Brain age predicted accurately from white matter fiber directions with new rotation-aware deep learning
Interpretable Brain Age Prediction Using White Matter Fiber Orientation Distributions with Rotation-Equivariant Deep Learning
Computer Vision and Pattern RecognitionMachine Learning
Summary
Estimating a person's brain age helps understand brain health and aging. The authors developed a new method that uses detailed information about how white matter fibers in the brain are oriented, processed by a special type of deep learning model that respects 3D rotations. This approach outperformed older models that ignored orientation or used simpler features. They also identified specific brain pathways important for predicting age at different time periods, making the results easier to interpret.
What this means in practice
- •For medical imaging teams: Improve brain age assessment from diffusion MRI data by employing rotation-equivariant models that use fiber orientation distributions for better accuracy and interpretability.
- •For clinical neuroscience groups: Identify age-related changes in specific white matter pathways by analyzing model sensitivity patterns, aiding targeted investigations of brain aging.
Authors
Chenyang Fan, Robert D. Sanders, Elie Matar, Yixuan Yuan, Xiang Li, Sharon L. Naismith, Fernando Calamante, Jinglei Lv
Abstract
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.