Reconstructing lost BOLD signal in individual participants using deep machine learning.

Journal: Nature communications
PMID: 33028816

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.

Authors

  • Yuxiang Yan
    Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA, USA.
  • Louisa Dahmani
    Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA, USA.
  • Jianxun Ren
    Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA, USA.
  • Lunhao Shen
    Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA, USA.
  • Xiaolong Peng
    Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA, USA.
  • Ruiqi Wang
    Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA, USA.
  • Changgeng He
    Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA, USA.
  • Changqing Jiang
    National Engineering Laboratory for Neuromodulation, School of Aerospace Engineering, Tsinghua University, Beijing, China.
  • Chen Gong
    School of Journalism, Fudan University, Shanghai, China.
  • Ye Tian
    State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics and Center for Molecular Imaging and Translational Medicine, School of Public Health, Xiamen University, Xiamen, 361102, China.
  • Jianguo Zhang
    College of Automation, Harbin Engineering University, No. 145, Nantong street, Harbin, China.
  • Yi Guo
    Department of Respiratory and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China.
  • Yuanxiang Lin
    Department of Neurosurgery, National Regional Medical Center, Binhai Campus of the First Affiliated Hospital, Fujian Medical University, Fuzhou, Fujian, China.
  • Shijun Li
    Key Laboratory of Agricultural Animal Genetics, Breeding and Reproduction, Ministry of Education, Huazhong Agricultural University, Wuhan, Hubei Province, 430070 China. Electronic address: lishijun@mail.hzau.edu.cn.
  • Meiyun Wang
  • Luming Li
    National Engineering Laboratory for Neuromodulation, Tsinghua University, Beijing, China.
  • Bo Hong
    Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, 100084, China. hongbo@tsinghua.edu.cn.
  • Hesheng Liu
    Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA, USA. hesheng.liu@mgh.harvard.edu.

Keywords

External Resources

Popular Topics
Recent Journals