ito, Nobuo Shinohara, Hiroki Shirato, Shinichi Shimizu
    Radiation oncology (London, England), 14, 1, 226, 226, 2019年12月12日, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, PURPOSE: To determine the best method to contour the planning organ at risk volume (PRV) for the urethra, this study aimed to investigate the displacement of a Foley catheter in the urethra with a soft and thin guide-wire. METHODS: For each patient, the study used two sets of computed tomography (CT) images for radiation treatment planning (RT-CT): (1) set with a Foley urethral catheter (4.0 mm diameter) plus a guide-wire (0.46 mm diameter) in the first RT-CT and (2) set with a guide-wire alone in the second CT recorded 2 min after the first RT-CT. Using three fiducial markers in the prostate for image fusion, the displacement between the catheter and the guide-wire in the prostatic urethra was calculated. In 155 consecutive patients treated between 2011 and 2017, 5531 slices of RT-CT were evaluated. RESULTS: Assuming that ≥3.0 mm of difference between the catheter and the guide-wire position was a significant displacement, the urethra with the catheter was displaced significantly from the urethra with the guide-wire alone in > 20% of the RT-CT slices in 23.2% (36/155) of the patients. The number of patients who showed ≥3.0 mm anterior displacement with the catheter in ≥20% RT-CT slices was significantly larger at the superior segment (38/155) than at the middle (14/155) and inferior segments (18/155) of the prostatic urethra (p < 0.0167). CONCLUSIONS: The urethral position with a Foley catheter is different from the urethral position with a thin and soft guide-wire in a significant proportion of the patients. This should be taken into account for the PRV of the urethra to ensure precise radiotherapy such as in urethra-sparing radiotherapy., 13099649
  • Clinical experience of craniospinal intensity-modulated spot-scanning proton therapy using large fields for central nervous system medulloblastomas and germ cell tumors in children, adolescents, and young adults.
    Takayuki Hashimoto, Shinichi Shimizu, Seishin Takao, Shunsuke Terasaka, Akihiro Iguchi, Hiroyuki Kobayashi, Takashi Mori, Takaaki Yoshimura, Yuto Matsuo, Masaya Tamura, Taeko Matsuura, Yoichi M Ito, Rikiya Onimaru, Hiroki Shirato
    Journal of radiation research, 60, 4, 527, 537, 2019年07月01日, ［査読有り］, ［国際誌］
    英語, 研究論文（学術雑誌）, The outcomes of intensity-modulated proton craniospinal irradiation (ipCSI) are unclear. We evaluated the clinical benefit of our newly developed ipCSI system that incorporates two gantry-mounted orthogonal online X-ray imagers with a robotic six-degrees-of-freedom patient table. Nine patients (7-19 years old) were treated with ipCSI. The prescribed dose for CSI ranged from 23.4 to 36.0 Gy (relative biological effectiveness) in 13-20 fractions. Four adolescent and young adult (AYA) patients (15 years or older) were treated with vertebral-body-sparing ipCSI (VBSipCSI). Myelosuppression following VBSipCSI was compared with that of eight AYA patients treated with photon CSI at the same institution previously. The mean homogeneity index (HI) in the nine patients was 0.056 (95% confidence interval: 0.044-0.068). The mean time from the start to the end of all beam delivery was 37 min 39 s ± 2 min 24 s (minimum to maximum: 22 min 49 s - 42 min 51 s). The nadir white blood cell, hemoglobin, and platelet levels during the 4 weeks following the end of the CSI were significantly higher in the VBSipCSI group than in the photon CSI group (P = 0.0071, 0.0453, 0.0024, respectively). The levels at 4 weeks after the end of CSI were significantly higher in the VBSipCSI group than in the photon CSI group (P = 0.0023, 0.0414, 0.0061). Image-guided ipCSI was deliverable in a reasonable time with sufficient HI. Using VBSipCSI, AYA patients experienced a lower incidence of serious acute hematological toxicity than AYA patients treated with photon CSI.
