2D Multi-Class Model for Gray and White Matter Segmentation of the Cervical Spinal Cord at 7T

TL;DR

This paper introduces a new deep learning model for accurate gray and white matter segmentation of the cervical spinal cord in 7T MRI images, addressing challenges of existing methods and enhancing multi-center applicability.

Contribution

A novel multi-class deep learning model specifically designed for 7T MRI spinal cord segmentation, incorporating a specialized data augmentation strategy for robustness across centers.

Findings

Improved segmentation accuracy on 7T MRI data.

Enhanced robustness with the proposed data augmentation.

Potential for multi-center application of the model.

Abstract

The spinal cord (SC), which conveys information between the brain and the peripheral nervous system, plays a key role in various neurological disorders such as multiple sclerosis (MS) and amyotrophic lateral sclerosis (ALS), in which both gray matter (GM) and white matter (WM) may be impaired. While automated methods for WM/GM segmentation are now largely available, these techniques, developed for conventional systems (3T or lower) do not necessarily perform well on 7T MRI data, which feature finer details, contrasts, but also different artifacts or signal dropout. The primary goal of this study is thus to propose a new deep learning model that allows robust SC/GM multi-class segmentation based on ultra-high resolution 7T T2*-w MR images. The second objective is to highlight the relevance of implementing a specific data augmentation (DA) strategy, in particular to generate a generic model that could be used for multi-center studies at 7T.