Experimental Comparisons of Sparse Dictionary Learning and Independent Component Analysis for Brain Network Inference From fMRI Data

• Published in: IEEE transactions on biomedical engineering Vol. 66; no. 1; pp. 289 - 299
• Main Authors: Zhang, Wei, Lv, Jinglei, Li, Xiang, Zhu, Dajiang, Jiang, Xi, Zhang, Shu, Zhao, Yu, Guo, Lei, Ye, Jieping, Hu, Dewen, Liu, Tianming
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Brain; Brain - diagnostic imaging; Brain mapping; Brain Mapping - methods; Dictionaries; Empirical analysis; Functional magnetic resonance imaging; functional network; Humans; Independent component analysis; Machine learning; Magnetic Resonance Imaging - methods; Matrix decomposition; Networks; Principal Component Analysis; Resting state fMRI; sparse dictionary learning; Sparse matrices; Supervised Machine Learning; Task analysis
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2018.2831186

In this work, we conduct comprehensive comparisons between four variants of independent component analysis (ICA) methods and three variants of sparse dictionary learning (SDL) methods, both at the subject-level, by using synthesized fMRI data with ground-truth. Our results showed that ICA methods perform very well and slightly better than SDL methods when functional networks' spatial overlaps are minor, but ICA methods have difficulty in differentiating functional networks with moderate or significant spatial overlaps. In contrast, the SDL algorithms perform consistently well no matter how functional networks spatially overlap, and importantly, SDL methods are significantly better than ICA methods when spatial overlaps between networks are moderate or severe. This work offers empirical better understanding of ICA and SDL algorithms in inferring functional networks from fMRI data and provides new guidelines and caveats when constructing and interpreting functional networks in the era of fMRI-based connectomics.