A pathology foundation model for cancer diagnosis and prognosis prediction

• Published in: Nature (London) Vol. 634; no. 8035; pp. 970 - 978
• Main Authors: Wang, Xiyue, Zhao, Junhan, Marostica, Eliana, Yuan, Wei, Jin, Jietian, Zhang, Jiayu, Li, Ruijiang, Tang, Hongping, Wang, Kanran, Li, Yu, Wang, Fang, Peng, Yulong, Zhu, Junyou, Zhang, Jing, Jackson, Christopher R., Zhang, Jun, Dillon, Deborah, Lin, Nancy U., Sholl, Lynette, Denize, Thomas, Meredith, David, Ligon, Keith L., Signoretti, Sabina, Ogino, Shuji, Golden, Jeffrey A., Nasrallah, MacLean P., Han, Xiao, Yang, Sen, Yu, Kun-Hsing
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 24.10.2024; Nature Publishing Group
• Subjects: 59; 631/114/1305; 631/114/1564; 631/114/2397; 631/114/2413; 631/67; Architecture; Artificial intelligence; Biopsy; Cancer; Cervix; Colon; Computer vision; Datasets; Datasets as Topic; Deep learning; Deep Learning - standards; Digital imaging; Digitization; Endometrium; Female; Histocytochemistry; Histopathology; Humanities and Social Sciences; Humans; Identification; Image resolution; Machine learning; Male; Medical diagnosis; Medical imaging; Medical prognosis; multidisciplinary; Neoplasms - classification; Neoplasms - diagnosis; Neoplasms - pathology; Observational learning; Pathology; Pathology, Clinical - methods; Pathology, Clinical - standards; Pattern recognition; Pattern Recognition, Automated - methods; Pattern Recognition, Automated - standards; Prognosis; Prostate; Representations; Reproducibility of Results; Science; Science (multidisciplinary); Sensitivity and Specificity; Slide preparation; Supervised learning; Supervised Machine Learning - standards
• ISSN: 0028-0836; 1476-4687; 1476-4687
• DOI: 10.1038/s41586-024-07894-z

Histopathology image evaluation is indispensable for cancer diagnoses and subtype classification. Standard artificial intelligence methods for histopathology image analyses have focused on optimizing specialized models for each diagnostic task 1 , 2 . Although such methods have achieved some success, they often have limited generalizability to images generated by different digitization protocols or samples collected from different populations 3 . Here, to address this challenge, we devised the Clinical Histopathology Imaging Evaluation Foundation (CHIEF) model, a general-purpose weakly supervised machine learning framework to extract pathology imaging features for systematic cancer evaluation. CHIEF leverages two complementary pretraining methods to extract diverse pathology representations: unsupervised pretraining for tile-level feature identification and weakly supervised pretraining for whole-slide pattern recognition. We developed CHIEF using 60,530 whole-slide images spanning 19 anatomical sites. Through pretraining on 44 terabytes of high-resolution pathology imaging datasets, CHIEF extracted microscopic representations useful for cancer cell detection, tumour origin identification, molecular profile characterization and prognostic prediction. We successfully validated CHIEF using 19,491 whole-slide images from 32 independent slide sets collected from 24 hospitals and cohorts internationally. Overall, CHIEF outperformed the state-of-the-art deep learning methods by up to 36.1%, showing its ability to address domain shifts observed in samples from diverse populations and processed by different slide preparation methods. CHIEF provides a generalizable foundation for efficient digital pathology evaluation for patients with cancer. A study describes the development of a generalizable foundation machine learning framework to extract pathology imaging features for cancer diagnosis and prognosis prediction.