DSA-CycleGAN: A Domain Shift Aware CycleGAN for Robust Multi-Stain Glomeruli Segmentation

2026-04-20

AI Summary

This work addresses the degradation in segmentation model generalization caused by staining variations in digital pathology images, particularly the performance interference from noise introduced by CycleGAN during cross-stain training. To mitigate this issue, the authors propose a Domain Shift-Aware CycleGAN (DSA-CycleGAN) that explicitly models stain-induced domain shifts to suppress unnecessary artifacts in image translation while preserving cycle consistency. Requiring only single-stain annotations, the method achieves robust glomeruli segmentation across multiple stains and significantly outperforms existing approaches in both segmentation accuracy and stain translation quality, even for stain pairs with substantial biological discrepancies. The code is publicly available.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Security and Privacy: Data transparency and provenance

Abstract

A key challenge in segmentation in digital histopathology is inter- and intra-stain variations as it reduces model performance. Labelling each stain is expensive and time-consuming so methods using stain transfer via CycleGAN, have been developed for training multi-stain segmentation models using labels from a single stain. Nevertheless, CycleGAN tends to introduce noise during translation because of the one-to-many nature of some stain pairs, which conflicts with its cycle consistency loss. To address this, we propose the Domain Shift Aware CycleGAN, which reduces the presence of such noise. Furthermore, we evaluate several advances from the field of machine learning aimed at resolving similar problems and compare their effectiveness against DSA-CycleGAN in the context of multi-stain glomeruli segmentation. Experiments demonstrate that DSA-CycleGAN not only improves segmentation performance in glomeruli segmentation but also outperforms other methods in reducing noise. This is particularly evident when translating between biologically distinct stains. The code is publicly available at https://github.com/zeeshannisar/DSA-CycleGAN.

Problem

• domain shift
• stain variation
• glomeruli segmentation
• histopathology
• noise in translation

Innovation

• Domain Shift Awareness
• CycleGAN
• Stain Transfer
• Glomeruli Segmentation
• Noise Reduction