Scholarlink

Introduction and objectives <p>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).</p> Materials and methods <p>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.</p> Results <p>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).</p> Conclusions <p>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.</p> Trial registration <p>NCT04605276.</p> Key Points <p><Emphasis Type="BoldItalic">Question</Emphasis> <i>Does the diagnostic performance of a 3D multiparametric ultrasound-based AI model translate from voxel-level training to patient-level biopsy simulation?</i></p> <p><Emphasis Type="BoldItalic">Findings</Emphasis> <i>Simulated biopsy performance aligned with voxel-level results, showing robust csPCa detection and supporting the model’s generalizability across independent datasets.</i></p> <p><Emphasis Type="BoldItalic">Clinical relevance</Emphasis> <i>The AI model’s consistent biopsy simulation performance confirms its readiness for clinical evaluation and suggests diagnostic value in MRI-constrained settings.</i></p> Graphical Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月6日

查看全文
  • Daniel L. van den Kroonenberg,
  • Florian Delberghe,
  • Auke Jager,
  • Arnoud W. Postema,
  • Katelijne C. C. de Bie,
  • Johannes B. Reitsma,
  • Marije Zwart,
  • Hessel Wijkstra,
  • Anna Garrido-Utrilla,
  • Joost de Baaij,
  • Jean-Paul A. van Basten,
  • Henk G. van der Poel,
  • Harrie P. Beerlage,
  • Massimo Mischi,
  • Jorg R. Oddens

摘要

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.

Graphical Abstract