8 papers
Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge
Asbjørn Munk, Stefano Cerri, Vardan Nersesjan +81
Clinical deployment of automated brain MRI analysis faces a fundamental challenge: clinical data is heterogeneous and noisy, and high-quality labels are prohibitively costly to obt…
Explaining Uncertainty in Multiple Sclerosis Cortical Lesion Segmentation Beyond Prediction Errors
Nataliia Molchanova, Pedro M. Gordaliza, Alessandro Cagol +14
Trustworthy artificial intelligence (AI) is essential in healthcare, particularly for high-stakes tasks like medical image segmentation. Explainable AI and uncertainty quantificati…
From 100,000+ images to winning the first brain MRI foundation model challenges: Sharing lessons and models
Pedro M. Gordaliza, Jaume Banus, Benoît Gérin +4
Developing Foundation Models for medical image analysis is essential to overcome the unique challenges of radiological tasks. The first challenges of this kind for 3D brain MRI, SS…
Causal Attribution of Model Performance Gaps in Medical Imaging Under Distribution Shifts
Pedro M. Gordaliza, Nataliia Molchanova, Jaume Banus +2
Deep learning models for medical image segmentation suffer significant performance drops due to distribution shifts, but the causal mechanisms behind these drops remain poorly unde…
Accounting for Underspecification in Statistical Claims of Model Superiority
Thomas Sanchez, Pedro M. Gordaliza, Meritxell Bach Cuadra
Machine learning methods are increasingly applied in medical imaging, yet many reported improvements lack statistical robustness: recent works have highlighted that small but signi…
Benchmarking and Explaining Deep Learning Cortical Lesion MRI Segmentation in Multiple Sclerosis
Nataliia Molchanova, Alessandro Cagol, Mario Ocampo-Pineda +15
Cortical lesions (CLs) have emerged as valuable biomarkers in multiple sclerosis (MS), offering high diagnostic specificity and prognostic relevance. However, their routine clinica…