Saved in:
Bibliographic Details
Main Authors: Matzkin, Franco, Larrazabal, Agostina, Milone, Diego H, Dolz, Jose, Ferrante, Enzo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.14497
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909651524648960
author Matzkin, Franco
Larrazabal, Agostina
Milone, Diego H
Dolz, Jose
Ferrante, Enzo
author_facet Matzkin, Franco
Larrazabal, Agostina
Milone, Diego H
Dolz, Jose
Ferrante, Enzo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14497
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Reliable WMH Segmentation under Domain Shift: An Application Study using Maximum Entropy Regularization to Improve Uncertainty Estimation
Matzkin, Franco
Larrazabal, Agostina
Milone, Diego H
Dolz, Jose
Ferrante, Enzo
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title Towards Reliable WMH Segmentation under Domain Shift: An Application Study using Maximum Entropy Regularization to Improve Uncertainty Estimation
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.14497