Be Indiscrete: The Benefits of Learning Continuous Spine Degeneration Severity Scores
For radiologists and clinicians assessing spinal degeneration on MRI, this provides a more nuanced continuous scoring approach that avoids hard decision boundaries of ordinal grading.
This work proposes modeling lumbar spine degeneration as a continuous severity ranking problem instead of multi-class classification, introducing SpineRankNet. The method learns scalar severity scores that enable fine-grained ordering of MRI scans and recover ordinal grades with comparable accuracy, while improving discrimination between distant classes.
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.