# A Clinically Validated Foundation Model for Comprehensive Lung Pathology Interpretation

arXiv: https://arxiv.org/abs/2605.25878 · HTML: https://mlsanity.com/paper/2605.25878/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 145 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine](https://mlsanity.com/paper/2311.16452/) (2023)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [Lung and Colon Cancer Histopathological Image Dataset (LC25000)](https://mlsanity.com/paper/1912.12142/) (2019)
- [WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma](https://mlsanity.com/paper/2204.06455/) (2022)
- [PathBench: A comprehensive comparison benchmark for pathology foundation models towards precision oncology](https://mlsanity.com/paper/2505.20202/) (2025)
- [A Clinical-grade Universal Foundation Model for Intraoperative Pathology](https://mlsanity.com/paper/2510.04861/) (2025)
- [Computational Pathology in the Era of Emerging Foundation and Agentic AI -- International Expert Perspectives on Clinical Integration and Translational Readiness](https://mlsanity.com/paper/2603.05884/) (2026)
- [Genome-Anchored Foundation Model Embeddings Improve Molecular Prediction from Histology Images](https://mlsanity.com/paper/2506.19681/) (2025)

## Built on by (most cited first, 1 of 1)

- [Morphology signal in whole slide image foundation models can automatically triage slides](https://mlsanity.com/paper/2609.01987/) (2026)

## Abstract (arXiv)

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 1.000, 0.991, and 0.966. Beyond prospective validation, we conducted a crossover RCT with eight pathologists, in which AI assistance improved diagnostic accuracy across 5,264 case-reader pairs (91.7% w/ AI vs. 83.2% w/o AI). AI assistance also reduced median diagnostic time by 18.3%, increased diagnostic confidence by 9.0%, and improved inter-rater agreement from moderate (kappa = 0.55) to substantial (kappa = 0.76). Together, these evaluations support PulmoFoundation as a clinically validated decision-support system for lung pathology.