Can deep learning predict human intelligence from structural brain MRI?

Abstract

Can brain structure predict human intelligence? T1-weighted structural brain magnetic resonance images (sMRI) have been correlated with intelligence. Nevertheless, population-level association does not fully account for individual variability in intelligence. To address this, individual prediction studies emerge recently. However, they are mostly on predicting fluid intelligence (the ability to solve new problems). Studies are lacking to predict crystallized intelligence (the ability to accumulate knowledge) or general intelligence (fluid and crystallized intelligence combined). This study tests whether deep learning of sMRI can predict an individual verbal, comprehensive, and full-scale intelligence quotients (VIQ, PIQ, FSIQ), which reflect both fluid and crystallized intelligence. We performed a comprehensive set of 432 experiments, using different input images, six deep learning models, and two outcome settings, on 850 autistic and healthy subjects 6-64 years of age. Results show promise with statistical significance, and also open up questions inviting further future studies.

Enhancing Neurocognitive Outcome Prediction in Congenital Heart Disease Patients: The Role of Brain Age Biomarkers and Beyond

“…Full-scale IQ is typically used to assess human general intelligence, the fundamental ability that combines all subdomains of neurocognitive abilities 42, 43 . These subdomain abilities can be assessed via different neurocognitive tests, some of which are available with the PCGC dataset we used in this study (see Table 2).…”

A New Forgery Image Dataset and its Subjective Evaluation

“…High and low-resolution tampered images are available in 24-bit and 32-bit at their sources. So, sampling post-processing is applied to both image quality and fixed values (like 24-bit to 8-bit 1 and 32-bit to 8-bit) [32]. A carefully selected radius is taken into account for sharpening methods.…”