Evidence map›Paper›PMID 42249085›Full record

ArticleNPJ digital medicine2026

Enhancing foundation model transfer for prostate cancer detection with patch-level contrastive learning.

Jeong Hoon Lee, Cynthia Xinran Li, Hassan Jahanandish, Indrani Bhattacharya, Sulaiman Vesal, Yuze Song, Lichun Zhang, Shengtian Sang, Moon Hyung Choi, Simon John Christoph Soerensen and 7 more

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in NPJ digital medicine, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.

0numbers the graph read from it
0cells of the map it votes in
0citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

0 citing papers in PubMed.

No citing paper in PubMed yet.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

17 authors.

Jeong Hoon LeeDepartment of Radiology, Stanford University, Stanford, CA, USA. sosal@stanford.edu.
Cynthia Xinran LiDepartment of Radiology, Stanford University, Stanford, CA, USA.
Hassan JahanandishDepartment of Urology, Stanford University, Stanford, CA, USA.
Indrani BhattacharyaDepartment of Radiology, Stanford University, Stanford, CA, USA.
Sulaiman VesalDepartment of Urology, Stanford University, Stanford, CA, USA.
Yuze SongDepartment of Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, CA, USA.
Lichun ZhangDepartment of Radiology, Stanford University, Stanford, CA, USA.
Shengtian SangDepartment of Radiology, Stanford University, Stanford, CA, USA.
Moon Hyung ChoiDepartment of Radiology, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea.
Simon John Christoph SoerensenDepartment of Urology, Stanford University, Stanford, CA, USA.
Steve Ran ZhouDepartment of Urology, Stanford University, Stanford, CA, USA.
Elijah Richard SommerDepartment of Urology, Stanford University, Stanford, CA, USA.
Tyler M SeibertDepartment of Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, CA, USA.
Richard FanDepartment of Urology, Stanford University, Stanford, CA, USA.
Pejman GhanouniDepartment of Radiology, Stanford University, Stanford, CA, USA.
Geoffrey A Sonn *Department of Radiology, Stanford University, Stanford, CA, USA.
Mirabela Rusu *Department of Radiology, Stanford University, Stanford, CA, USA. mirabela.rusu@stanford.edu.

Funding

Multimodal, Multi-scale Framework for Ethical AI Model DevelopmentOT2OD038065 · OD · EMORY UNIVERSITY · PI Judy Gichoya · 2025 to 2026
$2.9M
Rad-pathomic deep learning models to assist radiologists in differentiating aggressive from indolent prostate cancer on MRIR37CA260346 · NCI · STANFORD UNIVERSITY · PI Mirabela Rusu · 2022 to 2026
$2.8M
Predicting Pain Recovery: A Multimodality Machine-learning Approach using Harmonized Electronic Health Record DataOT2OD037955 · OD · MAYO CLINIC ARIZONA · PI Catherine Daniela Chong · 2025 to 2026
$2.3M
National Cancer Institute, National Institutes of Health R37CA260346National Institutes of Health (NIH) OT2OD037955-01NCI NIH HHS R37 CA260346NIH HHS OT2 OD037955NIH HHS OT2 OD038065U.S. Department of Defense PC220278
6 · The paper itself

Abstract

Accurate localization of prostate cancer on magnetic resonance imaging (MRI) remains challenging due to the subtle appearance of cancer, resulting in missed clinically significant cancers, large inter-reader variability and large numbers of confounders that require biopsy confirmation. Vision foundation models have shown promise, but direct transfer to prostate MRI is challenging due to the substantial domain gap between natural images and prostate MRI and the subtle appearance of prostate cancer. We therefore developed prostate vision contrastive networks (ProViCNet), a weakly supervised model utilizing patch-level contrastive learning on MRI to support MRI-based screening, biopsy targeting and focal treatment planning. ProViCNet was trained and validated (using 4401 patients across six cohorts) as a prostate cancer detection model on MRI. Training labels were biopsy-confirmed radiologist annotations, while the evaluation labels included both biopsy and surgery-confirmed lesions. ProViCNet demonstrated consistent detection and segmentation performance across multiple internal and external validation cohorts, with area under the receiver operating characteristic curve (AUROC) values ranging from 0.875 to 0.966, and outperforming radiologists in the MRI expert reader study (0.907 versus 0.805, p < 0.01). We also integrated ProViCNet with serum PSA to develop a virtual screening test, which preserved high sensitivity for detecting clinically significant cancers while more than doubling specificity from 15% to 38% (p < 0.001) among men with PSA ≥ 4 ng/mL, thereby potentially reducing unnecessary biopsies. These findings highlight ProViCNet's potential for enhancing the accuracy of prostate cancer diagnosis and reducing unnecessary biopsies.

Identifiers

PMID42249085
PMCPMC13562539

What OpenQuestion holds

Textmetadata
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.