4 papers
Multi-Rater Calibrated Segmentation Models
Meritxell Riera-MarÃn, Javier GarcÃa López, Júlia RodrÃguez-Comas +2
Objective: Accurate probability estimates are essential for the safe deployment of medical image segmentation models in clinical decision-making. However, modern deep segmentation…
Assessing Pancreatic Ductal Adenocarcinoma Vascular Invasion: the PDACVI Benchmark
M. Riera-MarÃn, O. K. Sikha, J. RodrÃguez-Comas +23
Surgical resection remains the only potentially curative treatment for pancreatic ductal adenocarcinoma (PDAC), and eligibility depends on accurate assessment of vascular invasion…
Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS) challenge results
Meritxell Riera-Marin, Sikha O K, Julia Rodriguez-Comas +29
Deep learning (DL) has become the dominant approach for medical image segmentation, yet ensuring the reliability and clinical applicability of these models requires addressing key…
Uncertainty-Aware Segmentation Quality Prediction via Deep Learning Bayesian Modeling: Comprehensive Evaluation and Interpretation on Skin Cancer and Liver Segmentation
Sikha O K, Meritxell Riera-MarÃn, Adrian Galdran +4
Image segmentation is a critical step in computational biomedical image analysis, typically evaluated using metrics like the Dice coefficient during training and validation. Howeve…