  • Physical and biological impacts of collimator-scattered protons in spot-scanning proton therapy.
    Ueno K, Matsuura T, Hirayama S, Takao S, Ueda H, Matsuo Y, Yoshimura T, Umegaki K
    Journal of applied clinical medical physics, 20, 7, 48, 57, Wiley, 2019年06月, ［査読有り］
    研究論文（学術雑誌）
  • NTCP modeling analysis of acute hematologic toxicity in whole pelvic radiation therapy for gynecologic malignancies - A dosimetric comparison of IMRT and spot-scanning proton therapy (SSPT)
    Takaaki Yoshimura, Rumiko Kinoshita, Shunsuke Onodera, Chie Toramatsu, Ryusuke Suzuki, Yoichi M. Ito, Seishin Takao, Taeko Matsuura, Yuka Matsuzaki, Kikuo Umegaki, Hiroki Shirato, Shinichi Shimizu
    PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS, 32, 9, 1095, 1102, ELSEVIER SCI LTD, 2016年09月, ［査読有り］, ［筆頭著者］
    英語, 研究論文（学術雑誌）, Purpose: This treatment planning study was conducted to determine whether spot scanning proton beam therapy (SSPT) reduces the risk of grade >= 3 hematologic toxicity (HT3+) compared with intensity modulated radiation therapy (IMRT) for postoperative whole pelvic radiation therapy (WPRT).
    Methods and materials: The normal tissue complication probability (NTCP) of the risk of HT3+ was used as an in silico surrogate marker in this analysis. IMRT and SSPT plans were created for 13 gynecologic malignancy patients who had received hysterectomies. The IMRT plans were generated using the 7-fields step and shoot technique. The SSPT plans were generated using anterior-posterior field with single field optimization. Using the relative biological effectives (RBE) value of 1.0 for IMRT and 1.1 for SSPT, the prescribed dose was 45 Gy(RBE) in 1.8 Gy(RBE) per fractions for 95% of the planning target volume (PTV). The homogeneity index (HI) and the conformity index (CI) of the PTV were also compared.
    Results: The bone marrow (BM) and femoral head doses using SSPT were significantly lower than with IMRT. The NTCP modeling analysis showed that the risk of HT3+ using SSPT was significantly lower than with IMRT (NTCP = 0.04 +/- 0.01 and 0.19 +/- 0.03, p = 0.0002, respectively). There were no significant differences in the CI and HI of the PTV between IMRT and SSPT (CI = 0.97 +/- 0.01 and 0.96 +/- 0.02, p = 0.3177, and HI = 1.24 +/- 0.11 and 1.27 +/- 0.05, p = 0.8473, respectively).
    Conclusion: The SSPT achieves significant reductions in the dose to BM without compromising target coverage, compared with IMRT. The NTCP value for HT3+ in SSPT was significantly lower than in IMRT. (C) 2016 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license.
  • Aldehyde oxidase 1 gene is regulated by Nrf2 pathway
    Kenichiro Maeda, Takashi Ohno, Shizuka Igarashi, Takaaki Yoshimura, Koji Yamashiro, Masaharu Sakai
    GENE, 505, 2, 374, 378, ELSEVIER SCIENCE BV, 2012年09月, ［査読有り］
    英語, 研究論文（学術雑誌）, Aldehyde oxidase is a member of the molybd-flavo enzyme family that catalyzes the hydroxylation of heterocycles and the oxidation of aldehydes into corresponding carboxylic acids. Aldehyde oxidase-1 (AOX1) is highly expressed in liver and is involved in the oxidation of a variety of aldehydes and nitrogenous heterocyclic compounds, including anti-cancer and immunosuppressive drugs. However, the physiological substrates of AOX1 have not been identified, and it was unknown how the expression of AOX1 is regulated. Here, we found that the AOX1 gene is regulated by the Nrf2 pathway. Two Nrf2 binding consensus elements (antioxidant responsive element, ARE) are located in the 5' upstream region of the rat AOX1 gene. Molecular analyses using reporter transfection analysis, EMSA, and ChIP analysis show that Nrf2 binds to and strongly activates the rat AOX1 gene. (C) 2012 Elsevier B.V. All rights reserved.

