A pathology foundation model for cancer diagnosis and prognosis prediction
Furkejuvvon:
| Publikašuvnnas: | Nature vol. 634, no. 8035 (Oct 24, 2024), p. 970 |
|---|---|
| Váldodahkki: | |
| Eará dahkkit: | , , , , , , , , , , , , , , , , , , , , , , , , , , , |
| Almmustuhtton: |
Nature Publishing Group
|
| Fáttát: | |
| Liŋkkat: | Citation/Abstract Full Text Full Text - PDF |
| Fáddágilkorat: |
Eai fáddágilkorat, Lasit vuosttaš fáddágilkora!
|
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 |