Back to Search
Start Over
A visual-language foundation model for computational pathology.
- Source :
-
Nature medicine [Nat Med] 2024 Mar; Vol. 30 (3), pp. 863-874. Date of Electronic Publication: 2024 Mar 19. - Publication Year :
- 2024
-
Abstract
- The accelerated adoption of digital pathology and advances in deep learning have enabled the development of robust models for various pathology tasks across a diverse array of diseases and patient cohorts. However, model training is often difficult due to label scarcity in the medical domain, and a model's usage is limited by the specific task and disease for which it is trained. Additionally, most models in histopathology leverage only image data, a stark contrast to how humans teach each other and reason about histopathologic entities. We introduce CONtrastive learning from Captions for Histopathology (CONCH), a visual-language foundation model developed using diverse sources of histopathology images, biomedical text and, notably, over 1.17 million image-caption pairs through task-agnostic pretraining. Evaluated on a suite of 14 diverse benchmarks, CONCH can be transferred to a wide range of downstream tasks involving histopathology images and/or text, achieving state-of-the-art performance on histology image classification, segmentation, captioning, and text-to-image and image-to-text retrieval. CONCH represents a substantial leap over concurrent visual-language pretrained systems for histopathology, with the potential to directly facilitate a wide array of machine learning-based workflows requiring minimal or no further supervised fine-tuning.<br /> (© 2024. The Author(s), under exclusive licence to Springer Nature America, Inc.)
- Subjects :
- Humans
Workflow
Language
Machine Learning
Subjects
Details
- Language :
- English
- ISSN :
- 1546-170X
- Volume :
- 30
- Issue :
- 3
- Database :
- MEDLINE
- Journal :
- Nature medicine
- Publication Type :
- Academic Journal
- Accession number :
- 38504017
- Full Text :
- https://doi.org/10.1038/s41591-024-02856-4