Tractography from T1-Weighted MRI Using Segmentation-Guided and Patch-Based Diffusion Model

Motivation: Generating tractography from diffusion MRI (dMRI) is valuable for studying brain connectivity, but is limited by its accessibility. Many existing neuroimaging datasets only include T1-weighted MRI, motivating the need for a dMRI-free approach. Goal(s): This study aims to develop an efficient, accurate method to generate tractography directly from T1-weighted MRI, enabling broader applications in both clinical and research settings. Approach: We designed a segmentation-guided, patch-based framework that focuses on anatomically relevant regions, facilitating high-fidelity Tract Orientation Map (TOM) generation. Results: Our framework achieves structural accuracy comparable to dMRI-based methods, as demonstrated by quantitative and qualitative evaluations. Impact: This study introduces a novel approach for generating tractography directly from T1-weighted MRI rapidly and accurately. This can be a useful tool to facilitate large-scale brain connectivity studies without the resource constraints associated with dMRI.