Evaluation of an artificial intelligence model based on multiparametric transrectal ultrasound for localizing clinically significant prostate cancer by simulation of targeted biopsies

European Radiology, vol. 36, pp. 3043–3049

Abstract

INTRODUCTION AND OBJECTIVES: An AI model that performs well during training does not guarantee similar performance in clinical practice and should be carefully evaluated before implementation. We aimed to evaluate a voxel-level trained AI model (AUROC 0.87), which utilizes a three-dimensional multiparametric transrectal prostate ultrasound (3D mpUS) to identify clinically significant prostate cancer (csPCa). MATERIALS AND METHODS: We included patients with csPCa (Grade Group ≥ 2 and scheduled for radical prostatectomy (RP)) and without csPCa (PI-RADS ≤ 2 and/or negative systematic biopsies). Histopathology of RP specimens provided the csPCa reference standard. 3D mpUS consisted of grayscale, contrast-enhanced ultrasound, and shear-wave elastography using automated acquisition. We assessed patient-level diagnostic accuracy by comparing the results of simulated targeted biopsies based on the AI model with the reference standard in internal and external evaluation. Patients without csPCa and RP reference standard were used to determine specificity. RESULTS: Based on internal evaluation of 250 patients, a sensitivity of 0.82 (CI 0.75 to 0.87) and specificity of 0.43 (CI 0.32 to 0.55) was reached for ISUP ≥ 2. For ISUP ≥ 3, this was 0.90 (CI 0.83-0.95) and 0.39 (CI 0.31-0.47). In the external evaluation of 77 patients, the sensitivity for ISUP ≥ 2 was 0.81 (CI 0.65-0.90), with a specificity of 0.42 (CI 0.28-0.57). For ISUP ≥ 3, this was 0.96 (CI 0.78-0.99) and 0.42 (CI 0.30-0.55). CONCLUSIONS: The AI model based on 3D mpUS showed consistent patient-level performance for csPCa detection in internal and external evaluation, comparable to voxel-level analysis. These suggest strong generalizability and support prospective clinical trials. TRIAL REGISTRATION: NCT04605276. KEY POINTS: Question Does the diagnostic performance of a 3D multiparametric ultrasound-based AI model translate from voxel-level training to patient-level biopsy simulation? Findings Simulated biopsy performance aligned with voxel-level results, showing robust csPCa detection and supporting the model's generalizability across independent datasets. Clinical relevance The AI model's consistent biopsy simulation performance confirms its readiness for clinical evaluation and suggests diagnostic value in MRI-constrained settings.

Authors 15

1. Daniël L. van den Kroonenberg corresponding

   Amsterdam University Medical Centers · Cancer Center Amsterdam

   Affiliation as printed

   Cancer Centre Amsterdam, Amsterdam, The Netherlands. d.kroonenbergvanden@amsterdamumc.nl

   Department of Urology, Amsterdam UMC, Amsterdam, The Netherlands. d.kroonenbergvanden@amsterdamumc.nl

   Cancer Centre Amsterdam, Amsterdam, The Netherlands

   Department of Urology, Amsterdam UMC, Amsterdam, The Netherlands

2. Florian Delberghe

   Eindhoven University of Technology

   Affiliation as printed

   Lab of Biomedical Diagnostics, Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands

3. Auke Jager

   Amsterdam University Medical Centers

   Affiliation as printed

   Department of Urology, Amsterdam UMC, Amsterdam, The Netherlands

4. Arnoud W. Postema Aachen Department of Urology, Leiden University Medical Center

   Leiden University Medical Center

   Affiliation as printed

   Department of Urology, Leiden University Medical Center, Leiden, The Netherlands

5. Katelijne C. C. de Bie

   Amsterdam University Medical Centers · Cancer Center Amsterdam

   Affiliation as printed

   Cancer Centre Amsterdam, Amsterdam, The Netherlands

   Department of Urology, Amsterdam UMC, Amsterdam, The Netherlands

6. Johannes B. Reitsma

   Utrecht University · University Medical Center Utrecht

   Affiliation as printed

   Julius Center for Health Sciences and Primary Care, UMC Utrecht, Utrecht University, Utrecht, The Netherlands

7. Marije J. Zwart
   Affiliation as printed

   Angiogenesis Analytics, Den Bosch, The Netherlands

8. Hessel Wijkstra

   Eindhoven University of Technology

   Affiliation as printed

   Lab of Biomedical Diagnostics, Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands

9. Anna Garrido‐Utrilla
   Affiliation as printed

   Angiogenesis Analytics, Den Bosch, The Netherlands

10. Joost de Baaij

    Canisius-Wilhelmina Ziekenhuis

    Affiliation as printed

    Department of Urology, Canisius Wilhelmina Hospital, Nijmegen, The Netherlands

    Prosper Collaborative Prostate Cancer Clinics, Nijmegen-Eindhoven, The Netherlands

11. Jean‐Paul A. van Basten

    Canisius-Wilhelmina Ziekenhuis

    Affiliation as printed

    Department of Urology, Canisius Wilhelmina Hospital, Nijmegen, The Netherlands

    Prosper Collaborative Prostate Cancer Clinics, Nijmegen-Eindhoven, The Netherlands

12. Henk G. van der Poel

    The Netherlands Cancer Institute · Amsterdam University Medical Centers

    Affiliation as printed

    Department of Urology, Amsterdam UMC, Amsterdam, The Netherlands

    Department of Urology, Netherlands Cancer Institute - Antoni van Leeuwenhoek Hospital, Amsterdam, The Netherlands

13. Harrie P. Beerlage

    Amsterdam University Medical Centers

    Affiliation as printed

    Department of Urology, Amsterdam UMC, Amsterdam, The Netherlands

14. Massimo Mischi

    Eindhoven University of Technology

    Affiliation as printed

    Lab of Biomedical Diagnostics, Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands

15. Jorg Reinier Oddens

    Amsterdam University Medical Centers · Cancer Center Amsterdam

    Affiliation as printed

    Cancer Centre Amsterdam, Amsterdam, The Netherlands

    Department of Urology, Amsterdam UMC, Amsterdam, The Netherlands