Artificial intelligence algorithms aimed at characterizing or detecting prostate cancer on MRI: How accurate are they when tested on independent cohorts? – A systematic review - 13/12/22
Five independency domains to better characterize the test cohorts used for assessing artificial intelligence-based algorithms in prostate MRI were defined including institution, MRI vendor, magnetic field strength, population, and period of acquisition.
Most algorithms provide good results in test cohorts, challenging those obtained by human reading.
Using predefined diagnostic thresholds, robust results were obtained with algorithms aimed at characterizing regions-of-interests defined by human readers.
Predefined diagnostic thresholds yielded variable results for algorithms aimed at both detecting and characterizing lesions.
Conflicting results were obtained by studies assessing unassisted and assisted prostate MRI reading.
The purpose of this study was to perform a systematic review of the literature on the diagnostic performance, in independent test cohorts, of artificial intelligence (AI)-based algorithms aimed at characterizing/detecting prostate cancer on magnetic resonance imaging (MRI).
Materials and methods
Medline, Embase and Web of Science were searched for studies published between January 2018 and September 2022, using a histological reference standard, and assessing prostate cancer characterization/detection by AI-based MRI algorithms in test cohorts composed of more than 40 patients and with at least one of the following independency criteria as compared to the training cohort: different institution, different population type, different MRI vendor, different magnetic field strength or strict temporal splitting.
Thirty-five studies were selected. The overall risk of bias was low. However, 23 studies did not use predefined diagnostic thresholds, which may have optimistically biased the results. Test cohorts fulfilled one to three of the five independency criteria. The diagnostic performance of the algorithms used as standalones was good, challenging that of human reading. In the 12 studies with predefined diagnostic thresholds, radiomics-based computer-aided diagnosis systems (assessing regions-of-interest drawn by the radiologist) tended to provide more robust results than deep learning-based computer-aided detection systems (providing probability maps). Two of the six studies comparing unassisted and assisted reading showed significant improvement due to the algorithm, mostly by reducing false positive findings.
Prostate MRI AI-based algorithms showed promising results, especially for the relatively simple task of characterizing predefined lesions. The best management of discrepancies between human reading and algorithm findings still needs to be defined.Le texte complet de cet article est disponible en PDF.
Keywords : Artificial intelligence, Magnetic resonance imaging, Prostatic neoplasms, Systematic review
List of abbreviations : AI, AUC, CADe, CADx, CADp, csPCa, DCE, DSC, ISUP, MRI, PCa, PI-RADS, PZ, TZ
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?