ABSTRACT Background Accurate assessment of the severity of central canal stenosis (CCS) on lumbar spine MRI is critical for clinical decision‐making. We evaluated deep learning models for automated CCS grading on sagittal T2‐weighted MRI, focusing on uncertainty quantification to improve clinical reliability. Methods Using a retrospective cohort from the LumbarDISC dataset (1974 patients), we compared multiple deep learning architectures for three‐level CCS classification (normal/mild, moderate, severe). To assess model confidence, Monte Carlo (MC) dropout and Test Time Augmentation (TTA) techniques were applied to quantify prediction uncertainty. Results The fine‐tuned Spine Grading Network (SGN) achieved a balanced accuracy of 79.4% and a macro F1 score of 68.8%, with per‐class accuracies of 71.3% for moderate and 78.5% for severe stenosis. MC dropout revealed an increase in uncertainty predominantly in moderate and severe cases, while TTA uncertainty was higher for mild stenosis. Conclusion DL‐based CCS grading demonstrates potential to assist radiologists by providing rapid, standardized evaluations. Incorporating uncertainty quantification offers a safeguard to flag ambiguous cases, thus supporting clinical trust and facilitating safer integration of AI tools into the interpretation of spine MRI.
Brenzikofer et al. (Mon,) studied this question.