Decoding Brain States From fMRI Signals by Using Unsupervised Domain Adaptation

• Published in: IEEE journal of biomedical and health informatics Vol. 24; no. 6; pp. 1677 - 1685
• Main Authors: Gao, Yufei, Zhang, Yameng, Cao, Zhiyuan, Guo, Xiaojuan, Zhang, Jiacai
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-06-2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Activity patterns; Adaptation; Adult; Annotations; Artificial neural networks; Brain; Brain - diagnostic imaging; Brain - physiology; Brain mapping; Cognitive ability; Connectome; cross-subject; Decoding; Deep learning; Domains; Electronic devices; Feature extraction; Functional magnetic resonance imaging; Humans; Image analysis; Image processing; Kernel; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Memory tasks; Mental task performance; Neural decoding; Neural networks; Neuroimaging; Performance degradation; Short term memory; Signal Processing, Computer-Assisted; Task analysis; Task Performance and Analysis; tfMRI; Three-dimensional displays; unsupervised domain adaptation; Unsupervised Machine Learning; Young Adult
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2019.2940695

With the development of deep learning in medical image analysis, decoding brain states from functional magnetic resonance imaging (fMRI) signals has made significant progress. Previous studies often utilized deep neural networks to automatically classify brain activity patterns related to diverse cognitive states. However, due to the individual differences between subjects and the variation in acquisition parameters across devices, the inconsistency in data distributions degrades the performance of cross-subject decoding. Besides, most current networks were trained in a supervised way, which is not suitable for the actual scenarios in which massive amounts of data are unlabeled. To address these problems, we proposed the deep cross-subject adaptation decoding (DCAD) framework to decipher the brain states. The proposed volume-based 3D feature extraction architecture can automatically learn the common spatiotemporal features of labeled source data to generate a distinct descriptor. Then, the distance between the source and target distributions is minimized via an unsupervised domain adaptation (UDA) method, which can help to accurately decode the cognitive states across subjects. The performance of the DCAD was evaluated on task-fMRI (tfMRI) dataset from the Human Connectome Project (HCP). Experimental results showed that the proposed method achieved the state-of-the-art decoding performance with mean 81.9% and 84.9% accuracies under two conditions (4 brain states and 9 brain states respectively) of working memory task. Our findings also demonstrated that UDA can mitigate the impact of the data distribution shift, thereby providing a superior choice for increasing the performance of cross-subject decoding without depending on annotations.