News
人材検索について
ハイパフォーマンススポーツに係る研究者やサポートスタッフ等の人材情報の検索ができます。HPSCに現在勤務する職員（HPSCスタッフ）、HPSCの勤務経験者（HPSC OB/OG）、HPSCの各種事業における協力者（HPSC事業協力者）のカテゴリーに分けております。人材データベースへのご登録はHPSCからご依頼させて頂いた方のみとしております。
最終更新日：2025/07/07
髙橋 英幸
タカハシ ヒデユキ
(Hideyuki TAKAHASHI)
論文
- タイトル
- Semantic segmentation for individual thigh skeletal muscles of athletes on magnetic resonance images
- タイトル（英）
- Semantic segmentation for individual thigh skeletal muscles of athletes on magnetic resonance images
- 参照URL
- https://researchmap.jp/takahashi-hideyuki/published_papers/50455536
- 著者
- Kasahara, Jun,Ozaki, Hiroki,Matsubayashi, Takeo,Takahashi, Hideyuki,Nakayama, Ryohei
- 著者（英）
- Kasahara, Jun,Ozaki, Hiroki,Matsubayashi, Takeo,Takahashi, Hideyuki,Nakayama, Ryohei
- 担当区分
- 概要
- The skeletal muscles that athletes should train vary depending on their discipline and position. Therefore, individual skeletal muscle cross-sectional area assessment is important in the development of training strategies. To measure the cross-sectional area of skeletal muscle, manual segmentation of each muscle is performed using magnetic resonance (MR) imaging. This task is time-consuming and requires significant effort. Additionally, interobserver variability can sometimes be problematic. The purpose of this study was to develop an automated computerized method for semantic segmentation of individual thigh skeletal muscles from MR images of athletes. Our database consisted of 697 images from the thighs of 697 elite athletes. The images were randomly divided into a training dataset (70%), a validation dataset (10%), and a test dataset (20%). A label image was generated for each image by manually annotating 15 object classes: 12 different skeletal muscles, fat, bones, and vessels and nerves. Using the validation dataset, DeepLab v3+ was chosen from three different semantic segmentation models as a base model for segmenting individual thigh skeletal muscles. The feature extractor in DeepLab v3+ was also optimized to ResNet50. The mean Jaccard index and Dice index for the proposed method were 0.853 and 0.916, respectively, which were significantly higher than those from conventional DeepLab v3+ (Jaccard index: 0.810, p < .001; Dice index: 0.887, p < .001). The proposed method achieved a mean area error for 15 objective classes of 3.12%, useful in the assessment of skeletal muscle cross-sectional area from MR images.
- 概要（英）
- The skeletal muscles that athletes should train vary depending on their discipline and position. Therefore, individual skeletal muscle cross-sectional area assessment is important in the development of training strategies. To measure the cross-sectional area of skeletal muscle, manual segmentation of each muscle is performed using magnetic resonance (MR) imaging. This task is time-consuming and requires significant effort. Additionally, interobserver variability can sometimes be problematic. The purpose of this study was to develop an automated computerized method for semantic segmentation of individual thigh skeletal muscles from MR images of athletes. Our database consisted of 697 images from the thighs of 697 elite athletes. The images were randomly divided into a training dataset (70%), a validation dataset (10%), and a test dataset (20%). A label image was generated for each image by manually annotating 15 object classes: 12 different skeletal muscles, fat, bones, and vessels and nerves. Using the validation dataset, DeepLab v3+ was chosen from three different semantic segmentation models as a base model for segmenting individual thigh skeletal muscles. The feature extractor in DeepLab v3+ was also optimized to ResNet50. The mean Jaccard index and Dice index for the proposed method were 0.853 and 0.916, respectively, which were significantly higher than those from conventional DeepLab v3+ (Jaccard index: 0.810, p < .001; Dice index: 0.887, p < .001). The proposed method achieved a mean area error for 15 objective classes of 3.12%, useful in the assessment of skeletal muscle cross-sectional area from MR images.
- 出版者・発行元
- Springer
- 出版者・発行元（英）
- Springer
- 誌名
- Radiological Physics and Technology
- 誌名（英）
- Radiological Physics and Technology
- 巻
- 18
- 号
- 2
- 開始ページ
- 496
- 終了ページ
- 504
- 出版年月
- 2025年6月
- 査読の有無
- 査読有り
- 招待の有無
- 掲載種別
- 研究論文（学術雑誌）
- ISSN
- DOI URL
- https://doi.org/10.1007/s12194-025-00901-6
- 共同研究・競争的資金等の研究課題