EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access

ProMUS ‐ NET : Artificial intelligence detects more prostate cancer than urologists on micro‐ultrasonography

Steve R Zhou iD, Lichun Zhang, Moon Hyung Choi iD, Sulaiman Vesal, Adam Kinnaird iD, Wayne G Brisbane iD, Giovanni Lughezzani, Davide Maffei iD, Vittorio Fasulo, Patrick Albers, Richard E Fan, Wei Shao und 2 weitere

BJU International · 2025

DOI: 10.1111/bju.16892 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift BJU International, 2025. Verfasst von Steve R Zhou und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Urology, Stanford School of Medicine, Palo Alto, CA, USA. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Artificial Intelligence, Deep Learning, Urologists. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To improve sensitivity and inter‐reader consistency of prostate cancer localisation on micro‐ultrasonography (MUS) by developing a deep learning model for automatic cancer segmentation, and to compare model performance with that of expert urologists. Patients and Methods We performed an institutional review board‐approved prospective collection of MUS images from patients undergoing magnetic resonance imaging (MRI)‐ultrasonography fusion guided biopsy at a single institution. Patients underwent 14‐core systematic biopsy and additional targeted sampling of suspicious MRI lesions. Biopsy pathology and MRI information were cross‐referenced to annotate the locations of International Society of Urological Pathology Grade Group (GG) ≥2 clinically significant cancer on MUS images. We trained a no‐new U‐Net model – the Prostate Micro‐Ultrasound Network (ProMUS‐NET) – to localise GG ≥2 cancer on these image stacks in a fivefold cross‐validation. Performance was compared vs that of six expert urologists in a matched sub‐cohort.

Results

The artificial intelligence (AI) model achieved an area under the receiver‐operating characteristic curve of 0.92 and detected more cancers than urologists (lesion‐level sensitivity 73% vs 58%; patient‐level sensitivity 77% vs 66%). AI lesion‐level sensitivity for peripheral zone lesions was 86.2%.

Conclusions

Our AI model identified prostate cancer lesions on MUS with high sensitivity and specificity. Further work is ongoing to improve margin overlap, to reduce false positives, and to perform external validation. AI‐assisted prostate cancer detection on MUS has great potential to improve biopsy diagnosis by urologists.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Prostatic NeoplasmsArtificial IntelligenceDeep LearningUrologistsHumansMaleMiddle AgedAgedProspective StudiesSensitivity and SpecificityImage-Guided BiopsyUltrasonographyMagnetic Resonance Imaging

Stichwörter der Autor:innen

artificial intelligenceconvolutional neural networksmicro‐ultrasonographyprostate cancertargeted biopsy

Autor:innen und Institutionen

  • Department of Urology, Stanford School of Medicine, Palo Alto, CA, USA.
  • Department of Radiology, Stanford School of Medicine, Palo Alto, CA, USA.
  • Department of Radiology, College of Medicine, The Catholic University of Korea, Jongno-gu, Korea.
  • Department of Urology, University of Alberta, Edmonton, AB, Canada.
  • Department of Urology, UCLA, Los Angeles, CA, USA.
  • Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Milan, Italy.

ORCID-Profile: Steve R Zhou, Moon Hyung Choi, Adam Kinnaird, Wayne G Brisbane, Davide Maffei

Förderung

  • NCI NIH HHS

Zitieren

APA

Zhou, S. R., Zhang, L., Choi, M. H., Vesal, S., Kinnaird, A., Brisbane, W. G., Lughezzani, G., Maffei, D., Fasulo, V., Albers, P., Fan, R. E., Shao, W., Sonn, G. A., & Rusu, M. (2025). ProMUS ‐ NET : Artificial intelligence detects more prostate cancer than urologists on micro‐ultrasonography. BJU International. https://doi.org/10.1111/bju.16892

Vancouver

Zhou SR, Zhang L, Choi MH, Vesal S, Kinnaird A, Brisbane WG, et al. ProMUS ‐ NET : Artificial intelligence detects more prostate cancer than urologists on micro‐ultrasonography. BJU International. 2025. doi:10.1111/bju.16892

BibTeX
@article{Zhou2025,
  author = {Zhou, Steve R and Zhang, Lichun and Choi, Moon Hyung and Vesal, Sulaiman and Kinnaird, Adam and Brisbane, Wayne G and Lughezzani, Giovanni and Maffei, Davide and Fasulo, Vittorio and Albers, Patrick and Fan, Richard E and Shao, Wei and Sonn, Geoffrey A and Rusu, Mirabela},
  title = {ProMUS ‐ NET : Artificial intelligence detects more prostate cancer than urologists on micro‐ultrasonography},
  journal = {BJU International},
  year = {2025},
  doi = {10.1111/bju.16892}
}
Kostenlos starten →