LEXU: Learning from Expert Disagreement for Single-Pass Uncertainty Estimation in Medical Image Segmentation

Kudaibergen Abutalip, Numan Saeed, Fadillah Adamsyah Maani, Ikboljon Sobirov, Vincent Andrearczyk, Adrien Depeursinge, Mohammad Yaqub

Keywords: Uncertainty estimation · Medical image segmentation · Model calibration.

Abstract:

Deploying deep learning (DL) models in medical applications
relies on predictive performance and other critical factors, such as conveying
trustworthy predictive uncertainty. Uncertainty estimation (UE)
methods provide potential solutions for evaluating prediction reliability
and improving the model confidence calibration. This paper introduces
Learning from EXpert Disagreement for UE (LEXU) for medical image
segmentation, a method that leverages the variability in annotations
from multiple experts to guide model training. By focusing on regions of
disagreement among experts and incorporating multi-rater optimization
strategy, LEXU enhances the model’s awareness of challenging cases,
resulting in better calibration and predictive uncertainty. The method
shows a 55% improvement in correlation with expert disagreements at the
image level and a 23% improvement at the pixel level, along with competitive
segmentation performance compared to state-of-the-art techniques,
all while requiring only a single forward pass.

Submission Number: 11