その他活動・業績

書籍等出版物

  • A Decade of Health Sciences in Asia: Looking Back at the FHS International Conference　　　　　　　　　　　　　　　
    Faculty of Health Sciences, Hokkaido University, 2023年03月01日, 9784600011901, 英語

担当経験のある科目_授業

  • 大学院共通授業科目（教育プログラム）：社会と健康 社会と健康Ⅳ（健康増進科目）〜健康科学特論　　　　　　　　　　　　　　　
    北海道大学
    2024年04月 - 現在, 日本国
  • 健康科学特論　　　　　　　　　　　　　　　
    北海道大学（大学院保健科学院）
    2024年04月 - 現在, 大学院専門科目, 日本国
  • 放射化学実験　　　　　　　　　　　　　　　
    北海道大学（医学部保健学科）
    2024年04月 - 現在, 学部専門科目, 日本国
  • 実践臨床画像学　　　　　　　　　　　　　　　
    北海道大学（医学部保健学科）
    2024年04月 - 現在, 学部専門科目, 日本国
  • 医学総論 医学AI特論科目～データハンドリング演習特論　　　　　　　　　　　　　　　
    北海道大学（大学院医学院）
    2023年04月 - 現在, 大学院専門科目, 日本国
  • 医学総論 医学AI特論科目～診断・治療支援特論　　　　　　　　　　　　　　　
    北海道大学（大学院医学院）
    2023年04月 - 現在, 大学院専門科目, 日本国
  • 医学総論 医学AIコア科目～医学AIセミナー　　　　　　　　　　　　　　　
    北海道大学（大学院医学院）
    2023年04月 - 現在, 大学院専門科目, 日本国
  • 基本医学総論 医学AIコア科目～医学AIセミナー　　　　　　　　　　　　　　　
    北海道大学（大学院医学院）
    2023年04月 - 現在, 大学院専門科目, 日本国
  • 基本医学総論 医学AI特論科目～診断・治療支援特論　　　　　　　　　　　　　　　
    北海道大学（大学院医学院）
    2023年04月 - 現在, 大学院専門科目, 日本国
  • 基本医学総論 医学AI特論科目～データハンドリング演習特論　　　　　　　　　　　　　　　
    北海道大学（大学院医学院）
    2023年04月 - 現在, 大学院専門科目, 日本国
  • 保健科学特別研究　　　　　　　　　　　　　　　
    北海道大学（大学院保健科学院）
    2022年04月 - 現在, 大学院専門科目, 日本国
  • 保健科学研究　　　　　　　　　　　　　　　
    北海道大学（大学院保健科学院）
    2022年04月 - 現在, 大学院専門科目, 日本国
  • 保健・医療概論　　　　　　　　　　　　　　　
    北海道大学（医学部保健学科）
    2021年04月 - 現在
  • 医療情報学　　　　　　　　　　　　　　　
    北海道大学（医学部保健学科）
    2019年04月 - 現在
  • 医用機器工学実習　　　　　　　　　　　　　　　
    北海道大学（医学部保健学科）
    2019年04月 - 現在
  • 基礎放射線治療技術学実習　　　　　　　　　　　　　　　
    北海道大学（医学部保健学科）
    2019年04月 - 現在
  • 基礎撮影技術学実習　　　　　　　　　　　　　　　
    北海道大学（医学部保健学科）
    2019年04月 - 現在
  • 放射線腫瘍学　　　　　　　　　　　　　　　
    北海道大学（医学部保健学科）
    2019年04月 - 現在
  • 保健解剖学演習　　　　　　　　　　　　　　　
    北海道大学（医学部保健学科）
    2019年04月 - 現在
  • 臨床実習Ⅰ～Ⅵ　　　　　　　　　　　　　　　
    北海道大学（医学部保健学科）
    2019年04月 - 現在
  • 卒業研究　　　　　　　　　　　　　　　
    北海道大学（医学部保健学科）
    2019年04月 - 現在
  • 放射線計測学実習　　　　　　　　　　　　　　　
    北海道大学（医学部保健学科）
    2019年04月 - 現在

