Diffusion MRI
Diffusion MRI (dMRI) is a neuroimaging technique used to map the brain's microstructure and connectivity by measuring the diffusion of water molecules. Current research focuses on improving dMRI data quality through techniques like deep generative models (e.g., diffusion models, U-Nets) for tasks such as field-of-view extension, denoising, and super-resolution, often incorporating multi-modal data and physics-informed approaches. These advancements aim to enhance the accuracy and efficiency of dMRI-based analyses, including tractography, brain parcellation, and microstructure estimation, ultimately improving the diagnosis and treatment of neurological disorders and advancing our understanding of brain structure and function. The development of open-source datasets and standardized evaluation metrics is also a significant area of focus.
Papers
$E(3) \times SO(3)$-Equivariant Networks for Spherical Deconvolution in Diffusion MRI
Axel Elaldi, Guido Gerig, Neel Dey
Cancer-Net BCa-S: Breast Cancer Grade Prediction using Volumetric Deep Radiomic Features from Synthetic Correlated Diffusion Imaging
Chi-en Amy Tai, Hayden Gunraj, Alexander Wong
A Multi-Institutional Open-Source Benchmark Dataset for Breast Cancer Clinical Decision Support using Synthetic Correlated Diffusion Imaging Data
Chi-en Amy Tai, Hayden Gunraj, Alexander Wong