UniStain: A unified and organ-aware virtual H&E staining framework for label-free autofluorescence images

doi:10.1016/j.artmed.2025.103335

CSpace

	UniStain: A unified and organ-aware virtual H&E staining framework for label-free autofluorescence images
	Shi, Lulin 1; Hou, Xingzhong 2; Lai, James K. W.1; Wong, Ivy H. M.1; Huang, Bingxin 1; Hui, Athena L. Y.1; Chan, Ronald C. K.3,4; Wong, Terence T. W.1
	2026-03-01
发表期刊	ARTIFICIAL INTELLIGENCE IN MEDICINE
ISSN	0933-3657
卷号	173 页码:10
摘要	While hematoxylin and eosin (H&E) staining remains the gold standard for pathological diagnosis, its chemical-dependent workflow presents significant limitations, such as time-consuming protocols, hazardous reagent disposal and batch-to-batch variability in stain quality. We present UniStain, a breakthrough virtual staining framework that leverages label-free autofluorescence (AF) imaging and prompt-based deep learning to overcome these challenges. Unlike existing single-organ approaches that require multiple specialized models, our architecture enables versatile multi-tissue staining through a single model, significantly reducing computational overhead. The proposed crosspatch self-attention guidance (CPSG) mechanism addresses critical whole-slide image challenges by maintaining style consistency across adjacent patches and eliminating stitching artifacts. To support comprehensive evaluation, we curate and release the first multi-organ AF/H&E dataset with human tissue samples. Additionally, we introduce downstream clinical validation tasks including image retrieval and cancer subtyping analysis, thereby establishing a robust evaluation framework for virtual staining models. Quantitative assessments (image quality metrics, visual Turing tests) and downstream analyses demonstrate UniStain's superior performance compared to existing image translation methods, achieving state-of-the-art results while eliminating chemical staining requirements. The dataset and code of UniStain can be found at https://github.com/TABLAB-HKUST/UniStain.
关键词	Deep learning Parameter-efficient fine-tuning Pre-trained diffusion model Virtual staining
DOI	10.1016/j.artmed.2025.103335
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering ; Medical Informatics
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Biomedical ; Medical Informatics
WOS记录号	WOS:001658301000001
出版者	ELSEVIER
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42924
专题	中国科学院计算技术研究所
通讯作者	Wong, Terence T. W.
作者单位	1.Hong Kong Univ Sci & Technol, Dept Chem & Biol Engn, Hong Kong, Peoples R China 2.Chinese Acad Sci, State Key Lab Comp Architecture, Inst Comp Technol, Beijing, Peoples R China 3.Chinese Univ Hong Kong, Dept Anat & Cellular Pathol, Hong Kong, Peoples R China 4.Chinese Univ Hong Kong, Pathol Artificial Intelligence Dev & Assessment La, State Key Lab Translat Oncol, Hong Kong, Peoples R China
推荐引用方式 GB/T 7714	Shi, Lulin,Hou, Xingzhong,Lai, James K. W.,et al. UniStain: A unified and organ-aware virtual H&E staining framework for label-free autofluorescence images[J]. ARTIFICIAL INTELLIGENCE IN MEDICINE,2026,173:10.
APA	Shi, Lulin.,Hou, Xingzhong.,Lai, James K. W..,Wong, Ivy H. M..,Huang, Bingxin.,...&Wong, Terence T. W..(2026).UniStain: A unified and organ-aware virtual H&E staining framework for label-free autofluorescence images.ARTIFICIAL INTELLIGENCE IN MEDICINE,173,10.
MLA	Shi, Lulin,et al."UniStain: A unified and organ-aware virtual H&E staining framework for label-free autofluorescence images".ARTIFICIAL INTELLIGENCE IN MEDICINE 173(2026):10.