Leveraging Representation Learning for Bi-parametric Prostate MRI to Disambiguate PI-RADS 3 and Improve Biopsy Decision Strategies.

Journal: Investigative radiology
Published Date: Jun 30, 2025

Abstract

OBJECTIVES: Despite its high negative predictive value (NPV) for clinically significant prostate cancer (csPCa), MRI suffers from a substantial number of false positives, especially for intermediate-risk cases. In this work, we determine whether a deep learning model trained with PI-RADS-guided representation learning can disambiguate the PI-RADS 3 classification, detect csPCa from bi-parametric prostate MR images, and avoid unnecessary benign biopsies.

Authors

  • Lavanya Umapathy
    Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, NY (L.U., P.J., T.D., A.T., S.C., D.K.S., H.C.); Center for Advanced Imaging Innovation and Research (CAI2R), Department of Radiology, New York University Grossman School of Medicine, New York, NY (L.U., P.J., S.C., D.K.S., H.C.); Courant Institute of Mathematical Sciences, New York University, New York, NY (S.C.); and Vilcek Institute of Graduate Biomedical Sciences, New York University Grossman School of Medicine, New York, NY (P.J., D.K.S., H.C.).
  • Patricia M Johnson
    Imaging Research Laboratories, Robarts Research Institute, The University of Western Ontario, London, Ontario, Canada.
  • Tarun Dutt
  • Angela Tong
    Department of Radiology, NYU Langone Health, 660 1st Avenue, 3rd Floor, New York, NY, 10016, USA.
  • Sumit Chopra
    Imagen Technologies, New York, NY 10012.
  • Daniel K Sodickson
    Center for Biomedical Imaging, Department of Radiology, NYU School of Medicine, New York, New York, USA.
  • Hersh Chandarana
    Department of Radiology, NYU Langone Health, 660 1st Avenue, 3rd Floor, New York, NY, 10016, USA.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals