Disc-Centric Contrastive Learning for Lumbar Spine Severity Grading

TL;DR

This paper introduces a disc-centric contrastive learning approach for automated lumbar spinal stenosis severity grading from MRI, improving accuracy and reducing misclassification by focusing on meaningful disc features.

Contribution

It presents a novel combination of contrastive pretraining and disc-level fine-tuning with an auxiliary localization task for better severity assessment.

Findings

Achieved 78.1% balanced accuracy

Reduced severe-to-normal misclassification to 2.13%

Improved focus on relevant disc features

Abstract

This work examines a disc-centric approach for automated severity grading of lumbar spinal stenosis from sagittal T2-weighted MRI. The method combines contrastive pretraining with disc-level fine-tuning, using a single anatomically localized region of interest per intervertebral disc. Contrastive learning is employed to help the model focus on meaningful disc features and reduce sensitivity to irrelevant differences in image appearance. The framework includes an auxiliary regression task for disc localization and applies weighted focal loss to address class imbalance. Experiments demonstrate a 78.1% balanced accuracy and a reduced severe-to-normal misclassification rate of 2.13% compared with supervised training from scratch. Detecting discs with moderate severity can still be challenging, but focusing on disc-level features provides a practical way to assess the lumbar spinal stenosis.