A deep learning based approach identifies regions more relevant than resting-state networks to the prediction of general intelligence from resting-state fMRI

Autor(es)

Vieira, Bruno Hebling ^{[1, 2]} ; Dubois, Julien ^{[3, 4]} ; Calhoun, Vince D. ^{[2, 5, 6]} ; Salmon, Carlos Ernesto Garrido ^[1]

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, InBrain Lab, Dept Fis, Ribeirao Preto - Brazil

^[2] Emory Univ, Triinst Ctr Translat Res Neuroimaging & Data Sci, Georgia State Univ, Georgia Inst Technol, Atlanta, GA 30322 - USA

^[3] CALTECH, Pasadena, CA 91125 - USA

^[4] Cedars Sinai Med Ctr, Los Angeles, CA 90048 - USA

^[5] Mind Res Network, Albuquerque, NM - USA

^[6] Georgia Inst Technol, Sch Elect & Comp Engn, Atlanta, GA 30332 - USA

• Tipo de documento: Artigo Científico
• Fonte: Human Brain Mapping; v. 42, n. 18 SEP 2021.
• Citações Web of Science: 0

Resumo

Prediction of cognitive ability latent factors such as general intelligence from neuroimaging has elucidated questions pertaining to their neural origins. However, predicting general intelligence from functional connectivity limit hypotheses to that specific domain, being agnostic to time-distributed features and dynamics. We used an ensemble of recurrent neural networks to circumvent this limitation, bypassing feature extraction, to predict general intelligence from resting-state functional magnetic resonance imaging regional signals of a large sample (n = 873) of Human Connectome Project adult subjects. Ablating common resting-state networks (RSNs) and measuring degradation in performance, we show that model reliance can be mostly explained by network size. Using our approach based on the temporal variance of saliencies, that is, gradients of outputs with regards to inputs, we identify a candidate set of networks that more reliably affect performance in the prediction of general intelligence than similarly sized RSNs. Our approach allows us to further test the effect of local alterations on data and the expected changes in derived metrics such as functional connectivity and instantaneous innovations. (AU)

• Processo FAPESP: 18/11881-1 - Predição de capacidades intelectuais por aprendizado de máquina a partir de neuroimagem por ressonância magnética
• Beneficiário: Bruno Hebling Vieira
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 17/02752-0 - Predição do desempenho em testes de inteligência a partir das conectividades estruturais e funcionais do cérebro humano
• Beneficiário: Carlos Ernesto Garrido Salmon
• Modalidade de apoio: Auxílio à Pesquisa - Regular