Reconstructing lost BOLD signal in individual participants using deep machine learning

• Published in: Nature communications Vol. 11; no. 1; p. 5046
• Main Authors: Yan, Yuxiang, Dahmani, Louisa, Ren, Jianxun, Shen, Lunhao, Peng, Xiaolong, Wang, Ruiqi, He, Changgeng, Jiang, Changqing, Gong, Chen, Tian, Ye, Zhang, Jianguo, Guo, Yi, Lin, Yuanxiang, Li, Shijun, Wang, Meiyun, Li, Luming, Hong, Bo, Liu, Hesheng
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 07.10.2020; Nature Portfolio
• Subjects: 59/36; 631/378/116; 631/378/3920; Adolescent; Adult; Brain Mapping - methods; Cerebral Cortex - blood supply; Cerebral Cortex - diagnostic imaging; Cerebral Cortex - physiology; Datasets as Topic; Deep Brain Stimulation; Deep Learning; Female; Healthy Volunteers; Humanities and Social Sciences; Humans; Image Processing, Computer-Assisted - methods; Magnetic Resonance Imaging - methods; Male; Models, Neurological; multidisciplinary; Oxygen - blood; Parkinson Disease - diagnosis; Parkinson Disease - physiopathology; Parkinson Disease - therapy; Science; Science (multidisciplinary); Young Adult
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-020-18823-9

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. Signal loss in blood oxygen level‐dependent (BOLD) fMRI can lead to misinterpretation of findings. The authors trained a deep learning model to reconstruct compromised BOLD signal in datasets from healthy participants and in patients whose scans suffered signal loss due to intracortical electrodes.