Predicting fluid intelligence in adolescence from structural MRI with deep learning methods

Abstract

BackgroundThe objective of this study was to investigate the potential of unsegmented structural T1w MR images of adolescent brain for predicting uncorrected/actual fluid intelligence scores without any predefined feature extraction. We also examined whether prediction of uncorrected scores is simply a harder problem from both biological and technical point of view, than prediction of residualised scores. MethodsABCD (Adolescent Brain Cognitive Development) study data was used from 7709 children aged 9–10, including T1-weighted MRIs and fluid intelligence scores, with data split into training (n = 3739), validation (n = 415) and test (n = 3555) subsets. We developed several deep learning convolutional neural network (CNN) models for both actual and residualised fluid intelligence score prediction from the MR images. State of the art, conventional or reverse 2D/3D CNN architectures were developed to perform the regression task and optimised based on Pearson's correlation coefficient, r. The models were then compared with published results on the same dataset. ResultsOur proposed model achieved prediction accuracies of r = 0.18 (p < 0.001) for the validation and r = 0.1 (p < 0.05) for the test, for actual IQ prediction. Our results showed that, although we achieved ~10 times higher correlation for the residualised score prediction than the correlations reported by previous CNN studies, using the same unsegmented MR images, it could not exceed the actual IQ prediction performance. This suggests that the image features associated with covariates aided up in the uncorrected score prediction rather than making the task harder. ConclusionOur deep learning CNN was able to establish a weak but stable correlation between structural brain features and raw fluid intelligence. To improve neuroimaging-based fluid intelligence prediction performance, future studies will be required to explore ensembled regression strategies with multiple machine learning algorithms on multimodal MRIs.