Prostate-Specific Foundation Models for Enhanced Detection of Clinically Significant Cancer

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Jeong Hoon, Li, Cynthia Xinran, Jahanandish, Hassan, Bhattacharya, Indrani, Vesal, Sulaiman, Zhang, Lichun, Sang, Shengtian, Choi, Moon Hyung, Soerensen, Simon John Christoph, Zhou, Steve Ran, Sommer, Elijah Richard, Fan, Richard, Ghanouni, Pejman, Song, Yuze, Seibert, Tyler M., Sonn, Geoffrey A., Rusu, Mirabela
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913677788053504
author Lee, Jeong Hoon
Li, Cynthia Xinran
Jahanandish, Hassan
Bhattacharya, Indrani
Vesal, Sulaiman
Zhang, Lichun
Sang, Shengtian
Choi, Moon Hyung
Soerensen, Simon John Christoph
Zhou, Steve Ran
Sommer, Elijah Richard
Fan, Richard
Ghanouni, Pejman
Song, Yuze
Seibert, Tyler M.
Sonn, Geoffrey A.
Rusu, Mirabela
author_facet Lee, Jeong Hoon
Li, Cynthia Xinran
Jahanandish, Hassan
Bhattacharya, Indrani
Vesal, Sulaiman
Zhang, Lichun
Sang, Shengtian
Choi, Moon Hyung
Soerensen, Simon John Christoph
Zhou, Steve Ran
Sommer, Elijah Richard
Fan, Richard
Ghanouni, Pejman
Song, Yuze
Seibert, Tyler M.
Sonn, Geoffrey A.
Rusu, Mirabela
contents Accurate prostate cancer diagnosis remains challenging. Even when using MRI, radiologists exhibit low specificity and significant inter-observer variability, leading to potential delays or inaccuracies in identifying clinically significant cancers. This leads to numerous unnecessary biopsies and risks of missing clinically significant cancers. Here we present prostate vision contrastive network (ProViCNet), prostate organ-specific vision foundation models for Magnetic Resonance Imaging (MRI) and Trans-Rectal Ultrasound imaging (TRUS) for comprehensive cancer detection. ProViCNet was trained and validated using 4,401 patients across six institutions, as a prostate cancer detection model on radiology images relying on patch-level contrastive learning guided by biopsy confirmed radiologist annotations. ProViCNet demonstrated consistent performance across multiple internal and external validation cohorts with area under the receiver operating curve values ranging from 0.875 to 0.966, significantly outperforming radiologists in the reader study (0.907 versus 0.805, p<0.001) for mpMRI, while achieving 0.670 to 0.740 for TRUS. We also integrated ProViCNet with standard PSA to develop a virtual screening test, and we showed that we can maintain the high sensitivity for detecting clinically significant cancers while more than doubling specificity from 15% to 38% (p<0.001), thereby substantially reducing unnecessary biopsies. These findings highlight that ProViCNet's potential for enhancing prostate cancer diagnosis accuracy and reduce unnecessary biopsies, thereby optimizing diagnostic pathways.
format Preprint
id arxiv_https___arxiv_org_abs_2502_00366
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prostate-Specific Foundation Models for Enhanced Detection of Clinically Significant Cancer
Lee, Jeong Hoon
Li, Cynthia Xinran
Jahanandish, Hassan
Bhattacharya, Indrani
Vesal, Sulaiman
Zhang, Lichun
Sang, Shengtian
Choi, Moon Hyung
Soerensen, Simon John Christoph
Zhou, Steve Ran
Sommer, Elijah Richard
Fan, Richard
Ghanouni, Pejman
Song, Yuze
Seibert, Tyler M.
Sonn, Geoffrey A.
Rusu, Mirabela
Image and Video Processing
Computer Vision and Pattern Recognition
Accurate prostate cancer diagnosis remains challenging. Even when using MRI, radiologists exhibit low specificity and significant inter-observer variability, leading to potential delays or inaccuracies in identifying clinically significant cancers. This leads to numerous unnecessary biopsies and risks of missing clinically significant cancers. Here we present prostate vision contrastive network (ProViCNet), prostate organ-specific vision foundation models for Magnetic Resonance Imaging (MRI) and Trans-Rectal Ultrasound imaging (TRUS) for comprehensive cancer detection. ProViCNet was trained and validated using 4,401 patients across six institutions, as a prostate cancer detection model on radiology images relying on patch-level contrastive learning guided by biopsy confirmed radiologist annotations. ProViCNet demonstrated consistent performance across multiple internal and external validation cohorts with area under the receiver operating curve values ranging from 0.875 to 0.966, significantly outperforming radiologists in the reader study (0.907 versus 0.805, p<0.001) for mpMRI, while achieving 0.670 to 0.740 for TRUS. We also integrated ProViCNet with standard PSA to develop a virtual screening test, and we showed that we can maintain the high sensitivity for detecting clinically significant cancers while more than doubling specificity from 15% to 38% (p<0.001), thereby substantially reducing unnecessary biopsies. These findings highlight that ProViCNet's potential for enhancing prostate cancer diagnosis accuracy and reduce unnecessary biopsies, thereby optimizing diagnostic pathways.
title Prostate-Specific Foundation Models for Enhanced Detection of Clinically Significant Cancer
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.00366