---
title: "Advancing Stain Transfer for Multi-Biomarkers: A Human Annotation-Free Method Based on Auxiliary Task Supervision"
authors:
  - "Siyuan Xu"
  - "Haofei Song"
  - "Yingjiao Deng"
  - "Jiansheng Wang"
  - "Yan Wang"
  - "Qingli Li"
doi: "10.24963/ijcai.2025/236"
url: "https://ijcai.org/proceedings/2025/236"
pdf: "https://ijcai.org/proceedings/2025/0236.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "2116-2124"
track: "Main Track"
keywords:
  - "Multidisciplinary Topics and Applications: MTA: Bioinformatics"
  - "Computer Vision: CV: Biomedical image analysis"
  - "Multidisciplinary Topics and Applications: MTA: Health and medicine"
---

# Advancing Stain Transfer for Multi-Biomarkers: A Human Annotation-Free Method Based on Auxiliary Task Supervision

Siyuan Xu, Haofei Song, Yingjiao Deng, Jiansheng Wang, Yan Wang, Qingli Li

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 2116-2124. DOI: [10.24963/ijcai.2025/236](https://doi.org/10.24963/ijcai.2025/236)

## Abstract

Histopathological examination primarily relies on hematoxylin and eosin (H&E) and immunohistochemical (IHC) staining. Though IHC provides more crucial molecular information for diagnosis, it is more costly than H&E staining. Stain transfer technology seeks to efficiently generate virtual IHC images from H&E images. While current deep learning-based methods have made progress, they still struggle to maintain pathological and structural consistency across biomarkers without pixel-level aligned reference. To address the problem, we propose an Auxiliary Task supervision-based Stain Transfer method for multi-biomarkers (ATST-Net), which pioneeringly employs human annotation-free masks as ground truth (GT). ATST-Net ensures pathological consistency, structural preservation and style transfer. It automatically annotates H&E masks in a cost-effective manner by utilizing consecutive IHC sections. Multiple auxiliary tasks provide diverse supervisory information on the location and intensity of biomarker expression, ensuring model accuracy and interpretability. We design a pretrained model-based generator to extract deep feature in H&E images, improving generalization performance. Extensive experiments demonstrate the effectiveness of ATST-Net's components. Compared to existing methods, ATST-Net achieves state-of-the-art (SOTA) accuracy on datasets with multiple biomarkers and intensity levels, while also reflecting high practical value. Code is available at https://github.com/SikangSHU/ATST-Net.