Characterization of prostate MRI focal lesions by combining human reading, artificial intelligence and prostate-specific antigen density: A multi-reader study - 15/08/26
Highlights |
• | Combining PI-RADS scoring, artificial intelligence findings and prostate-specific antigen density reduces the proportion of unnecessary prostate biopsies. |
• | Combining PI-RADS scoring, artificial intelligence findings and prostate-specific antigen density reduces variability in biopsy decision across readers with varying experience. |
• | Combining PI-RADS scoring, artificial intelligence findings and prostate-specific antigen density slightly reduces the sensitivity for clinically significant prostate cancer. |
Abstract |
Purpose |
The purpose of this study was to compare, across readers with varying experience, the characterisation of prostate MRI lesions as grade group (GG) ≥ 2 cancer, by using the PI-RADS version 2.1 (PI-RADSv2.1) score alone and by combining prostate specific antigen density (PSAd), the PI-RADSv2.1 score and the output of a radiomics-based algorithm (Q-CAD).
Materials and methods |
The MULTI database in which 21 readers (seven experienced seniors, seven less-experienced seniors, seven juniors) had assigned a PI-RADSv2.1 score to 240 prostate MRI lesions was retrospectively used. The lesions were outlined by two independent experts to compute their Q-CAD score. For each reader, four biopsy strategies were simulated. PI-RADS 3 and PI-RADS 4 strategies triggered biopsy in PI-RADSv2.1 ≥ 3 and PI-RADSv2.1 ≥ 4 lesions respectively. Combined 3 and Combined 4 strategies triggered biopsy when at least two of the following conditions were fulfilled: positive PI-RADSv2.1 score (≥ 3 for Combined 3 ; ≥ 4 for Combined 4 ), positive Q-CAD score (≥ 0.45 in peripheral zone; ≥ 0.79 in transition zone), PSAd ≥ 0.15 ng/mL/cm 3 .
Results |
A total of 232 lesions were included. Using lesions’ delineations by Expert 1 for the three readers’ experience groups, the Combined 3 strategy was significantly less sensitive for GG ≥ 2 cancers (87–88% vs . 91–96%; P = 0.026 to < 0.001), but significantly more specific (45%–55% vs . 15%–34%; P < 0.001) than the PI-RADS 3 strategy. The Combined 4 strategy was less sensitive than the PI-RADS 4 strategy (84%–86% vs . 85%–91%) but the difference was significant only for less-experienced seniors ( P = 0.023); it was significantly more specific (51%–63% vs . 27%–50%; P < 0.001) in all groups. The Combined 4 strategy provided the highest net benefit for risk thresholds > 12%–16%. Using lesions’ delineations by Expert 2 yielded similar results.
Conclusion |
The combined strategies significantly increased specificity, at the cost of slightly reducing sensitivity for GG ≥ 2 cancers.
Le texte complet de cet article est disponible en PDF.Graphical abstract |
Keywords : Artificial intelligence, Prostate biopsy, Prostate cancer, Magnetic resonance imaging
Abbreviations : AI, AUC, CDR, CI, csPCa, DCA, GG, MRI, PI-RADS, PI-RADSv2.1, PSA, PSAd, PZ, ROI, TZ
Plan
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 ?