A Clinically Validated Foundation Model for Comprehensive Lung Pathology Interpretation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918521545424896 |
|---|---|
| author | Guo, Zhengrui Zhang, Zhengyu Ma, Jiabo Wang, Yihui Zhou, Fengtao Xu, Yingxue Liang, Ling Zhao, Chenglong Xie, Qi Li, Jinbang Guo, Shujing Han, Fangyi Cen, Zhijian Liu, Ziyi Jin, Cheng Hou, Junlin Chen, Zhixuan Cai, Yu Qu, Lijuan Chen, Shifu Liu, Yueping Wang, Zhe Zhang, Xiuming Cai, Muyan Liang, Li Chen, Hao |
| author_facet | Guo, Zhengrui Zhang, Zhengyu Ma, Jiabo Wang, Yihui Zhou, Fengtao Xu, Yingxue Liang, Ling Zhao, Chenglong Xie, Qi Li, Jinbang Guo, Shujing Han, Fangyi Cen, Zhijian Liu, Ziyi Jin, Cheng Hou, Junlin Chen, Zhixuan Cai, Yu Qu, Lijuan Chen, Shifu Liu, Yueping Wang, Zhe Zhang, Xiuming Cai, Muyan Liang, Li Chen, Hao |
| contents | Pathological assessment guides lung cancer diagnosis, treatment selection, and prognostic evaluation, yet current CPath approaches rely on task-specific models for isolated objectives. Although pan-cancer foundation models offer versatility, they lack subspecialty-level depth and have not been evaluated across clinical workflows or prospectively validated in real-world settings. We introduce PulmoFoundation, a multi-center, prospectively validated, randomized controlled trial (RCT)-evaluated foundation model for comprehensive lung pathology assessment across pre-operative, intra-operative, and post-operative care. Built upon Virchow2 via subspecialty-specific pretraining using ~40,000 diagnostic H&E-stained whole-slide images (WSIs), PulmoFoundation was systematically evaluated on ~26,000 WSIs across 32 clinically relevant tasks. In addition to accurately predicting molecular markers and patient survival, our model achieves clinical-grade performance in core diagnostic tasks across biopsy, frozen section, and surgical resection slides. In a registered prospective study of 1,357 patients across 11 diagnostic tasks, our model achieved an average AUC of 92.3%. Using pre-specified triage thresholds, PulmoFoundation could reduce additional second-review burden for 68.8% of biopsies and 83.0% of frozen sections, and defer 44.5% of IHC stain orders, with PPVs of 1.0, 0.991, and 0.966. Beyond prospective validation, we conducted a crossover RCT with eight pathologists, in which AI assistance improved diagnostic accuracy across 4,928 case-reader pairs (91.7% w/ AI vs. 83.8% w/o AI). AI assistance also reduced median diagnostic time by 19.6%, increased diagnostic confidence by 8.7%, and improved inter-rater agreement from moderate (kappa = 0.56) to substantial (kappa = 0.76). Together, these evaluations support PulmoFoundation as a clinically validated decision-support system for lung pathology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_25878 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Clinically Validated Foundation Model for Comprehensive Lung Pathology Interpretation Guo, Zhengrui Zhang, Zhengyu Ma, Jiabo Wang, Yihui Zhou, Fengtao Xu, Yingxue Liang, Ling Zhao, Chenglong Xie, Qi Li, Jinbang Guo, Shujing Han, Fangyi Cen, Zhijian Liu, Ziyi Jin, Cheng Hou, Junlin Chen, Zhixuan Cai, Yu Qu, Lijuan Chen, Shifu Liu, Yueping Wang, Zhe Zhang, Xiuming Cai, Muyan Liang, Li Chen, Hao Image and Video Processing Computer Vision and Pattern Recognition Pathological assessment guides lung cancer diagnosis, treatment selection, and prognostic evaluation, yet current CPath approaches rely on task-specific models for isolated objectives. Although pan-cancer foundation models offer versatility, they lack subspecialty-level depth and have not been evaluated across clinical workflows or prospectively validated in real-world settings. We introduce PulmoFoundation, a multi-center, prospectively validated, randomized controlled trial (RCT)-evaluated foundation model for comprehensive lung pathology assessment across pre-operative, intra-operative, and post-operative care. Built upon Virchow2 via subspecialty-specific pretraining using ~40,000 diagnostic H&E-stained whole-slide images (WSIs), PulmoFoundation was systematically evaluated on ~26,000 WSIs across 32 clinically relevant tasks. In addition to accurately predicting molecular markers and patient survival, our model achieves clinical-grade performance in core diagnostic tasks across biopsy, frozen section, and surgical resection slides. In a registered prospective study of 1,357 patients across 11 diagnostic tasks, our model achieved an average AUC of 92.3%. Using pre-specified triage thresholds, PulmoFoundation could reduce additional second-review burden for 68.8% of biopsies and 83.0% of frozen sections, and defer 44.5% of IHC stain orders, with PPVs of 1.0, 0.991, and 0.966. Beyond prospective validation, we conducted a crossover RCT with eight pathologists, in which AI assistance improved diagnostic accuracy across 4,928 case-reader pairs (91.7% w/ AI vs. 83.8% w/o AI). AI assistance also reduced median diagnostic time by 19.6%, increased diagnostic confidence by 8.7%, and improved inter-rater agreement from moderate (kappa = 0.56) to substantial (kappa = 0.76). Together, these evaluations support PulmoFoundation as a clinically validated decision-support system for lung pathology. |
| title | A Clinically Validated Foundation Model for Comprehensive Lung Pathology Interpretation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.25878 |