• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Self-supervised feature construction methods for multi-modal neuroimaging data

Research Project

Project/Area Number 21H03516
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 61040:Soft computing-related
Research InstitutionAdvanced Telecommunications Research Institute International

Principal Investigator

KAWANABE Motoaki  株式会社国際電気通信基礎技術研究所, 脳情報通信総合研究所, 研究室長 (30272389)

Co-Investigator(Kenkyū-buntansha) 宮西 大樹  株式会社国際電気通信基礎技術研究所, 脳情報通信総合研究所, 研究員 (10737521)
平山 淳一郎  国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 主任研究員 (80512269)
Project Period (FY) 2021-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥17,290,000 (Direct Cost: ¥13,300,000、Indirect Cost: ¥3,990,000)
Fiscal Year 2023: ¥5,460,000 (Direct Cost: ¥4,200,000、Indirect Cost: ¥1,260,000)
Fiscal Year 2022: ¥5,850,000 (Direct Cost: ¥4,500,000、Indirect Cost: ¥1,350,000)
Fiscal Year 2021: ¥5,980,000 (Direct Cost: ¥4,600,000、Indirect Cost: ¥1,380,000)
Keywords人間情報学 / マルチモーダル脳イメージング / 自己教師あり学習 / 転移学習 / 脳活動ダイナミクス
Outline of Research at the Start

うつ状態を予防するためには脳と心の不調の早期検出が重要であるが、教師ラベル付きの脳イメージングデータのサンプル数が限られているため、深層学習を用いた脳情報解読法が従来法と同等の性能に留まっている。本研究では、最先端の自然言語処理技術で活用されている自己教師あり学習アプローチを脳情報解読に導入し、深層学習を大幅に改良できる脳情報特徴量を構築するための新たなフレームワークを開発するとともに、結果が説明可能なニューロテクノロジーの確立を目指す。

Outline of Final Research Achievements

In order to address the issue that the statistical properties of neuroimaging data vary substantially between different subjects and sessions, we developed a transfer learning method for brain information inference named TSMNet which can calibrate these inter-domain differences. Then, in order to extract information representations shared by multimodal data acquired from EEG and fMRI, we developed a self-supervised representation learning method named DeepGeoCCA, by combining nonlinear filtering using deep learning with a geometric approach that matches the statistical properties of neuroimaging data. We applied to the classification problem of cognitive load on ATR's EEG-fMRI simultaneous recording data, and showed that it has high generalizability across different subjects by incorporating TSMNet into its EEG model.

Academic Significance and Societal Importance of the Research Achievements

本研究で開発されたDeepGeoCCAに基づくマルチモーダルデータの自己教師あり学習法は、ATRが実施中のプロジェクトで活用されており、メンタルヘルスや認知機能の維持・向上に資するブレイン・マシン・インタフェースの研究を通じて社会への貢献が期待される。また、脳イメージングデータのみならず、ScanQAのように、様々な状況が考えうる複雑な実環境データに対して、深層学習の性能向上などの波及効果が期待できる。

Report

(4 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Annual Research Report
  • 2021 Annual Research Report
  • Research Products

    (16 results)

All 2024 2023 2022 2021 Other

All Int'l Joint Research (3 results) Journal Article (5 results) (of which Int'l Joint Research: 2 results,  Peer Reviewed: 4 results,  Open Access: 5 results) Presentation (8 results) (of which Int'l Joint Research: 4 results,  Invited: 1 results)

  • [Int'l Joint Research] Nanyang Technological University(シンガポール)

    • Related Report
      2023 Annual Research Report
  • [Int'l Joint Research] University of Sydney(オーストラリア)

    • Related Report
      2023 Annual Research Report
  • [Int'l Joint Research] University of Oxford(英国)

    • Related Report
      2021 Annual Research Report
  • [Journal Article] Deep Geodesic Canonical Correlation Analysis for Covariance-Based Neuroimaging Data2024

