3SGAN: Semi-Supervised and Multi-Task GAN for Stain Normalization and Nuclei Segmentation of Histopathological Images
Cancers · 28.02.2026 · 18 (5) · 791
DOI: 10.3390/cancers18050791 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cancers, online erschienen am 28.02.2026. Verfasst von Yifan Chen und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Biomedical Engineering, Fudan University, Shanghai 200438, China. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China MOST.
Abstract (Originalsprache)
Background/Objectives: Variations in staining styles—arising from differences in tissue preparation, scanners, and laboratory protocols—severely compromise the robustness of automated cell segmentation algorithms in digital pathology. Moreover, manual nucleus annotation is extremely labor-intensive, leading to a scarcity of large-scale, fully annotated datasets for supervised nucleus segmentation. This study proposes a novel framework that simultaneously mitigates staining variability and achieves high-accuracy nucleus segmentation using only minimal annotations.
Methods
We present 3SGAN, a multi-task dual-branch generative adversarial network (GAN) that jointly performs stain normalization and nucleus segmentation in a semi-supervised manner. The framework adopts a teacher–student paradigm: a lightweight teacher model (AttCycle) equipped with attention gates generates reliable pseudo-labels, while a high-capacity student model (TransCycle) leveraging a hybrid CNN–Transformer architecture further refines performance. 3SGAN was trained and evaluated on a large dataset of 1408 Whole-Slide Images (WSIs) from two medical institutions, encompassing 101 distinct staining styles, with nucleus-level annotations required for only 5% of the data.
Results
3SGAN significantly outperformed state-of-the-art methods, achieving superior segmentation accuracy with an F1-score of 0.8140, mean IoU of 0.8201, and AJI of 0.6915. Simultaneously, it demonstrated substantial improvements in stain normalization quality, yielding a low RMSE of 0.0908, high PSNR of 21.0615, and SSIM of 0.8556 on the internal test set. External validation on independent MoNuSeg and PanNuke datasets, as well as on previously untested tumor-rich non-ROI regions from our in-house WSIs, confirmed strong generalizability with excellent stain normalization and top-tier segmentation accuracy across diverse staining protocols, tissue types, and pathological patterns.
Conclusions
The proposed 3SGAN framework demonstrates that high-performance nucleus segmentation and stain normalization can be achieved with minimal annotation requirements, offering a practical and scalable solution for digital pathology applications across diverse clinical settings and staining protocols.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Biomedical Engineering, Fudan University, Shanghai 200438, China.
- Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai 200040, China.
- Department of Anatomical and Cellular Pathology, The Chinese University of Hong Kong, Prince of Wales Hospital, Hong Kong SAR, China.
ORCID-Profile: Kay Ka-Wai Li, Ho-Keung Ng, Guohui Zhou
Förderung
- National Key R&D Program of China MOST
Zitieren
APA
Chen, Y., Yang, Z., Wu, G., Tang, Q., Li, K. K., Ng, H. K., Shi, Z., Yu, J., & Zhou, G. (2026). 3SGAN: Semi-Supervised and Multi-Task GAN for Stain Normalization and Nuclei Segmentation of Histopathological Images. Cancers, 18(5), 791. https://doi.org/10.3390/cancers18050791
Vancouver
Chen Y, Yang Z, Wu G, Tang Q, Li KK, Ng HK, et al. 3SGAN: Semi-Supervised and Multi-Task GAN for Stain Normalization and Nuclei Segmentation of Histopathological Images. Cancers. 2026;18(5):791. doi:10.3390/cancers18050791
BibTeX
@article{Chen2026,
author = {Chen, Yifan and Yang, Zhiruo and Wu, Guoqing and Tang, Qisheng and Li, Kay Ka-Wai and Ng, Ho-Keung and Shi, Zhifeng and Yu, Jinhua and Zhou, Guohui},
title = {3SGAN: Semi-Supervised and Multi-Task GAN for Stain Normalization and Nuclei Segmentation of Histopathological Images},
journal = {Cancers},
year = {2026},
volume = {18},
number = {5},
pages = {791},
doi = {10.3390/cancers18050791}
}
EUVIMED