TwinTrack: Post-hoc Multi-Rater Calibration for Medical Image Segmentation
For medical image segmentation tasks with inherent inter-rater ambiguity, TwinTrack provides a simple post-hoc calibration method that yields interpretable probabilities reflecting expert disagreement.
TwinTrack calibrates ensemble segmentation probabilities to match the empirical mean human response (MHR), enabling direct interpretation as expected annotator agreement. It consistently improves calibration metrics over standard approaches on the MICCAI 2025 CURVAS-PDACVI benchmark.
Pancreatic ductal adenocarcinoma (PDAC) segmentation on contrast-enhanced CT is inherently ambiguous: inter-rater disagreement among experts reflects genuine uncertainty rather than annotation noise. Standard deep learning approaches assume a single ground truth, producing probabilistic outputs that can be poorly calibrated and difficult to interpret under such ambiguity. We present TwinTrack, a framework that addresses this gap through post-hoc calibration of ensemble segmentation probabilities to the empirical mean human response (MHR) -the fraction of expert annotators labeling a voxel as tumor. Calibrated probabilities are thus directly interpretable as the expected proportion of annotators assigning the tumor label, explicitly modeling inter-rater disagreement. The proposed post-hoc calibration procedure is simple and requires only a small multi-rater calibration set. It consistently improves calibration metrics over standard approaches when evaluated on the MICCAI 2025 CURVAS-PDACVI multi-rater benchmark.