AI-powered prostate cancer detection: a multi-centre, multi-scanner validation study
European Radiology · 28.02.2025 · 35 (8) · 4915-4924
DOI: 10.1007/s00330-024-11323-0 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift European Radiology, online erschienen am 28.02.2025. Verfasst von Francesco Giganti und 34 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, University College London Hospitals NHS Foundation Trust, London, UK. f.giganti@ucl.ac.uk. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Artificial Intelligence, Magnetic Resonance Imaging, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Lucida Medical.
Abstract (Originalsprache)
Objectives
Multi-centre, multi-vendor validation of artificial intelligence (AI) software to detect clinically significant prostate cancer (PCa) using multiparametric magnetic resonance imaging (MRI) is lacking. We compared a new AI solution, validated on a separate dataset from different UK hospitals, to the original multidisciplinary team (MDT)-supported radiologist’s interpretations. Materials and methods A Conformité Européenne (CE)-marked deep-learning (DL) computer-aided detection (CAD) medical device (Pi) was trained to detect Gleason Grade Group (GG) ≥ 2 cancer using retrospective data from the PROSTATEx dataset and five UK hospitals (793 patients). Our separate validation dataset was on six machines from two manufacturers across six sites (252 patients). Data included in the study were from MRI scans performed between August 2018 to October 2022. Patients with a negative MRI who did not undergo biopsy were assumed to be negative (90.4% had prostate-specific antigen density < 0.15 ng/mL 2 ). ROC analysis was used to compare radiologists who used a 5-category suspicion score.
Results
GG ≥ 2 prevalence in the validation set was 31%. Evaluated per patient, Pi was non-inferior to radiologists (considering a 10% performance difference as acceptable), with an area under the curve (AUC) of 0.91 vs. 0.95. At the predetermined risk threshold of 3.5, the AI software’s sensitivity was 95% and specificity 67%, while radiologists at Prostate Imaging-Reporting and Data Systems/Likert ≥ 3 identified GG ≥ 2 with a sensitivity of 99% and specificity of 73%. AI performed well per-site (AUC ≥ 0.83) at the patient-level independent of scanner age and field strength.
Conclusion
Real-world data testing suggests that Pi matches the performance of MDT-supported radiologists in GG ≥ 2 PCa detection and generalises to multiple sites, scanner vendors, and models. Key Points Question The performance of artificial intelligence-based medical tools for prostate MRI has yet to be evaluated on multi-centre, multi-vendor data to assess generalisability.
Findings
A dedicated AI medical tool matches the performance of multidisciplinary team-supported radiologists in prostate cancer detection and generalises to multiple sites and scanners. Clinical relevance This software has the potential to support the MRI process for biopsy decision-making and target identification, but future prospective studies, where lesions identified by artificial intelligence are biopsied separately, are needed. Graphical Abstract
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, University College London Hospitals NHS Foundation Trust, London, UK. f.giganti@ucl.ac.uk.
- Division of Surgery & Interventional Science, University College London, London, UK. f.giganti@ucl.ac.uk.
- Lucida Medical Ltd, Cambridge, UK.
- Cambridge University Hospitals NHS Foundation Trust & University of Cambridge, Cambridge, UK.
- Royal Cornwall Hospitals NHS Trust, Truro, UK.
- Royal United Hospitals Bath NHS Foundation Trust, Bath, UK.
Förderung
- Lucida Medical
Zitieren
APA
Giganti, F., Moreira da Silva, N., Yeung, M., Davies, L., Frary, A., Ferrer Rodriguez, M., Sushentsev, N., Ashley, N., Andreou, A., Bradley, A., Wilson, C., Maskell, G., Brembilla, G., Caglic, I., Suchánek, J., Budd, J., Arya, Z., Aning, J., Hayes, J., …, & Sala, E. (2025). AI-powered prostate cancer detection: a multi-centre, multi-scanner validation study. European Radiology, 35(8), 4915-4924. https://doi.org/10.1007/s00330-024-11323-0
Vancouver
Giganti F, Moreira da Silva N, Yeung M, Davies L, Frary A, Ferrer Rodriguez M, et al. AI-powered prostate cancer detection: a multi-centre, multi-scanner validation study. European Radiology. 2025;35(8):4915-4924. doi:10.1007/s00330-024-11323-0
BibTeX
@article{Giganti2025,
author = {Giganti, Francesco and Moreira da Silva, Nadia and Yeung, Michael and Davies, Lucy and Frary, Amy and Ferrer Rodriguez, Mirjana and Sushentsev, Nikita and Ashley, Nicholas and Andreou, Adrian and Bradley, Alison and Wilson, Chris and Maskell, Giles and Brembilla, Giorgio and Caglic, Iztok and Suchánek, Jakub and Budd, Jobie and Arya, Zobair and Aning, Jonathan and Hayes, John and De Bono, Mark and Vasdev, Nikhil and Sanmugalingam, Nimalan and Burn, Paul and Persad, Raj and Woitek, Ramona and Hindley, Richard and Liyanage, Sidath and Squire, Sophie and Barrett, Tristan and Barwick, Steffi and Hinton, Mark and Padhani, Anwar R and Rix, Antony and Shah, Aarti and Sala, Evis},
title = {AI-powered prostate cancer detection: a multi-centre, multi-scanner validation study},
journal = {European Radiology},
year = {2025},
volume = {35},
number = {8},
pages = {4915--4924},
doi = {10.1007/s00330-024-11323-0}
}
EUVIMED