Automatic Semantic Segmentation of the Lumbar Spine: Clinical Applicability in a Multi-parametric and Multi-centre Study on Magnetic Resonance Images

TL;DR

This study develops and evaluates convolutional neural network variants, based on U-Net, for automatic semantic segmentation of lumbar spine MRI images across multi-centre, multi-parametric datasets, demonstrating improved accuracy over standard models.

Contribution

Introduces novel U-Net based neural network variants with attention, deep supervision, and multilevel features for lumbar spine segmentation in diverse MRI data.

Findings

Proposed models outperform standard U-Net in segmentation accuracy.

Ensemble strategies further improve segmentation results.

Models demonstrate robustness across multi-centre, multi-parametric datasets.

Abstract

One of the major difficulties in medical image segmentation is the high variability of these images, which is caused by their origin (multi-centre), the acquisition protocols (multi-parametric), as well as the variability of human anatomy, the severity of the illness, the effect of age and gender, among others. The problem addressed in this work is the automatic semantic segmentation of lumbar spine Magnetic Resonance images using convolutional neural networks. The purpose is to assign a class label to each pixel of an image. Classes were defined by radiologists and correspond to different structural elements like vertebrae, intervertebral discs, nerves, blood vessels, and other tissues. The proposed network topologies are variants of the U-Net architecture. Several complementary blocks were used to define the variants: Three types of convolutional blocks, spatial attention models, deep supervision and multilevel feature extractor. This document describes the topologies and analyses the results of the neural network designs that obtained the most accurate segmentations. Several of the proposed designs outperform the standard U-Net used as baseline, especially when used in ensembles where the output of multiple neural networks is combined according to different strategies.