所属学協会

共同研究・競争的資金等の研究課題

  • 適応放射線治療における線量合算の定量評価と不確かさ低減のための統合的アプローチ
    科学研究費助成事業
    2024年04月01日 - 2027年03月31日
    小橋 啓司, 橋本 孝之, 吉村 高明, 西岡 健太郎
    日本学術振興会, 基盤研究(C), 北海道大学, 24K10878
  • 前立腺癌に対するMR-Only尿道線量低減陽子線治療計画技術の開発
    科学研究費助成事業 若手研究
    2022年04月01日 - 2026年03月31日
    吉村 高明
    日本学術振興会, 若手研究, 北海道大学, 22K15797
  • AIを活用した小児がん陽子線照射のトリプルハイブリッド遠隔治療計画システムの開発
    科学研究費助成事業 基盤研究(C)
    2022年04月01日 - 2025年03月31日
    橋本 孝之, 高尾 聖心, 小橋 啓司, 吉村 高明, 西岡 健太郎
    日本学術振興会, 基盤研究(C), 北海道大学, 22K07631
  • 研究活動とライフイベントの両立のための補助人材支援
    2023年04月 - 2025年03月
    吉村 高明
    北海道大学ダイバーシティ・インクルージョン推進本部, 北海道大学, 研究代表者, その他
  • 医療AIを活用した前立腺癌に対する寡分割Adaptive陽子線治療技術開発　　　　　　　　　　　　　　　
    若手研究人材育成事業 若手研究人材・ネットワーク育成補助金（タレント補助金）
    2023年08月 - 2024年03月
    吉村 高明
    公益財団法人 北海道科学技術総合振興センター, 北海道大学, 研究代表者, 競争的資金
  • 超低投与線量PET検査を実現するDeep Learning技術の確立
    2023年度 研究助成〈奨励〉
    2023年04月 - 2024年03月
    吉村高明
    公益財団法人 秋山記念生命科学振興財団, 研究代表者, 競争的資金
  • 超解像深層学習を用いた低投与線量PET検査の実現に向けたシステム開発
    第9回北海道大学部局横断シンポジウム研究助成採択 銅賞
    2023年10月 - 2023年10月
    吉村高明, 杉森博行, 平田健司, 藤後廉
    北海道大学, 北海道大学, 研究代表者
  • 人工知能を用いた前立腺癌に対する非侵襲的診断支援技術の開発
    若手研究人材育成事業 若手研究人材・ネットワーク育成補助金（ノースタレント補助金）
    2022年08月 - 2023年03月
    吉村 高明
    公益財団法人 北海道科学技術総合振興センター, 北海道大学, 研究代表者
  • 人獣連携によりMR画像-CT画像変換を高精度化する技術の開発~前立腺癌に対するMR画像誘導即時適応尿道線量低減陽子線治療の実現に向けて~　　　　　　　　　　　　　　　
    第8回北海道大学部局横断シンポジウム研究助成採択 銅賞
    2022年10月 - 2022年10月
    Yoshimura T, Shinbo G, Matsuura T, Hashimoto T, Nishioka K, Mori T, Kanehira T, Sugimori H
    北海道大学, 北海道大学, 研究代表者
  • 非侵襲的に前立腺癌と正常組織を識別するMRI画像を用いた放射線治療計画技術の開発
    科学研究費助成事業 若手研究
    2018年04月01日 - 2022年03月31日
    吉村 高明
    前立腺癌に対する放射線治療では、正常組織に高線量が照射されることによる尿道狭窄などの有害事象が問題となる。有害事象のリスクを最小限にするために、癌と前立腺内の正常組織を明確に識別し、正常組織への高線量を避けた治療計画が求められている。これまで、治療計画時に尿道カテーテルを留置し、正常組織を明確に識別することで有害事象のリスクを最小限にした放射線治療を実現してきたが、尿道カテーテル留置は侵襲的であり、尿道カテーテルの有無による再現性の不確かさが課題であった。本研究では、3T-MRIによる高分解能撮像により、尿道カテーテルの留置に伴う侵襲が不要となると考えられる。
    本研究課題遂行にあたり、2018年度は、前立腺内の正常組織である尿道を正確に把握することがきるMRI撮像法を確立するために、北海道大学病院にて保有する3T-MRIを用いて撮像パラメータの検討を行った。治療計画に用いる治療計画CTおよびMRIの撮像プロトコルを策定し、自主臨床試験として申請し承認された。自主臨床試験の登録に時間を要したため、本年度の患者登録は行えず、次年度以降、健常ボランティアでの撮像プロトコルの確認を行った後、本研究の実施期間でおよそ100名の登録を予定している。
