Conference Paper Published

Predicting Intelligence Profile and Brain Age with Single- and Dual-Channel Cnns: A Study Based on Human Connectome Projects

Fong, M. C. M., Liu, J. C. H., Ma, M. K. H., Ng, X. S. W., Hui, C. L. L., Waye, M. M. Y., Chien, W. T., & Wang, W. S. Y. (2025). Predicting Intelligence Profile and Brain Age with Single- and Dual-Channel Cnns: A Study Based on Human Connectome Projects. In Proceedings of 2025 IEEE 22nd International Symposium on Biomedical Imaging.

DOI: https://doi.org/10.1109/ISBI60581.2025.10981090

Abstract

Many studies formulated brain age biomarkers by applying deep-learning on 3D MR images to predict chronological age, considered a proxy of cognitive functions. Using over 1,700 T1- and T2-weighted images from the Human Connectome Projects (HCP-Young adult and HCP-Aging), we constructed 3D convolutional neural networks to directly predict two major sub-divisions of cognitive functions (fluid vs. crystallized). After competitive performance was obtained for brain age prediction (r = 0.968, MAE = 3.327), the more novel intelligence prediction problem was investigated orthogonally with three factors: MRI modality (T1 / T2 / both), prediction target (fluid / crystallized / both), and correction for the “regression to the mean” problem (uncorrected vs. Cole's method). Results showed good performance for both fluid (r = 0.628) and crystallized intelligence (r = 0.486). Our findings speak to the promise of the direct approach for predicting cognition and revealed certain advantages of predicting the two intelligences simultaneously over separately.

Keywords

convolutional neural network, brain age, intelligence, magnetic resonance imaging, Human Connectome Project