Foundation Models in Medical Imaging: A Review and Outlook
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909910019604480 |
|---|---|
| author | van Veldhuizen, Vivien Botha, Vanessa Lu, Chunyao Cesur, Melis Erdal Lipman, Kevin Groot de Jong, Edwin D. Horlings, Hugo Sanchez, Clárisa I. Snoek, Cees G. M. Wessels, Lodewyk Mann, Ritse Marcus, Eric Teuwen, Jonas |
| author_facet | van Veldhuizen, Vivien Botha, Vanessa Lu, Chunyao Cesur, Melis Erdal Lipman, Kevin Groot de Jong, Edwin D. Horlings, Hugo Sanchez, Clárisa I. Snoek, Cees G. M. Wessels, Lodewyk Mann, Ritse Marcus, Eric Teuwen, Jonas |
| contents | Foundation models (FMs) are changing the way medical images are analyzed by learning from large collections of unlabeled data. Instead of relying on manually annotated examples, FMs are pre-trained to learn general-purpose visual features that can later be adapted to specific clinical tasks with little additional supervision. In this review, we examine how FMs are being developed and applied in pathology, radiology, and ophthalmology, drawing on evidence from over 150 studies. We explain the core components of FM pipelines, including model architectures, self-supervised learning methods, and strategies for downstream adaptation. We also review how FMs are being used in each imaging domain and compare design choices across applications. Finally, we discuss key challenges and open questions to guide future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_09095 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Foundation Models in Medical Imaging: A Review and Outlook van Veldhuizen, Vivien Botha, Vanessa Lu, Chunyao Cesur, Melis Erdal Lipman, Kevin Groot de Jong, Edwin D. Horlings, Hugo Sanchez, Clárisa I. Snoek, Cees G. M. Wessels, Lodewyk Mann, Ritse Marcus, Eric Teuwen, Jonas Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Foundation models (FMs) are changing the way medical images are analyzed by learning from large collections of unlabeled data. Instead of relying on manually annotated examples, FMs are pre-trained to learn general-purpose visual features that can later be adapted to specific clinical tasks with little additional supervision. In this review, we examine how FMs are being developed and applied in pathology, radiology, and ophthalmology, drawing on evidence from over 150 studies. We explain the core components of FM pipelines, including model architectures, self-supervised learning methods, and strategies for downstream adaptation. We also review how FMs are being used in each imaging domain and compare design choices across applications. Finally, we discuss key challenges and open questions to guide future research. |
| title | Foundation Models in Medical Imaging: A Review and Outlook |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.09095 |