    また、本研究に関連する基礎研究成果として、動体追跡陽子線治療における治療計画データおよび装置ログデータを用いた解析を行うためのデータベースの構築を行った。構築したデータベースを用いて定量的に解析することにより、動体追跡陽子線治療プロセスや尿道カテーテルの有無による再現性の不確かさについて検討した。解析結果を論文にまとめ、投稿中である。また、成果の一部を第15回日本粒子線治療臨床研究会(2018.10.7, 大阪)および60th Annual meeting for American Society for Radiation Oncology (ASTRO)(2018.10.21-24, San Antonio)において発表した。
    日本学術振興会, 若手研究, 北海道大学, 研究代表者, 競争的資金, 18K15577
  • 人工知能を用いた前立腺がんに対する 動体追跡陽子線治療計画技術の開発　　　　　　　　　　　　　　　
    ノーステック財団理事長賞
    2022年03月 - 2022年03月
    吉村 高明
    公益財団法人 北海道科学技術総合振興センター, 北海道大学, 研究代表者
  • PET検査における超解像深層学習を用いた被ばく線量低減の試み
    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）
    2021年08月 - 2022年03月
    吉村高明
    公益財団法人 北海道科学技術総合振興センター, 研究代表者
  • 微小空間画像による極低侵襲・マーカーレス実時間画像誘導放射線治療技法の開発
    科学研究費助成事業 基盤研究(B)
    2018年04月01日 - 2021年03月31日
    清水 伸一, 宮本 直樹, 高尾 聖心, 梅垣 菊男, 橋本 孝之, 木下 留美子, 吉村 高明, 西岡 健太郎, 加藤 徳雄, 田口 大志, 松浦 妙子
    本研究は、陽子線治療ガントリー設置動体追跡装置の2軸X線透視装置を発展させ、現状より更に低侵襲で尚且つ腫瘍や体内臓器の空間的・時間的変動や呼吸性移動を考慮したがん治療が実現できる実時間画像誘導放射線治療システムを創造することを目的としている。動体追跡装置では2方向X線透視画像から特徴点の3次元位置座標をリアルタイムに計算し、様々な呼吸位相から治療計画に用いたのものと同じ呼吸位相を時間的に演算によって切り出しゲーティング治療を実現している。透視X線は治療放射線を照射する時間以外にも待機的に用いられているため本来不要な被曝が生じており、特徴点の抽出・認識にマーカを使用する必要があるため、観血的手技が必要などの患者負担が生じている。
    本年度の実績として、マーカを用いずにゲーティング治療を行う手法についての特許出願を行った(特願2019-056069, 2019)。この特許出願は本研究で想定している特徴点近傍に領域を絞って情報を得、判断を行う画像認識手法を用い実際に治療を行う際に必須の物となる。正常組織の線量負荷を低減することの臨床的意義を検証する研究を実施した。
    日本学術振興会, 基盤研究(B), 北海道大学, 18H02758
  • 人工知能を用いた前立腺癌に対する動体追跡陽子線治療計画技術の開発
    若手研究人材育成事業 若手研究人材・ネットワーク育成補助金（ノースタレント補助金）
    2020年08月 - 2021年03月
    吉村 高明
    公益財団法人 北海道科学技術総合振興センター, 研究代表者
  • 婦人科腫瘍に対する陽子線治療の予後予測をin-slico surrogate markerに用いた治療計画技術の開発
    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））
    2019年08月 - 2020年03月
    吉村高明
    公益財団法人 北海道科学技術総合振興センター, 研究代表者, 競争的資金
  • the 58th PTCOG Travel Fellowship Award　　　　　　　　　　　　　　　
    PTCOG Travel Fellowship Program
    2019年06月 - 2019年06月
    Yoshimrua T
    Particle Therapy Co-Operative Group, 北海道大学, 研究代表者
  • イン・シリコ・サロゲートエンドポイントによる術後陽子線治療の晩期有害事象の評価
    科学研究費助成事業 若手研究(B)
    2015年04月01日 - 2019年03月31日
    木下 留美子, 吉村 高明
    婦人科癌の術後全骨盤照射についてX線によるIMRTとspot scanning proton therapy(SSPT)
    による治療計画の比較・検討を行った。SSPTではIMRTと比較しターゲットに対する照射線量を損なうことなく骨髄の線量が低減可能であり、Grade3以上の血液毒性のNTCP値も有意に低減されることが示された。
    乳癌の術後照射については温存乳房に対する術後照射及び温存乳房及び領域リンパ節に対する術後照射を行った症例の線量体積評価を行った。温存乳房に対する照射では内胸リンパ節への照射は不十分であることが示された。
    日本学術振興会, 若手研究(B), 北海道大学, 15K19760

担当教育組織