Evaluating Artificial Intelligence-Assisted Prostate Biparametric MRI Interpretation: An International Multireader Study.

Journal: AJR. American journal of roentgenology
Published Date: Jul 16, 2025

Abstract

Variability in prostate biparametric MRI (bpMRI) interpretation limits diagnostic reliability for prostate cancer (PCa). Artificial intelligence (AI) has potential to reduce this variability and improve diagnostic accuracy. The objective of this study was to evaluate impact of a deep learning AI model on lesion- and patient-level clinically significant PCa (csPCa) and PCa detection rates and interreader agreement in bpMRI interpretations. This retrospective, multireader, multicenter study used a balanced incomplete block design for MRI randomization. Six radiologists of varying experience interpreted bpMRI scans with and without AI assistance in alternating sessions. The reference standard for lesion-level detection for cases was whole-mount pathology after radical prostatectomy; for control patients, negative 12-core systematic biopsies. In all, 180 patients (120 in the case group, 60 in the control group) who underwent mpMRI and prostate biopsy or radical prostatectomy between January 2013 and December 2022 were included. Lesion-level sensitivity, PPV, patient-level AUC for csPCa and PCa detection, and interreader agreement in lesion-level PI-RADS scores and size measurements were assessed. AI assistance improved lesion-level PPV (PI-RADS ≥ 3: 77.2% [95% CI, 71.0-83.1%] vs 67.2% [61.1-72.2%] for csPCa; 80.9% [75.2-85.7%] vs 69.4% [63.4-74.1%] for PCa; both p < .001), reduced lesion-level sensitivity (PIRADS ≥ 3: 44.4% [38.6-50.5%] vs 48.0% [42.0-54.2%] for csPCa, p = .01; 41.7% [37.0-47.4%] vs 44.9% [40.5-50.2%] for PCa, p = .01), and no difference in patient-level AUC (0.822 [95% CI, 0.768-0.866] vs 0.832 [0.787-0.868] for csPCa, p = .61; 0.833 [0.782-0.874] vs 0.835 [0.792-0.871] for PCa, p = .91). AI assistance improved interreader agreement for lesion-level PI-RADS scores (κ = 0.748 [95% CI, 0.701-0.796] vs 0.336 [0.288-0.381], p < .001), lesion size measurements (coverage probability of 0.397 [0.376-0.419] vs 0.367 [0.349-0.383], p < .001), and patient-level PI-RADS scores (κ = 0.704 [0.627-0.767] versus 0.507 [0.421-0.584], p < .001). AI improved lesion-level PPV and interreader agreement with slightly lower lesion-level sensitivity. AI may enhance consistency and reduce false-positives in bpMRI interpretations. Further optimization is required to improve sensitivity without compromising specificity.

Authors

  • David G Gelikman
    Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, 10 Center Dr., MSC 1182, Building 10, Room B3B85, Bethesda, MD, 20892, USA.
  • Enis C Yilmaz
    Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Stephanie A Harmon
    Clinical Research Directorate, Frederick National Laboratory for Cancer Research sponsored by the National Cancer Institute, Frederick, Maryland, USA.
  • Erich P Huang
    From the Molecular Imaging Branch (E.C.Y., S.A.H., M.J.B., Y.L., D.G.G., K.B.O., N.S.L., P.E., P.L.C., B.T.), Biometric Research Program, Division of Cancer Treatment and Diagnosis (E.P.H.), Center for Interventional Oncology (L.A.H., C.G., B.J.W.), Department of Radiology, Clinical Center (L.A.H., C.G., B.J.W.), Laboratory of Pathology (A.T., M.J.M.), and Urologic Oncology Branch (S.G., P.A.P.), National Cancer Institute, National Institutes of Health, 10 Center Dr, MSC 1182, Bldg 10, Rm B3B85, Bethesda, MD 20892; Department of Radiology, Singapore General Hospital, Singapore (Y.M.L.); and NVIDIA Corporation, Santa Clara, Calif (D.Y., Z.X., J.T., D.X.).
  • Julie Y An
    Department of Radiology, University of California, San Diego, California, USA (J.Y.A.).
  • Sena Azamat
    Department of Radiology, Basaksehir Cam and Sakura City Hospital, Istanbul, Turkey.
  • Yan Mee Law
    Department of Diagnostic Radiology, Singapore General Hospital, Singapore.
  • Daniel J A Margolis
    Department of Radiology, Weill Cornell Medicine, New York, NY, USA. Electronic address: djm9016@med.cornell.edu.
  • Jamie Marko
    Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD.
  • Valeria Panebianco
    Department of Radiological Sciences, Oncology and Pathology, Sapienza/Policlinico Umberto I, Rome, Italy.
  • Omer Tarik Esengur
    Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Yue Lin
    Institute of Applied Remote Sensing and Information Technology, College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, China.
  • Mason J Belue
    Medical Research Scholars Program Fellow, Artificial Intelligence Resource, Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland.
  • Sonia Gaur
    Department of Radiology, Massachusetts General Hospital, Boston, Massachusetts, USA (S.G.).
  • Marco Bicchetti
    Department of Radiological Sciences, Oncology and Pathology, Sapienza University/Policlinico Umberto I, Viale Regina Elena 324, 00161, Rome, Italy.
  • Ziyue Xu
    Center for Infectious Disease Imaging (CIDI), Radiology and Imaging Science Department, National Institutes of Health (NIH), Bethesda, MD 20892, United States.
  • Jesse Tetreault
    NVIDIA Corporation, Bethesda, Maryland, USA.
  • Dong Yang
    College of Chemistry and Chemical Engineering, Shaanxi University of Science and Technology Xi'an 710021 China yangdong@sust.edu.cn.
  • Daguang Xu
    NVIDIA, Santa Clara, CA, USA.
  • Nathan S Lay
    Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, 10 Center Dr., MSC 1182, Building 10, Room B3B85, Bethesda, Maryland.
  • Sandeep Gurram
    National Cancer Institute, Bethesda, MD.
  • Joanna H Shih
    Division of Cancer Treatment and Diagnosis: Biometric Research Program, National Cancer Institute, National Institutes of Health, Rockville, MD.
  • Maria J Merino
    Center for Interventional Oncology, National Cancer Institute & Clinical Center, National Institutes of Health, Bethesda, MD, USA.
  • Rosina Lis
    Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, Massachusetts.
  • Peter L Choyke
    Molecular Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Bradford J Wood
    Molecular Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Peter A Pinto
    Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Baris Turkbey
    Molecular Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals