Generalist medical foundation model improves prostate cancer segmentation from multimodal MRI images

Abstract Prostate cancer (PCa) is one of the most common types of cancer, seriously affecting adult male health. Accurate and automated PCa segmentation is essential for radiologists to confirm the location of cancer, evaluate its severity, and design appropriate treatments. This paper presents PCaS...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuhan Zhang, Xiao Ma, Mingchao Li, Kun Huang, Jie Zhu, Miao Wang, Xi Wang, Menglin Wu, Pheng-Ann Heng
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01756-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850207179679727616
author Yuhan Zhang
Xiao Ma
Mingchao Li
Kun Huang
Jie Zhu
Miao Wang
Xi Wang
Menglin Wu
Pheng-Ann Heng
author_facet Yuhan Zhang
Xiao Ma
Mingchao Li
Kun Huang
Jie Zhu
Miao Wang
Xi Wang
Menglin Wu
Pheng-Ann Heng
author_sort Yuhan Zhang
collection DOAJ
description Abstract Prostate cancer (PCa) is one of the most common types of cancer, seriously affecting adult male health. Accurate and automated PCa segmentation is essential for radiologists to confirm the location of cancer, evaluate its severity, and design appropriate treatments. This paper presents PCaSAM, a fully automated PCa segmentation model that allows us to input multi-modal MRI images into the foundation model to improve performance significantly. We collected multi-center datasets to conduct a comprehensive evaluation. The results showed that PCaSAM outperforms the generalist medical foundation model and the other representative segmentation models, with the average DSC of 0.721 and 0.706 in the internal and external datasets, respectively. Furthermore, with the assistance of segmentation, the PI-RADS scoring of PCa lesions was improved significantly, leading to a substantial increase in average AUC by 8.3–8.9% on two external datasets. Besides, PCaSAM achieved superior efficiency, making it highly suitable for real-world deployment scenarios.
format Article
id doaj-art-e2983803337e4ba5b49e915fa8fb2e4c
institution OA Journals
issn 2398-6352
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-e2983803337e4ba5b49e915fa8fb2e4c2025-08-20T02:10:35ZengNature Portfolionpj Digital Medicine2398-63522025-06-018111110.1038/s41746-025-01756-2Generalist medical foundation model improves prostate cancer segmentation from multimodal MRI imagesYuhan Zhang0Xiao Ma1Mingchao Li2Kun Huang3Jie Zhu4Miao Wang5Xi Wang6Menglin Wu7Pheng-Ann Heng8School of Biomedical Engineering, Shenzhen UniversityDepartment of Computer Science and Engineering, Nanjing University of Science and TechnologyAcademy of Arts and Design, Tsinghua UniversityDepartment of Computer Science and Engineering, Nanjing University of Science and TechnologySenior Department of Urology, The Third Medical Center of Chinese PLA General HospitalDepartment of Urology, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical SciencesDepartment of Computer Science and Engineering, The Chinese University of Hong KongCarbon Medical Device Ltd.Department of Computer Science and Engineering, The Chinese University of Hong KongAbstract Prostate cancer (PCa) is one of the most common types of cancer, seriously affecting adult male health. Accurate and automated PCa segmentation is essential for radiologists to confirm the location of cancer, evaluate its severity, and design appropriate treatments. This paper presents PCaSAM, a fully automated PCa segmentation model that allows us to input multi-modal MRI images into the foundation model to improve performance significantly. We collected multi-center datasets to conduct a comprehensive evaluation. The results showed that PCaSAM outperforms the generalist medical foundation model and the other representative segmentation models, with the average DSC of 0.721 and 0.706 in the internal and external datasets, respectively. Furthermore, with the assistance of segmentation, the PI-RADS scoring of PCa lesions was improved significantly, leading to a substantial increase in average AUC by 8.3–8.9% on two external datasets. Besides, PCaSAM achieved superior efficiency, making it highly suitable for real-world deployment scenarios.https://doi.org/10.1038/s41746-025-01756-2
spellingShingle Yuhan Zhang
Xiao Ma
Mingchao Li
Kun Huang
Jie Zhu
Miao Wang
Xi Wang
Menglin Wu
Pheng-Ann Heng
Generalist medical foundation model improves prostate cancer segmentation from multimodal MRI images
npj Digital Medicine
title Generalist medical foundation model improves prostate cancer segmentation from multimodal MRI images
title_full Generalist medical foundation model improves prostate cancer segmentation from multimodal MRI images
title_fullStr Generalist medical foundation model improves prostate cancer segmentation from multimodal MRI images
title_full_unstemmed Generalist medical foundation model improves prostate cancer segmentation from multimodal MRI images
title_short Generalist medical foundation model improves prostate cancer segmentation from multimodal MRI images
title_sort generalist medical foundation model improves prostate cancer segmentation from multimodal mri images
url https://doi.org/10.1038/s41746-025-01756-2
work_keys_str_mv AT yuhanzhang generalistmedicalfoundationmodelimprovesprostatecancersegmentationfrommultimodalmriimages
AT xiaoma generalistmedicalfoundationmodelimprovesprostatecancersegmentationfrommultimodalmriimages
AT mingchaoli generalistmedicalfoundationmodelimprovesprostatecancersegmentationfrommultimodalmriimages
AT kunhuang generalistmedicalfoundationmodelimprovesprostatecancersegmentationfrommultimodalmriimages
AT jiezhu generalistmedicalfoundationmodelimprovesprostatecancersegmentationfrommultimodalmriimages
AT miaowang generalistmedicalfoundationmodelimprovesprostatecancersegmentationfrommultimodalmriimages
AT xiwang generalistmedicalfoundationmodelimprovesprostatecancersegmentationfrommultimodalmriimages
AT menglinwu generalistmedicalfoundationmodelimprovesprostatecancersegmentationfrommultimodalmriimages
AT phengannheng generalistmedicalfoundationmodelimprovesprostatecancersegmentationfrommultimodalmriimages