Be Indiscrete: The Benefits of Learning Continuous Spine Degeneration Severity Scores

2026-07-06

AI Summary

This work addresses the common practice of modeling lumbar degenerative disease on MRI as an ordinal classification task, which overlooks the inherently continuous nature of degeneration and the asymmetric costs of misclassification. To overcome these limitations, the authors propose SpineRankNet, a deep learning framework that formulates degeneration assessment as a continuous severity ranking problem, predicting a scalar severity score directly from lumbar MRI scans. By employing a ranking-based loss function, the method preserves accuracy in recovering the original discrete grades while significantly enhancing discriminative power between distant categories. Experiments on the Genodisc dataset demonstrate that the learned continuous scores not only faithfully reconstruct the established grading system but also outperform conventional multiclass and ordinal regression approaches in fine-grained ranking and cross-category discrimination tasks.

Abstract

Lumbar spine degeneration is a major contributor to chronic low back pain and is routinely assessed on MRI using ordinal grading systems, e.g. normal, mild, moderate, severe. Consequently, most approaches to train models to grade these MRIs formulate grading as a multi-class classification problem, treating ordinal grades as categorical, ignoring differences in misclassification severity, and imposing hard decision boundaries on a continuous disease process. This work explores modeling spinal degeneration as a continuous severity ranking problem. We introduce SpineRankNet, a framework that learns scalar severity scores from lumbar spinal MRI, and compare it against multi-class classification and ordinal regression. Using multiple degeneration measures from the Genodisc dataset, we show that a model trained using a ranking loss to produce a continuous score enables fine-grained ordering of MRI scans. Furthermore, the ordinal grading classes can be recovered from the score with comparable accuracy to those from a model trained directly for classification. The score learned by ranking even improves discrimination between more distant classes. Source code is available at https://github.com/spinetools/spineranknet.

Problem

• spine degeneration
• ordinal grading
• continuous severity
• MRI assessment
• classification limitations

Innovation

• continuous severity scoring
• ordinal regression
• ranking loss
• SpineRankNet
• lumbar spine degeneration