Multi-Center Benchmarking of a Commercially Available Artificial Intelligence Algorithm for Prostate Imaging Reporting and Data System (PI-RADS) Score Assignment and Lesion Detection in Prostate MRI.
Simple Summary: The number of MRI examinations of the prostate currently increases and is expected to rise even further upon the implementation of prostate cancer screening. Reading examinations is time-consuming but could be accelerated by AI algorithms that detect and stratify cancerous lesions ac...
| Publicado en: | Cancers Vol. 17; no. 5; pp. 815 - 828 |
|---|---|
| Autores principales: | , , , , , , , , , , , , , , , , |
| Formato: | diagnostic images research tables/charts Journal Article |
| Publicado: |
MDPI
Mar2025
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=183650650&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 183650650 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 20726694 B74B jtl: Cancers issn: 20726694 maglogo: N pubinfo: dt: Mar2025 vid: 17 iid: 5 pid: 97109 pub: MDPI artinfo: ui: 183650650 183650650 183650650 10.3390/cancers17050815 183650650 ppf: 815 ppct: 13 formats: tig: atl: Multi-Center Benchmarking of a Commercially Available Artificial Intelligence Algorithm for Prostate Imaging Reporting and Data System (PI-RADS) Score Assignment and Lesion Detection in Prostate MRI. aug: au: Oerther, Benedict Engel, Hannes Wilpert, Caroline Nedelcu, Andrea Sigle, August Grimm, Robert von Busch, Heinrich Schlett, Christopher L. Bamberg, Fabian Benndorf, Matthias Herrmann, Judith Nikolaou, Konstantin Amend, Bastian Bolenz, Christian Kloth, Christopher Beer, Meinrad Vogele, Daniel affil: Department of Diagnostic and Interventional Radiology, Medical Center—University of Freiburg, Faculty of Medicine, University of Freiburg, 79106 Freiburg, Germany sug: subj: Benchmarking Artificial Intelligence Algorithms Prostatic Neoplasms Diagnosis Magnetic Resonance Imaging Methods Prostatic Neoplasms Classification Human Retrospective Design Multicenter Studies Germany Male Middle Age Aged Aged, 80 and Over Academic Medical Centers Middle Aged: 45-64 years Aged: 65+ years Aged, 80 & over Male ab: Simple Summary: The number of MRI examinations of the prostate currently increases and is expected to rise even further upon the implementation of prostate cancer screening. Reading examinations is time-consuming but could be accelerated by AI algorithms that detect and stratify cancerous lesions according to the PI-RADS classification system. A plethora of algorithms was developed but lacks generalizability, external validation, and robustness when applied in different hospitals and varying MRI scanners. The algorithm tested in this study proved to be accurate and robust in a multi-center setting across different scanners, especially in confidently excluding prostate cancer. This suggests that it could be implemented in human reading to improve efficiency and readers' confidence. Background: The increase in multiparametric magnetic resonance imaging (mpMRI) examinations as a fundamental tool in prostate cancer (PCa) diagnostics raises the need for supportive computer-aided imaging analysis. Therefore, we evaluated the performance of a commercially available AI-based algorithm for prostate cancer detection and classification in a multi-center setting. Methods: Representative patients with 3T mpMRI between 2017 and 2022 at three different university hospitals were selected. Exams were read according to the PI-RADSv2.1 protocol and then assessed by an AI algorithm. Diagnostic accuracy for PCa of both human and AI readings were calculated using MR-guided ultrasound fusion biopsy as the gold standard. Results: Analysis of 91 patients resulted in 138 target lesions. Median patient age was 67 years (range: 49–82), median PSA at the time of the MRI exam was 8.4 ng/mL (range: 1.47–73.7). Sensitivity and specificity for clinically significant prostate cancer (csPCa, defined as ISUP ≥ 2) were 92%/64% for radiologists vs. 91%/57% for AI detection on patient level and 90%/70% vs. 81%/78% on lesion level, respectively (cut-off PI-RADS ≥ 4). Two cases of csPCa were missed by the AI on patient-level, resulting in a negative predictive value (NPV) of 0.88 at a cut-off of PI-RADS ≥ 3. Conclusions: AI-augmented lesion detection and scoring proved to be a robust tool in a multi-center setting with sensitivity comparable to the radiologists, even outperforming human reader specificity on both patient and lesion levels at a threshold of PI-RADS ≥3 and a threshold of PI-RADS ≥ 4 on lesion level. In anticipation of refinements of the algorithm and upon further validation, AI-detection could be implemented in the clinical workflow prior to human reading to exclude PCa, thereby drastically improving reading efficiency. pubtype: Academic Journal doctype: diagnostic images research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|