Real-world deployment of a fine-tuned pathology foundation model for lung cancer biomarker detection
Journal article, 2025
Artificial intelligence models using digital histopathology slides stained with hematoxylin and eosin offer promising, tissue-preserving diagnostic tools for patients with cancer. Despite their advantages, their clinical utility in real-world settings remains unproven. Assessing EGFR mutations in lung adenocarcinoma demands rapid, accurate and cost-effective tests that preserve tissue for genomic sequencing. PCR-based assays provide rapid results but with reduced accuracy compared with next-generation sequencing and require additional tissue. Computational biomarkers leveraging modern foundation models can address these limitations. Here we assembled a large international clinical dataset of digital lung adenocarcinoma slides (N = 8,461) to develop a computational EGFR biomarker. Our model fine-tunes an open-source foundation model, improving task-specific performance with out-of-center generalization and clinical-grade accuracy on primary and metastatic specimens (mean area under the curve: internal 0.847, external 0.870). To evaluate real-world clinical translation, we conducted a prospective silent trial of the biomarker on primary samples, achieving an area under the curve of 0.890. The artificial-intelligence-assisted workflow reduced the number of rapid molecular tests needed by up to 43% while maintaining the current clinical standard performance. Our retrospective and prospective analyses demonstrate the real-world clinical utility of a computational pathology biomarker.
Author
Gabriele Campanella
Icahn School of Medicine at Mount Sinai
Neeraj Kumar
Memorial Sloan-Kettering Cancer Center
Swaraj Nanda
Memorial Sloan-Kettering Cancer Center
Siddharth Singi
Memorial Sloan-Kettering Cancer Center
Eugene Fluder
Icahn School of Medicine at Mount Sinai
Ricky Kwan
Icahn School of Medicine at Mount Sinai
Silke Muehlstedt
Icahn School of Medicine at Mount Sinai
Nicole Pfarr
Technical University of Munich
Peter J. Schüffler
Technical University of Munich
Ida Häggström
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering
University of Gothenburg
Noora Neittaanmäki
Sahlgrenska University Hospital
University of Gothenburg
Levent M. Akyürek
University of Gothenburg
Sahlgrenska University Hospital
Alina Basnet
State University of New York
Tamara Jamaspishvili
State University of New York
Michel R. Nasr
State University of New York
Matthew M. Croken
Icahn School of Medicine at Mount Sinai
Fred R. Hirsch
Icahn School of Medicine at Mount Sinai
Arielle Elkrief
Université de Montréal
Helena Yu
Weill Cornell Medical College
Memorial Sloan-Kettering Cancer Center
Orly Ardon
Memorial Sloan-Kettering Cancer Center
Gregory M. Goldgof
Memorial Sloan-Kettering Cancer Center
Meera Hameed
Memorial Sloan-Kettering Cancer Center
Jane Houldsworth
Icahn School of Medicine at Mount Sinai
Maria Arcila
Memorial Sloan-Kettering Cancer Center
Thomas J. Fuchs
Icahn School of Medicine at Mount Sinai
Chad Vanderbilt
Memorial Sloan-Kettering Cancer Center
Nature Medicine
1078-8956 (ISSN) 1546170x (eISSN)
Vol. 31 9 3002-3010Subject Categories (SSIF 2025)
Cancer and Oncology
DOI
10.1038/s41591-025-03780-x
PubMed
40634781