ProFound: A moderate-sized vision foundation model for multi-task prostate imaging
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911484005580800 |
|---|---|
| author | Wang, Yipei Xu, Yinsong Yi, Weixi Saeed, Shaheer Ullah Thorley, Natasha Ng, Alexander Zhou, Yukun Yan, Wen Barratt, Dean Punwani, Shonit Kasivisvanathan, Veeru Emberton, Mark Alexander, Daniel C. Hu, Yipeng |
| author_facet | Wang, Yipei Xu, Yinsong Yi, Weixi Saeed, Shaheer Ullah Thorley, Natasha Ng, Alexander Zhou, Yukun Yan, Wen Barratt, Dean Punwani, Shonit Kasivisvanathan, Veeru Emberton, Mark Alexander, Daniel C. Hu, Yipeng |
| contents | Many diagnostic and therapeutic clinical tasks for prostate cancer increasingly rely on multi-parametric MRI. Automating these tasks is challenging because they necessitate expert interpretations, which are difficult to scale to capitalise on modern deep learning. Although modern automated systems achieve expert-level performance in isolated tasks, their general clinical utility remains limited by the requirement of large task-specific labelled datasets. In this paper, we present ProFound, a domain-specialised vision foundation model for volumetric prostate mpMRI. ProFound is pre-trained using several variants of self-supervised approaches on a diverse, multi-institutional collection of 5,000 patients, with a total of over 22,000 unique 3D MRI volumes (over 1,800,000 2D image slices). We conducted a systematic evaluation of ProFound across a broad spectrum of $11$ downstream clinical tasks on over 3,000 independent patients, including prostate cancer detection, Gleason grading, lesion localisation, gland volume estimation, zonal and surrounding structure segmentation. Experimental results demonstrate that finetuned ProFound consistently outperforms or remains competitive with state-of-the-art specialised models and existing medical vision foundation models trained/finetuned on the same data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03961 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ProFound: A moderate-sized vision foundation model for multi-task prostate imaging Wang, Yipei Xu, Yinsong Yi, Weixi Saeed, Shaheer Ullah Thorley, Natasha Ng, Alexander Zhou, Yukun Yan, Wen Barratt, Dean Punwani, Shonit Kasivisvanathan, Veeru Emberton, Mark Alexander, Daniel C. Hu, Yipeng Computer Vision and Pattern Recognition Many diagnostic and therapeutic clinical tasks for prostate cancer increasingly rely on multi-parametric MRI. Automating these tasks is challenging because they necessitate expert interpretations, which are difficult to scale to capitalise on modern deep learning. Although modern automated systems achieve expert-level performance in isolated tasks, their general clinical utility remains limited by the requirement of large task-specific labelled datasets. In this paper, we present ProFound, a domain-specialised vision foundation model for volumetric prostate mpMRI. ProFound is pre-trained using several variants of self-supervised approaches on a diverse, multi-institutional collection of 5,000 patients, with a total of over 22,000 unique 3D MRI volumes (over 1,800,000 2D image slices). We conducted a systematic evaluation of ProFound across a broad spectrum of $11$ downstream clinical tasks on over 3,000 independent patients, including prostate cancer detection, Gleason grading, lesion localisation, gland volume estimation, zonal and surrounding structure segmentation. Experimental results demonstrate that finetuned ProFound consistently outperforms or remains competitive with state-of-the-art specialised models and existing medical vision foundation models trained/finetuned on the same data. |
| title | ProFound: A moderate-sized vision foundation model for multi-task prostate imaging |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.03961 |