Deep EM with Hierarchical Latent Label Modelling for Multi-Site Prostate Lesion Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Wen, Wang, Yipei, Huang, Shiqi, Thorley, Natasha, Emberton, Mark, Stavrinides, Vasilis, Hu, Yipeng, Barratt, Dean
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912967197458432
author Yan, Wen
Wang, Yipei
Huang, Shiqi
Thorley, Natasha
Emberton, Mark
Stavrinides, Vasilis
Hu, Yipeng
Barratt, Dean
author_facet Yan, Wen
Wang, Yipei
Huang, Shiqi
Thorley, Natasha
Emberton, Mark
Stavrinides, Vasilis
Hu, Yipeng
Barratt, Dean
contents Label variability is a major challenge for prostate lesion segmentation. In multi-site datasets, annotations often reflect centre-specific contouring protocols, causing segmentation networks to overfit to local styles and generalise poorly to unseen sites in inference. We treat each observed annotation as a noisy observation of an underlying latent 'clean' lesion mask, and propose a hierarchical expectation-maximisation (HierEM) framework that alternates between: (1) inferring a voxel-wise posterior distribution over the latent mask, and (2) training a CNN using this posterior as a soft target and estimate site-specific sensitivity and specificity under a hierarchical prior. This hierarchical prior decomposes label-quality into a global mean with site- and case-level deviations, reducing site-specific bias by penalising the likelihood term contributed only by site deviations. Experiments on three cohorts demonstrate that the proposed hierarchical EM framework enhances cross-site generalisation compared to state-of-the-art methods. For pooled-dataset evaluation, the per-site mean DSC ranges from 29.50% to 39.69%; for leave-one-site-out generalisation, it ranges from 27.91% to 32.67%, yielding statistically significant improvements over comparison methods (p<0.039). The method also produces interpretable per-site latent label-quality estimates (sensitivity alpha ranges from 31.5% to 47.3% at specificity beta approximates 0.99), supporting post-hoc analyses of cross-site annotation variability. These results indicate that explicitly modelling site-dependent annotation can improve cross-site generalisation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14418
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Deep EM with Hierarchical Latent Label Modelling for Multi-Site Prostate Lesion Segmentation
Yan, Wen
Wang, Yipei
Huang, Shiqi
Thorley, Natasha
Emberton, Mark
Stavrinides, Vasilis
Hu, Yipeng
Barratt, Dean
Computer Vision and Pattern Recognition
Artificial Intelligence
I.2.0
Label variability is a major challenge for prostate lesion segmentation. In multi-site datasets, annotations often reflect centre-specific contouring protocols, causing segmentation networks to overfit to local styles and generalise poorly to unseen sites in inference. We treat each observed annotation as a noisy observation of an underlying latent 'clean' lesion mask, and propose a hierarchical expectation-maximisation (HierEM) framework that alternates between: (1) inferring a voxel-wise posterior distribution over the latent mask, and (2) training a CNN using this posterior as a soft target and estimate site-specific sensitivity and specificity under a hierarchical prior. This hierarchical prior decomposes label-quality into a global mean with site- and case-level deviations, reducing site-specific bias by penalising the likelihood term contributed only by site deviations. Experiments on three cohorts demonstrate that the proposed hierarchical EM framework enhances cross-site generalisation compared to state-of-the-art methods. For pooled-dataset evaluation, the per-site mean DSC ranges from 29.50% to 39.69%; for leave-one-site-out generalisation, it ranges from 27.91% to 32.67%, yielding statistically significant improvements over comparison methods (p<0.039). The method also produces interpretable per-site latent label-quality estimates (sensitivity alpha ranges from 31.5% to 47.3% at specificity beta approximates 0.99), supporting post-hoc analyses of cross-site annotation variability. These results indicate that explicitly modelling site-dependent annotation can improve cross-site generalisation.
title Deep EM with Hierarchical Latent Label Modelling for Multi-Site Prostate Lesion Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
I.2.0
url https://arxiv.org/abs/2603.14418