Spinal Cord Gray Matter-White Matter Segmentation on Magnetic Resonance AMIRA Images with MD-GRU

TL;DR

This paper introduces a new MRI segmentation pipeline for spinal cord gray and white matter using MD-GRU neural networks, achieving superior accuracy and reproducibility compared to previous methods, especially with AMIRA sequences.

Contribution

The study presents a novel segmentation pipeline utilizing MD-GRU with a generalized dice loss, improving accuracy and reproducibility in spinal cord MRI segmentation.

Findings

Superior segmentation results compared to recent challenges

High reproducibility in scan-rescan experiments

Enhanced performance with AMIRA sequence

Abstract

The small butterfly shaped structure of spinal cord (SC) gray matter (GM) is challenging to image and to delinate from its surrounding white matter (WM). Segmenting GM is up to a point a trade-off between accuracy and precision. We propose a new pipeline for GM-WM magnetic resonance (MR) image acquisition and segmentation. We report superior results as compared to the ones recently reported in the SC GM segmentation challenge and show even better results using the averaged magnetization inversion recovery acquisitions (AMIRA) sequence. Scan-rescan experiments with the AMIRA sequence show high reproducibility in terms of Dice coefficient, Hausdorff distance and relative standard deviation. We use a recurrent neural network (RNN) with multi-dimensional gated recurrent units (MD-GRU) to train segmentation models on the AMIRA dataset of 855 slices. We added a generalized dice loss to the cross entropy loss that MD-GRU uses and were able to improve the results.