Reconstructing Temporal Dynamics of fMRI Time Series via Encoded Contextual Information

Wenjun Bai, Tomoki Tokuda, Okito Yamashita, Junichiro Yoshimoto

研究成果: Conference contribution

抄録

To uncover the rich temporal dynamics from the noisy fMRI time series, we propose a data-driven time series model: temporal reconstruction model, targets on reconstructing subsequences of fMRI time series via encoded contextual representations. This novel reconstruction model is further perfected by learning the commonality among multiple reconstructed temporal resolutions. Through an empirical validation on a synthetic noisy time series, we demonstrate the superior denoising capacity of our reconstruction model. Implementing this reconstruction model on a real fMRI dataset, it reveals the rich temporal dynamics of reconstructed fMRI time series are revealed, assisting the subsequent neuroscientific analysis on discovering more consistent subject-level temporal independent functional modes.

本文言語English
ホスト出版物のタイトルProceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020
編集者Taesung Park, Young-Rae Cho, Xiaohua Tony Hu, Illhoi Yoo, Hyun Goo Woo, Jianxin Wang, Julio Facelli, Seungyoon Nam, Mingon Kang
出版社Institute of Electrical and Electronics Engineers Inc.
ページ968-971
ページ数4
ISBN(電子版)9781728162157
DOI
出版ステータスPublished - 16-12-2020
外部発表はい
イベント2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020 - Virtual, Seoul, Korea, Republic of
継続期間: 16-12-202019-12-2020

出版物シリーズ

名前Proceedings - 2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020

Conference

Conference2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020
国/地域Korea, Republic of
CityVirtual, Seoul
Period16-12-2019-12-20

All Science Journal Classification (ASJC) codes

  • コンピュータ サイエンスの応用
  • 情報システムおよび情報管理
  • 医学(その他)
  • 健康情報学

フィンガープリント

「Reconstructing Temporal Dynamics of fMRI Time Series via Encoded Contextual Information」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル