Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2605.08207 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918490778107904 |
|---|---|
| author | Xu, Yingxue Zhang, Zhengyu Zhang, Xiuming Xu, Mengwei Zhou, Fengtao Wang, Yihui Ma, Jiabo Xin, Yi Li, Danyi Lu, Chengyu Cen, Zhijian Tan, Ying Yao, Qingbing Wang, Qi Gao, Zizhao Zhang, Yong Chen, Jingjing Liu, Feifei Xu, Qian Dai, Yi Tan, Hongxuan Jin, Cheng Zhou, Huajun Guo, Zhengrui Liang, Ling Wang, Hongyi Chen, Yingcong Wang, Xi Li, Zhenhui Chan, Ronald Cheong Kin Mao, Ning Cai, Muyan Wang, Zhe Liang, Li Chen, Hao |
| author_facet | Xu, Yingxue Zhang, Zhengyu Zhang, Xiuming Xu, Mengwei Zhou, Fengtao Wang, Yihui Ma, Jiabo Xin, Yi Li, Danyi Lu, Chengyu Cen, Zhijian Tan, Ying Yao, Qingbing Wang, Qi Gao, Zizhao Zhang, Yong Chen, Jingjing Liu, Feifei Xu, Qian Dai, Yi Tan, Hongxuan Jin, Cheng Zhou, Huajun Guo, Zhengrui Liang, Ling Wang, Hongyi Chen, Yingcong Wang, Xi Li, Zhenhui Chan, Ronald Cheong Kin Mao, Ning Cai, Muyan Wang, Zhe Liang, Li Chen, Hao |
| contents | Pathology foundation models have shown strong retrospective performance, but whether such systems can support clinically relevant use remains unclear. This challenge is particularly important in breast cancer, where pathological assessment serves as the gold standard for diagnosis and guides treatment planning, surgical decision-making and risk stratification across pre-, intra- and post-operative stages. Here we present \textbf{BRAVE}, a breast-adaptive pathology foundation model developed and evaluated using a total resource of 101,638 breast whole-slide images from 32 sources across Asia, Europe and North America. We assessed BRAVE across 34 tasks in 82 cohorts spanning pre-operative biopsy, intra-operative frozen section and post-operative resection, using an evidence chain comprising retrospective benchmarking, clinically challenging scenarios, workflow-oriented clinical impact simulations, prospective observational validation with the thresholds locked in the retrospective cohorts and crossover pathologist-AI interaction studies. Across these settings, BRAVE supported practical roles in the clinical workflow, including safe exclusion of low-risk cases from routine review, AI-assisted second-review rescue of initially missed positives and prioritization of cases for further assessment. In prospective validation across three centres, BRAVE excluded 76.9% of negative biopsy cases (NPV 0.953) and 70.1% of negative frozen-section cases (NPV 0.973), and triaged 78.8% of post-operative subtyping cases as high-confidence clear-cut cases (NPV 1.000). In reader studies, AI assistance improved balanced accuracy from 88.5% to 95.1% (OR 3.14, P<0.001), with better efficiency, confidence and inter-rater agreement. BRAVE-derived scores also independently predicted disease-free survival (adjusted HR 4.79, P<0.001) and overall survival (adjusted HR 8.14, P<0.001). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08207 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Breast Vision Pathology Foundation Model for Real-world Clinical Utility Xu, Yingxue Zhang, Zhengyu Zhang, Xiuming Xu, Mengwei Zhou, Fengtao Wang, Yihui Ma, Jiabo Xin, Yi Li, Danyi Lu, Chengyu Cen, Zhijian Tan, Ying Yao, Qingbing Wang, Qi Gao, Zizhao Zhang, Yong Chen, Jingjing Liu, Feifei Xu, Qian Dai, Yi Tan, Hongxuan Jin, Cheng Zhou, Huajun Guo, Zhengrui Liang, Ling Wang, Hongyi Chen, Yingcong Wang, Xi Li, Zhenhui Chan, Ronald Cheong Kin Mao, Ning Cai, Muyan Wang, Zhe Liang, Li Chen, Hao Computer Vision and Pattern Recognition Pathology foundation models have shown strong retrospective performance, but whether such systems can support clinically relevant use remains unclear. This challenge is particularly important in breast cancer, where pathological assessment serves as the gold standard for diagnosis and guides treatment planning, surgical decision-making and risk stratification across pre-, intra- and post-operative stages. Here we present \textbf{BRAVE}, a breast-adaptive pathology foundation model developed and evaluated using a total resource of 101,638 breast whole-slide images from 32 sources across Asia, Europe and North America. We assessed BRAVE across 34 tasks in 82 cohorts spanning pre-operative biopsy, intra-operative frozen section and post-operative resection, using an evidence chain comprising retrospective benchmarking, clinically challenging scenarios, workflow-oriented clinical impact simulations, prospective observational validation with the thresholds locked in the retrospective cohorts and crossover pathologist-AI interaction studies. Across these settings, BRAVE supported practical roles in the clinical workflow, including safe exclusion of low-risk cases from routine review, AI-assisted second-review rescue of initially missed positives and prioritization of cases for further assessment. In prospective validation across three centres, BRAVE excluded 76.9% of negative biopsy cases (NPV 0.953) and 70.1% of negative frozen-section cases (NPV 0.973), and triaged 78.8% of post-operative subtyping cases as high-confidence clear-cut cases (NPV 1.000). In reader studies, AI assistance improved balanced accuracy from 88.5% to 95.1% (OR 3.14, P<0.001), with better efficiency, confidence and inter-rater agreement. BRAVE-derived scores also independently predicted disease-free survival (adjusted HR 4.79, P<0.001) and overall survival (adjusted HR 8.14, P<0.001). |
| title | A Breast Vision Pathology Foundation Model for Real-world Clinical Utility |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.08207 |