Deep Learning‐based Classification of Resting‐state fMRI Independent‐component Analysis

• Published in: Neuroinformatics (Totowa, N.J.) N.J.), 2021-10, Vol.19 (4), p.619-637
• Main Authors: Nozais, Victor, Boutinaud, Philippe, Verrecchia, Violaine, Gueye, Marie-Fateye, Hervé, Pierre-Yves, Tzourio, Christophe, Mazoyer, Bernard, Joliot, Marc
• Format: Article
• Language: English
• Subjects: Bioinformatics; Biomedical and Life Sciences; Biomedicine; Brain mapping; Classification; Computational Biology/Bioinformatics; Computer Appl. in Life Sciences; Cortex (parietal); Deep learning; Functional magnetic resonance imaging; Neural networks; Neurology; Neurosciences; Original Article; Substantia grisea
• ISSN: 1539-2791; 1559-0089
• DOI: 10.1007/s12021-021-09514-x

Functional connectivity analyses of fMRI data have shown that the activity of the brain at rest is spatially organized into resting-state networks (RSNs). RSNs appear as groups of anatomically distant but functionally tightly connected brain regions. Inter-RSN intrinsic connectivity analyses may provide an optimal spatial level of integration to analyze the variability of the functional connectome. Here we propose a deep learning approach to enable the automated classification of individual independent-component (IC) decompositions into a set of predefined RSNs. Two databases were used in this work, BIL&GIN and MRi-Share, with 427 and 1811 participants, respectively. We trained a multilayer perceptron (MLP) to classify each IC as one of 45 RSNs, using the IC classification of 282 participants in BIL&GIN for training and a 5-dimensional parameter grid search for hyperparameter optimization. It reached an accuracy of 92 %. Predictions for the remaining individuals in BIL&GIN were tested against the original classification and demonstrated good spatial overlap between the cortical RSNs. As a first application, we created an RSN atlas based on MRi-Share. This atlas defined a brain parcellation in 29 RSNs covering 96 % of the gray matter. Second, we proposed an individual-based analysis of the subdivision of the default-mode network into 4 networks. Minimal overlap between RSNs was found except in the angular gyrus and potentially in the precuneus . We thus provide the community with an individual IC classifier that can be used to analyze one dataset or to statistically compare different datasets for RSN spatial definitions.