Learning Disentangled Stain and Structural Representations for Semi-Supervised Histopathology Segmentation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pham, Ha-Hieu, Vu, Nguyen Lan Vi, Nguyen, Thanh-Huy, Bagci, Ulas, Xu, Min, Le, Trung-Nghia, Pham, Huy-Hieu
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915422809358336
author Pham, Ha-Hieu
Vu, Nguyen Lan Vi
Nguyen, Thanh-Huy
Bagci, Ulas
Xu, Min
Le, Trung-Nghia
Pham, Huy-Hieu
author_facet Pham, Ha-Hieu
Vu, Nguyen Lan Vi
Nguyen, Thanh-Huy
Bagci, Ulas
Xu, Min
Le, Trung-Nghia
Pham, Huy-Hieu
contents Accurate gland segmentation in histopathology images is essential for cancer diagnosis and prognosis. However, significant variability in Hematoxylin and Eosin (H&E) staining and tissue morphology, combined with limited annotated data, poses major challenges for automated segmentation. To address this, we propose Color-Structure Dual-Student (CSDS), a novel semi-supervised segmentation framework designed to learn disentangled representations of stain appearance and tissue structure. CSDS comprises two specialized student networks: one trained on stain-augmented inputs to model chromatic variation, and the other on structure-augmented inputs to capture morphological cues. A shared teacher network, updated via Exponential Moving Average (EMA), supervises both students through pseudo-labels. To further improve label reliability, we introduce stain-aware and structure-aware uncertainty estimation modules that adaptively modulate the contribution of each student during training. Experiments on the GlaS and CRAG datasets show that CSDS achieves state-of-the-art performance in low-label settings, with Dice score improvements of up to 1.2% on GlaS and 0.7% on CRAG at 5% labeled data, and 0.7% and 1.4% at 10%. Our code and pre-trained models are available at https://github.com/hieuphamha19/CSDS.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03923
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Disentangled Stain and Structural Representations for Semi-Supervised Histopathology Segmentation
Pham, Ha-Hieu
Vu, Nguyen Lan Vi
Nguyen, Thanh-Huy
Bagci, Ulas
Xu, Min
Le, Trung-Nghia
Pham, Huy-Hieu
Computer Vision and Pattern Recognition
Artificial Intelligence
Accurate gland segmentation in histopathology images is essential for cancer diagnosis and prognosis. However, significant variability in Hematoxylin and Eosin (H&E) staining and tissue morphology, combined with limited annotated data, poses major challenges for automated segmentation. To address this, we propose Color-Structure Dual-Student (CSDS), a novel semi-supervised segmentation framework designed to learn disentangled representations of stain appearance and tissue structure. CSDS comprises two specialized student networks: one trained on stain-augmented inputs to model chromatic variation, and the other on structure-augmented inputs to capture morphological cues. A shared teacher network, updated via Exponential Moving Average (EMA), supervises both students through pseudo-labels. To further improve label reliability, we introduce stain-aware and structure-aware uncertainty estimation modules that adaptively modulate the contribution of each student during training. Experiments on the GlaS and CRAG datasets show that CSDS achieves state-of-the-art performance in low-label settings, with Dice score improvements of up to 1.2% on GlaS and 0.7% on CRAG at 5% labeled data, and 0.7% and 1.4% at 10%. Our code and pre-trained models are available at https://github.com/hieuphamha19/CSDS.
title Learning Disentangled Stain and Structural Representations for Semi-Supervised Histopathology Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.03923