MARC

LEADER 00000nab a2200000uu 4500
001 3124143550
003 UK-CbPIL
022 |a 0028-0836 
022 |a 1476-4687 
024 7 |a 10.1038/s41586-024-07894-z  |2 doi 
035 |a 3124143550 
045 0 |b d20241024 
084 |a 28221  |2 nlm 
100 1 |a Wang, Xiyue  |u Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA 
245 1 |a A pathology foundation model for cancer diagnosis and prognosis prediction 
260 |b Nature Publishing Group  |c Oct 24, 2024 
513 |a Journal Article 
520 3 |a 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 task1,2. Although such methods have achieved some success, they often have limited generalizability to images generated by different digitization protocols or samples collected from different populations3. 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. 
653 |a Prostate 
653 |a Cancer 
653 |a Digital imaging 
653 |a Histopathology 
653 |a Artificial intelligence 
653 |a Deep learning 
653 |a Datasets 
653 |a Image resolution 
653 |a Observational learning 
653 |a Identification 
653 |a Pattern recognition 
653 |a Supervised learning 
653 |a Medical imaging 
653 |a Pathology 
653 |a Architecture 
653 |a Machine learning 
653 |a Representations 
653 |a Medical prognosis 
653 |a Computer vision 
653 |a Cervix 
653 |a Colon 
653 |a Biopsy 
653 |a Slide preparation 
653 |a Endometrium 
653 |a Digitization 
653 |a Medical diagnosis 
653 |a Social 
700 1 |a Zhao, Junhan  |u Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA 
700 1 |a Marostica, Eliana  |u Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA 
700 1 |a Yuan, Wei  |u College of Biomedical Engineering, Sichuan University, Chengdu, China 
700 1 |a Jin, Jietian  |u Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou, China 
700 1 |a Zhang, Jiayu 
700 1 |a Li, Ruijiang 
700 1 |a Tang, Hongping 
700 1 |a Wang, Kanran 
700 1 |a Li, Yu 
700 1 |a Wang, Fang 
700 1 |a Peng, Yulong 
700 1 |a Zhu, Junyou 
700 1 |a Zhang, Jing 
700 1 |a Jackson, Christopher R 
700 1 |a Zhang, Jun 
700 1 |a Dillon, Deborah 
700 1 |a Lin, Nancy U 
700 1 |a Sholl, Lynette 
700 1 |a Denize, Thomas 
700 1 |a Meredith, David 
700 1 |a Ligon, Keith L 
700 1 |a Signoretti, Sabina 
700 1 |a Ogino, Shuji 
700 1 |a Golden, Jeffrey A 
700 1 |a Nasrallah, MacLean P 
700 1 |a Han, Xiao 
700 1 |a Yang, Sen 
700 1 |a Yu, Kun-Hsing 
773 0 |t Nature  |g vol. 634, no. 8035 (Oct 24, 2024), p. 970 
786 0 |d ProQuest  |t Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3124143550/abstract/embedded/J7RWLIQ9I3C9JK51?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3124143550/fulltext/embedded/J7RWLIQ9I3C9JK51?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3124143550/fulltextPDF/embedded/J7RWLIQ9I3C9JK51?source=fedsrch