Segmentation Pre-Training for Efficient Spine Degeneration Grading
Self-supervised segmentation pre-training for label-efficient spine degeneration grading on MRI. MICCAI EMA Workshop 2026 (under review).
Beyond Fluency: A Clinical Benchmark and Anomaly-Enhanced Baseline for Spine MRI Report Generation
Clinical benchmark and anomaly-enhanced vision-language baseline for spine-MRI report generation. CVPR Workshops 2026 (CV4Clinic).
palau-b.
Be Indiscrete: The Benefits of Learning Continuous Spine Degeneration Severity Scores
SpineRankNet — learning continuous spine-degeneration severity scores by pairwise ranking, with Oxford VGG. MICCAI 2026.
Be Indiscrete: The Benefits of Learning Continuous Spine Degeneration Severity Scores
Lightning talk on learning continuous (rather than discrete) spine degeneration severity scores. SAIMI Symposium on AI in Medical Imaging, 2026.
Generative AI for spatial tumor growth on MRI: a proof-of-principle study in pediatric diffuse midline glioma
Guided denoising diffusion models to predict anatomical brain-tumor growth in pediatric diffuse midline glioma. BMC Medicine, 2026.
laslo-d.
Quantifying central canal stenosis prediction uncertainty in SpineNet with conformal prediction
Conformal prediction to calibrate and quantify the uncertainty of SpineNet central-canal-stenosis grading on lumbar MRI, giving statistically valid prediction sets. Scientific …
cina-a.
Uncertainty-Aware Lumbar Stenosis Classifier
Journal project building an uncertainty-aware deep learning classifier for central-canal stenosis grading from lumbar sagittal MRI. Combined Monte-Carlo dropout and test-time …
•
1 min read
Uncertainty Quantification of Central Canal Stenosis Deep Learning Classifier From Lumbar Sagittal T2-Weighted MRI
Monte-Carlo dropout and test-time augmentation to quantify uncertainty in a central-canal stenosis grading classifier. JOR Spine, 2026.
brenzikofer-a.
Lumbar Injection Satisfaction — Data-Driven Analysis
Data-driven study identifying which chronic low-back-pain patients benefit from lumbar steroid injections. Developed nested cross-validated ML models with SHAP interpretability on …
•
1 min read
Enhancing Low Back Pain Assessment with Diffusion Models for Lumbar Spine MRI Segmentation
Diffusion-based framework (SpineSegDiff) for semantic segmentation of lumbar spine MRI in low-back-pain patients, benchmarked on the SPIDER dataset. MIDL, PMLR v301, 2025.