Learning Anatomical Segmentations for Tractography from Diffusion MRI

TL;DR

This paper presents a fast deep learning method for segmenting 170 brain regions directly on diffusion MRI, enabling improved tractography without reliance on T1 images or extensive pre-processing.

Contribution

The authors introduce a novel diffusion-space segmentation approach that eliminates the need for T1 images and reduces pre-processing time, enhancing tractography workflows.

Findings

Achieved Dice scores between 0.70 and 0.87 across tissue types.

Demonstrated generalization across different gradient directions.

Reduced pre-processing time significantly in tractography pipelines.

Abstract

Deep learning approaches for diffusion MRI have so far focused primarily on voxel-based segmentation of lesions or white-matter fiber tracts. A drawback of representing tracts as volumetric labels, rather than sets of streamlines, is that it precludes point-wise analyses of microstructural or geometric features along a tract. Traditional tractography pipelines, which do allow such analyses, can benefit from detailed whole-brain segmentations to guide tract reconstruction. Here, we introduce fast, deep learning-based segmentation of 170 anatomical regions directly on diffusion-weighted MR images, removing the dependency of conventional segmentation methods on T 1-weighted images and slow pre-processing pipelines. Working natively in diffusion space avoids non-linear distortions and registration errors across modalities, as well as interpolation artifacts. We demonstrate consistent segmentation results between 0 .70 and 0 .87 Dice depending on the tissue type. We investigate various combinations of diffusion-derived inputs and show generalization across different numbers of gradient directions. Finally, integrating our approach to provide anatomical priors for tractography pipelines, such as TRACULA, removes hours of pre-processing time and permits processing even in the absence of high-quality T 1-weighted scans, without degrading the quality of the resulting tract estimates.