Reconstructing lost BOLD signal in individual participants using deep machine learning

Yuxiang Yan, Louisa Dahmani, Jianxun Ren, Lunhao Shen, Xiaolong Peng, Ruiqi Wang, Changgeng He, Changqing Jiang, Chen Gong, Ye Tian, Jianguo Zhang, Yi Guo, Yuanxiang Lin, Shijun Li, Meiyun Wang (), Luming Li (), Bo Hong () and Hesheng Liu ()
Additional contact information
Yuxiang Yan: Massachusetts General Hospital, Harvard Medical School
Louisa Dahmani: Massachusetts General Hospital, Harvard Medical School
Jianxun Ren: Massachusetts General Hospital, Harvard Medical School
Lunhao Shen: Massachusetts General Hospital, Harvard Medical School
Xiaolong Peng: Massachusetts General Hospital, Harvard Medical School
Ruiqi Wang: Massachusetts General Hospital, Harvard Medical School
Changgeng He: Massachusetts General Hospital, Harvard Medical School
Changqing Jiang: Tsinghua University
Chen Gong: Tsinghua University
Ye Tian: Tsinghua University
Jianguo Zhang: Capital Medical University
Yi Guo: Peking Union Medical College Hospital
Yuanxiang Lin: First Affiliated Hospital of Fujian Medical University
Shijun Li: Massachusetts General Hospital, Harvard Medical School
Meiyun Wang: Zhengzhou University People Hospital & Henan Provincial People’s Hospital
Luming Li: Tsinghua University
Bo Hong: Tsinghua University
Hesheng Liu: Massachusetts General Hospital, Harvard Medical School

Nature Communications, 2020, vol. 11, issue 1, 1-13

Abstract: Abstract Signal loss in blood oxygen level-dependent (BOLD) functional neuroimaging is common and can lead to misinterpretation of findings. Here, we reconstructed compromised fMRI signal using deep machine learning. We trained a model to learn principles governing BOLD activity in one dataset and reconstruct artificially compromised regions in an independent dataset, frame by frame. Intriguingly, BOLD time series extracted from reconstructed frames are correlated with the original time series, even though the frames do not independently carry any temporal information. Moreover, reconstructed functional connectivity maps exhibit good correspondence with the original connectivity maps, indicating that the model recovers functional relationships among brain regions. We replicated this result in two healthy datasets and in patients whose scans suffered signal loss due to intracortical electrodes. Critically, the reconstructions capture individual-specific information. Deep machine learning thus presents a unique opportunity to reconstruct compromised BOLD signal while capturing features of an individual’s own functional brain organization.

Date: 2020
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-020-18823-9 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:11:y:2020:i:1:d:10.1038_s41467-020-18823-9

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-020-18823-9

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().