    • Author(s)
      Ju, C., Kobler, R.J., Tang, L., Guan, C., Kawanabe, M.
    • Journal Title

      Proceedings of the Twelfth International Conference on Learning Representations (ICLR2024)

      Volume: -

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Cityrefer: geography-aware 3D visual grounding dataset on city-scale point cloud data2023

    • Author(s)
      Miyanishi, T., Kitamori, F., Kurita, S., Lee, J., Kawanabe, M., Inoue, N.
    • Journal Title

      Advances in Neural Information Processing Systems 36 (NeurIPS 2023)

      Volume: 36

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] ScanQA: 3D Question Answering for Spatial Scene Understanding2022

    • Author(s)
      Azuma Daichi、Miyanishi Taiki、Kurita Shuhei、Kawanabe Motoaki
    • Journal Title

      The 2022 Conference on Computer Vision and Pattern Recognition (CVPR2022)

      Volume: CVPR Pages: 19107-19117

    • DOI

      10.1109/cvpr52688.2022.01854

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEG2022

    • Author(s)
      Kobler, R., Hirayama, J., Zhao, Q., Kawanabe, M.
    • Journal Title

      Advances in Neural Information Processing Systems

      Volume: 35 Pages: 6219-6235

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Neural dSCA: demixing multimodal interaction among brain areas during naturalistic experiments2021

    • Author(s)
      Takagi, Y., Hunt, L.T., Ohata, R., Imamizu, H., Hirayama, J.
    • Journal Title

      arXiv

      Volume: 2106 Pages: 02948-02948

    • Related Report
      2021 Annual Research Report
    • Open Access / Int'l Joint Research
  • [Presentation] Deep Geodesic Canonical Correlation Analysis for Covariance-Based Neuroimaging Data2024

    • Author(s)
      Ju, C., Kobler, R.J., Tang, L., Guan, C., Kawanabe, M.
    • Organizer
      The Twelfth International Conference on Learning Representations (ICLR2024)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Learning latent representations from simultaneous EEG-fMRI2024

    • Author(s)
      Kobler, R., Kuroda, T., Ogawa, T., Ju, C., Kawanabe, M.
    • Organizer
      the OHBM 2024 Annual Meeting
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Cityrefer: geography-aware 3D visual grounding dataset on city-scale point cloud data2023

    • Author(s)
      Miyanishi, T., Kitamori, F., Kurita, S., Lee, J., Kawanabe, M., Inoue, N.
    • Organizer
      The Thirty-seventh Annual Conference on Neural Information Processing Systems (NeurIPS2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] TSMNet for BMI: inter-subject and session transfer and online, unsupervised adaptation2023

    • Author(s)
      Kobler, R., Hirayama, J., Zhao, Q., Kawanabe, M.
    • Organizer
      第10回日本BMI研究会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 異なるシーケンスにおける課題中のfMRIデータの比較2023

    • Author(s)
      堤 聖月, 黒田 敏数, 小川 剛史, 岸 朋彦, Kobler Reinmar, 川鍋 一晃
    • Organizer
      第10回日本BMI研究会
    • Related Report
      2023 Annual Research Report
  • [Presentation] 屋内環境の意味的理解に向けた3次元質問応答2022

    • Author(s)
      東 大地,宮西 大樹,栗田 修平,川鍋 一晃
    • Organizer
      第25回画像の認識・理解シンポジウム(MIRU2022)
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEG2022

    • Author(s)
      Kobler, R., Hirayama, J., Zhao, Q., Kawanabe, M.
    • Organizer
      Conference on Neural Information Processing Systems (NeurIPS2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] マルチストリーム3次元畳み込みネットワークによる外観・動作・音声情報を統合した映像質問応答2021

    • Author(s)
      宮西大樹, 川鍋一晃
    • Organizer
      人工知能学会全国大会 (第35回)
    • Related Report
      2021 Annual Research Report

URL: 

Published: 2021-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi