Be Indiscrete: The Benefits of Learning Continuous Spine Degeneration Severity Scores
2026-07-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors looked at how to better assess the severity of spine degeneration seen in MRI scans, which is usually put into categories like mild or severe. Instead of treating these categories as separate groups, they proposed a method called SpineRankNet that gives a continuous score to show how bad the degeneration is. This scoring system helps to rank the severity more precisely and still matches traditional category-based results. Their approach also better distinguishes between very different stages of degeneration compared to usual classification methods.
lumbar spine degenerationMRIordinal gradingmulti-class classificationordinal regressionranking losscontinuous severity scoreGenodisc dataset
Authors
Maria Monzon, Andrew Zisserman, Robin Y. Park, Catherine R. Jutzeler, Amir Jamaludin
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.