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

Abstract

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.

Mapping white matter structural covariance connectivity for single subject using wavelet transform with T1-weighted anatomical brain MRI

“…Several studies attempted to predict cognitive or behavior scores using machine learning and fMRI. The intelligence quotient (IQ), reading ability, sleep quality, inattention, impulsivity, and autistic symptoms could be predicted using machine learning ( Cui et al, 2018 ; Cai et al, 2020 ; Zhou et al, 2020 ; Hebling Vieira et al, 2021 ; Wang and Li, 2021 ). Specially, the brain-age predictive models exhibited relatively high performance ( Franke et al, 2012 ).…”

Accounting for temporal variability in functional magnetic resonance imaging improves prediction of intelligence

“…We note that while the proposed approach has some limited technical resemblance with the recent work by Hebling Vieira et al (2021), there are also fundamental differences. First, unlike their method, the proposed approach provides feature selection capabilities via an L 0 regularization on the input features, which is of paramount importance in neuroimaging studies and especially critical for our second goal of discovering shared and unique brain regions (pertaining to task and rest fMRI) that are related to intelligence.…”

“…First, unlike their method, the proposed approach provides feature selection capabilities via an regularization on the input features, which is of paramount importance in neuroimaging studies and especially critical for our second goal of discovering shared and unique brain regions (pertaining to task and rest fMRI) that are related to intelligence. Second, in addition to prediction based on region‐level time series data, we also extend our deep learning framework to predict intelligence using dynamic FC, which is not considered in Hebling Vieira et al (2021). Third, we investigate the capability of both resting state and task fMRI experiments to predict a slew of intelligence measures, which provides a richer analysis compared to the resting state fMRI‐based prediction presented in that article.…”

“…Third, we investigate the capability of both resting state and task fMRI experiments to predict a slew of intelligence measures, which provides a richer analysis compared to the resting state fMRI‐based prediction presented in that article. Fourth, our analysis is based on the ABCD cohort involving close to 7000 samples, which is considerably larger (by one order of magnitude) compared to the much smaller HCP cohort that was used for analysis in Hebling Vieira et al (2021). Such large sample sizes elicit more reproducible estimates and produce results with greater generalizability, which is consistent with recommendations in the literature (Marek et al, 2022).…”

Beyond functional connectivity: deep learning applied to resting-state fMRI time series in the prediction of 58 human traits in the HCP

“…Potential limitations of traditional methods, such as the need of engineering features relating brain and behavior, have motivated the use of deep neural networks to predict behavior from neuroimaging [7, 19, 20]. However, it has been demonstrated that newer deep-learning-based approaches using resting-state functional connectivity (RSFC) as input do not outperform classical KRR on the prediction of behavior and demographics [7].…”