• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 課題ページに戻る

2023 年度 実施状況報告書

Integrated deep learning model for personalized transcranial magnetic stimulation

研究課題

研究課題/領域番号 22K12765
研究機関兵庫県立大学

研究代表者

Rashed Essam  兵庫県立大学, 情報科学研究科, 教授 (60837590)

研究分担者 平田 晃正  名古屋工業大学, 工学(系)研究科(研究院), 教授 (00335374)
ゴメスタメス ホセデビツト  千葉大学, フロンティア医工学センター, 准教授 (60772902)
研究期間 (年度) 2022-04-01 – 2025-03-31
キーワードDeep learning / brain stimulation / TMS / Segmentation
研究実績の概要

In this year, we have have conducted a comprehensive training process for the developed deep learning models. The training consider optimizing the process of TMS focalization of specific brain region (motor cortex) and how to estimate stimulation parameters in different scenarios. The SHARM dataset (https://arxiv.org/abs/2309.06677) developed last year is used in the training process with TMS data obtain from our research collaborators.
After the initial training, the model parameters are optimized using several validation studies to achieve superior network performance. We have evaluated different versions of the network architecture to validate potential variations such as adding attention layers and include BN/dropout layers. Now, we are in the phase of preparing publications.

現在までの達成度 (区分)
現在までの達成度 (区分)

1: 当初の計画以上に進展している

理由

The research is progress smoothly than planned. We initially plan to complete three work packages in the first year (development of the deep learning model, data collection, and TMS simulation). Which are all successfully completed. Furthermore, we have reported results through several presentations and invited talks. Work package 4 that include network training (scheduled for FY2023) was partially completed in FY2022. Moreover, we have completed Work Package 5 (validation and optimization) which was planned to be completed within the third year.

今後の研究の推進方策

The research plan for FY2024 include two work packages (Result reporting) and (deployment of open-source software). We have made some conference publications and already submitted one journal paper to international journal and currently under review. Further publications is expected based on results we already have in hands.
Additional experiment will be conducted for extension of the achieved results in terms of TMS focal point optimization. Also, we will prepare documentation for the open-source software to ease sharing with research community.

次年度使用額が生じた理由

Some amount of the budget was actually planned for equipment purchase but we have found that it can be shifted to next year to fit more with the project progress and activities.

  • 研究成果

    (5件)

すべて 2024 2023

すべて 雑誌論文 (1件) (うち国際共著 1件、 オープンアクセス 1件) 学会発表 (4件) (うち国際学会 2件、 招待講演 2件)

  • [雑誌論文] SHARM: Segmented Head Anatomical Reference Models2023

    • 著者名/発表者名
      Essam A. Rashed, Mohammad al-Shatouri, Ilkka Laakso, Akimasa Hirata
    • 雑誌名

      arXiv (preprint)

      巻: Corresponding Author ページ: 1-20

    • DOI

      10.48550/arXiv.2309.06677

    • オープンアクセス / 国際共著
  • [学会発表] Improvement of brain stimulation pipeline using machine learning2024

    • 著者名/発表者名
      E. A. Rashed and A. Hirata
    • 学会等名
      Neuromodec Webinar Series
    • 国際学会 / 招待講演
  • [学会発表] Electromagnetic brain stimulation: verification of deep learning technology2024

    • 著者名/発表者名
      Essam A. Rashed
    • 学会等名
      The 63nd Annual Conference of Japanese Society for Medical and Biological Engineering," Kagoshima, Japan 22-25 May 2024
  • [学会発表] Deep learning models for brain stimulation2023

    • 著者名/発表者名
      Essam A. Rashed
    • 学会等名
      Research Seminar at Australian Catholic University (ACU), Australia
    • 国際学会 / 招待講演
  • [学会発表] Deep learning-based segmented human head dataset2023

    • 著者名/発表者名
      Essam A. Rashed
    • 学会等名
      The 62nd Annual Conference of Japanese Society for Medical and Biological Engineering," Nagoya, Japan 18-20 May 2023

URL: 

公開日: 2024-12-25  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi