Rotation-equivariant deep learning improves brain age prediction

Researchers have developed a novel framework for predicting brain age using diffusion MRI data, which captures white matter fiber orientation distributions. This approach utilizes a rotation-equivariant Convolutional Neural Network (CNN) that processes spherical harmonic coefficients of the fiber orientation distributions, preserving their geometric properties. In a study of 692 participants, this method demonstrated superior performance compared to traditional diffusion tensor imaging (DTI) models and conventional CNNs, achieving a mean absolute error of 3.54 years and a Pearson's correlation of 0.958. The study also identified specific white matter tracts that are most sensitive to age prediction, offering anatomical interpretability. AI

IMPACT This research advances interpretable AI in medical imaging, potentially improving diagnostic accuracy for age-related neurological conditions.

RANK_REASON Academic paper detailing a new methodology for brain age prediction using deep learning on MRI data. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• CatalyzeX
• CNNs
• DagsHub
• Diffusion tensor imaging
• Gotit.pub
• Hugging Face
• Human Connectome Project Aging
• ScienceCast
• SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
• white matter fiber orientation distributions

• paper
• model release
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →