Uncertainty Quantification of Central Canal Stenosis Deep Learning Classifier from Lumbar Sagittal T2-Weighted MRI
Brenzikofer, A.; Monzon, M.; Galbusera, F.; Manjaly, Z.-M.; Cina, A.; Jutzeler, C. R.
Show abstract
BackgroundAccurate 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. MethodsUsing a retrospective cohort from the LumbarDISC dataset (1,974 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. ResultsThe fine-tuned Spinal 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. ConclusionDL-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.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- AngioNet: A Convolutional Neural Network for Vessel Segmentation in X-ray Angiography 94%
- Toward Understanding COVID-19 Pneumonia: A Deep-learning-based Approach for Severity Analysis and Monitoring the Disease 94%
- Opportunistic Assessment of Ischemic Heart Disease Risk Using Abdominopelvic Computed Tomography and Medical Record Data: a Multimodal Explainable Artificial Intelligence Approach 93%
Similar papers in this journal
- Deep learning ensemble for abdominal aortic calcification scoring from lumbar spine X-ray and DXA images 95%
- Reconstructing microvascular network skeletons from 3D images: what is the ground truth? 92%
- Uncertainty in cardiovascular digital twins despite non-normal errors in 4D flow MRI: identifying reliable biomarkers such as ventricular relaxation rate 92%
Similar papers in this journal
- Designing a computer-assisted diagnosis system for cardiomegaly detection and radiology report generation 94%
- Uncovering the effects of model initialization on deep model generalization: A study with adult and pediatric chest X-ray images 93%
- Classification of Hyper-scale Multimodal Imaging Datasets 93%
Similar papers in this journal
- Pairwise learning of MRI scans using a convolutional Siamese network for prediction of knee pain 94%
- Evaluating Large Language Model-Generated Brain MRI Protocols: Performance of GPT4o, o3-mini, DeepSeek-R1 and Qwen2.5-72B 94%
- Assessing GPT-4 Multimodal Performance in Radiological Image Analysis 92%
Similar papers in this journal
- Enhancing Semantic Segmentation in Chest X-Ray Images through Image Preprocessing: ps-KDE for Pixel-wise Substitution by Kernel Density Estimation 95%
- pyKNEEr: An image analysis workflow for open and reproducible research on femoral knee cartilage 94%
- ai-corona : Radiologist-Assistant Deep Learning Framework for COVID-19 Diagnosis in Chest CT Scans 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.