マルチシーケンス脳MRIを用いたMulti-scale 3D-Attention Branch Networksによるグリオーマ分子サブタイプ分類

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2023/05/01

タイトル(英語): Computerized Classification Method for Molecular Subtypes in Glioma with Multi-Scale 3D-Attention Branch Networks Analyzing Multi-Sequence Brain MRI Images

著者名: 田中　大貴（立命館大学大学院理工学研究科），檜作　彰良（立命館大学大学院理工学研究科），中山　良平（立命館大学大学院理工学研究科），楠田　佳緒（東京医療保健大学医療保健学部医療情報学科），正宗　賢（東京女子医科大学先端生命医科学研究所），村垣　善浩（東京女子医科大学先端生命医科学研究所）

著者名(英語): Daiki Tanaka (Graduate School of Science and Engineering, Ritsumeikan University), Akiyoshi Hizukuri (Graduate School of Science and Engineering, Ritsumeikan University), Ryohei Nakayama (Graduate School of Science and Engineering, Ritsumeikan University), Kaori Kusuda (Division of Healthcare Informatics, Tokyo Healthcare Universtiy), Ken Masamune (Faculty of Advanced Techno-Surgery, Institute of Advanced Biomedical Engineering and Science, Tokyo Women's Medical University), Yoshihiro Muragaki (Faculty of Advanced Techno-Surgery, Institute of Advanced Biomedical Engineering and Science, Tokyo Women's Medical University)

キーワード: 低悪性度グリオーマ，分子サブタイプ，脳MRI画像，アテンション機構　　low-grade glioma，molecular subtype，brain MRI image，attention mechanism

要約(英語): The purpose of this study was to develop a computerized classification method for molecular subtypes in low-grade gliomas (LGGs) with multi-scale 3D-at-tention branch networks analyzing multi-sequence brain MRI images. Our dataset consisted of brain T1-weighted and T2-weighted MRI im-ages for 217 patients (58 Astrocytoma IDH-mutant, 49 Astrocytoma IDH-wildtype, and 110 Oligodendroglioma). The proposed method was constructed from a feature extractor, an attention branch, and a perception branch. In the feature extractor, the feature maps were extracted from brain T1-weighted and T2-weighted MRI images, respectively. The attention branch focused on a tumor region and generated the attention maps normalized to 0.0 - 1.0. The feature maps were then multiplied by the attention maps to weight features on LGG in the feature maps. The molecular subtype in LGG was evaluated in the perception branch. The classification accuracy for the proposed method was 63.6%, showing an improvement when compared with the conven-tional method using only single sequence (T2-weighted) MRI images (59.9%).

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.143 No.5 （2023） 特集：医用・生体工学関連技術

本誌掲載ページ: 539-545 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/143/5/143_539/_article/-char/ja/