Towards Reliable WMH Segmentation under Domain Shift: An Application Study using Maximum Entropy Regularization to Improve Uncertainty Estimation

TL;DR

This paper explores how maximum entropy regularization improves uncertainty estimation and model calibration for WMH segmentation across different MRI domains, aiding error detection without ground-truth labels.

Contribution

It introduces maximum-entropy regularization techniques to enhance uncertainty estimation and calibration in WMH segmentation models under domain shift conditions.

Findings

Entropy-based uncertainty can predict segmentation errors.

Maximum-entropy regularization improves model calibration.

Regularization strengthens correlation between uncertainty and performance.

Abstract

Accurate segmentation of white matter hyperintensities (WMH) is crucial for clinical decision-making, particularly in the context of multiple sclerosis. However, domain shifts, such as variations in MRI machine types or acquisition parameters, pose significant challenges to model calibration and uncertainty estimation. This study investigates the impact of domain shift on WMH segmentation by proposing maximum-entropy regularization techniques to enhance model calibration and uncertainty estimation, with the purpose of identifying errors post-deployment using predictive uncertainty as a proxy measure that does not require ground-truth labels. To do this, we conducted experiments using a U-Net architecture to evaluate these regularization schemes on two publicly available datasets, assessing performance with the Dice coefficient, expected calibration error, and entropy-based uncertainty estimates. Our results show that entropy-based uncertainty estimates can anticipate segmentation errors, and that maximum-entropy regularization further strengthens the correlation between uncertainty and segmentation performance while also improving model calibration under domain shift.