K-fold CV ensembles and deep ensembles produce distinct uncertainty behaviors, with deep ensembles improving calibration and failure detection while CV ensembles correlate more with inter-rater variability.
Explaining Uncertainty in Multiple Sclerosis Cortical Lesion Segmentation Beyond Prediction Errors
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Trustworthy artificial intelligence (AI) is essential in healthcare, particularly for high-stakes tasks like medical image segmentation. Explainable AI and uncertainty quantification significantly enhance AI reliability by addressing key attributes such as robustness, usability, and explainability. Despite extensive technical advances in uncertainty quantification for medical imaging, understanding the clinical informativeness and interpretability of uncertainty remains limited. This study presents an interpretability framework for analyzing lesion-scale predictive uncertainty in cortical lesion segmentation in multiple sclerosis using deep ensembles. The analysis shifts the focus from the uncertainty--error relationship towards clinically relevant medical and engineering factors. Our findings reveal that instance-wise uncertainty is strongly related to lesion size, shape, and cortical involvement. Expert rater feedback confirms that similar factors impede annotator confidence. Evaluations conducted on two datasets (206 patients, almost 2000 lesions) under both in-domain and distribution-shift conditions highlight the utility of the framework in different scenarios.
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Lost in the Folds: When Cross-Validation Is Not a Deep Ensemble for Uncertainty Estimation
K-fold CV ensembles and deep ensembles produce distinct uncertainty behaviors, with deep ensembles improving calibration and failure detection while CV ensembles correlate more with inter-rater variability.