Interpretable Brain Age Prediction Using White Matter Fiber Orientation Distributions with Rotation-Equivariant Deep Learning
Authors: Chenyang Fan, Robert D. Sanders, Elie Matar, Yixuan Yuan, Xiang Li, Sharon L. Naismith, Fernando Calamante, Jinglei Lv
Organizations: School of Biomedical Engineering and Brain and Mind Centre at the University of Sydney, Sydney, NSW 2050 Australia · Brain and Mind Centre and Central Clinical School at the University of Sydney, Sydney, NSW, 2050 Australia · Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong SAR 999077, China · Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA · Brain and Mind Centre and School of Psychology at the University of Sydney, Sydney, NSW, 2050 Australia · School of Biomedical Engineering, Brain and Mind Centre, and Sydney Imaging, at the University of Sydney, Sydney, NSW 2050 Australia · Sydney Medical School at the University of Sydney, Sydney, NSW 2050 Australia · School of Computer, Data and Mathematical Sciences, Western Sydney University, Parramatta, NSW 2116 Australia
Diffusion MRI (dMRI) provides information about white matter microstructure that can support brain age prediction. However, many existing prediction models use diffusion tensor imaging (DTI) scalar metrics that omit orientation information. Deep learning is increasingly used for brain age prediction, but conventional CNNs do not explicitly respect the geometric structure of orientation-dependent features. We present an interpretable brain age prediction framework that combines white matter fiber orientation distributions (WM-FODs) with an SE(3) (Special Euclidean group in 3 dimensions) equivariant CNN. The network operates directly on spherical harmonic (SH) coefficients of the FOD, preserving their transformation properties under rotation. Evaluation in 692 participants aged 36-90 years from the Human Connectome Project Aging dataset showed that the combined framework outperformed the evaluated DTI-based models and conventional CNNs. Averaging predictions from five cross-validation models yielded a mean absolute error of 3.54 years and Pearson's correlation of 0.958. Our results indicated that the performance advantage depended on combining WM-FODs with equivariant processing. Prediction accuracy was highest at a maximum SH order of Lmax = 2 and declined at higher orders. Tract-level occlusion, where each segmented tract was masked in turn, revealed age-dependent patterns of model sensitivity, with importance peaks in frontal projection pathways at 36-44 years, the fornix at 45-54 years, the callosal isthmus at 55-64 years, the middle cerebellar peduncle at 65-74 years, and the callosal genu at 75-90 years. These findings support rotation-equivariant processing of WM-FODs for accurate brain age prediction with anatomically interpretable model sensitivity.
School of Biomedical Engineering, The University of Sydney, Sydney, 2050, Australia. · Brain and Mind Centre, The University of Sydney, Sydney, 2050, Australia. · School of Medical Science, The University of Sydney, Sydney, 2050, Australia. +5
Department of Biomedical Engineering, Columbia University, New York, NY 10027-7041, USA · Zuckerman Institute, Columbia University, New York, NY 10027-7041, USA · Taub Institute for Research on Alzheimer’s Disease and the Aging Brain, Vagelos College of Physicians and Surgeons, Columbia University, New York, NY, USA +5