UniStain: A unified and organ-aware virtual H&E staining framework for label-free autofluorescence images
文献类型：期刊论文
| 作者 | Shi, Lulin2; Hou, Xingzhong3; Lai, James K. W.2; Wong, Ivy H. M.2; Huang, Bingxin2; Hui, Athena L. Y.2; Chan, Ronald C. K.1,4; Wong, Terence T. W.2 |
| 刊名 | ARTIFICIAL INTELLIGENCE IN MEDICINE
 |
| 出版日期 | 2026-03-01 |
| 卷号 | 173页码:10 |
| 关键词 | Deep learning Parameter-efficient fine-tuning Pre-trained diffusion model Virtual staining |
| ISSN号 | 0933-3657 |
| DOI | 10.1016/j.artmed.2025.103335 |
| 英文摘要 | 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. |
| 资助项目 | HKUST internal grant[R9421] |
| WOS研究方向 | Computer Science ; Engineering ; Medical Informatics |
| 语种 | 英语 |
| WOS记录号 | WOS:001658301000001 |
| 出版者 | ELSEVIER |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/42923]  |
| 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.Chinese Univ Hong Kong, Dept Anat & Cellular Pathol, Hong Kong, Peoples R China 2.Hong Kong Univ Sci & Technol, Dept Chem & Biol Engn, Hong Kong, Peoples R China 3.Chinese Acad Sci, State Key Lab Comp Architecture, Inst Comp Technol, Beijing, 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. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。