Characterization of prostate MRI focal lesions by combining human reading, artificial intelligence and prostate-specific antigen density: A multi-reader study.
Authors
Affiliations (9)
Affiliations (9)
- Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Imaging, Lyon, 69003, France.
- Pôle Santé Publique, Service de Biostatistique et Bioinformatique, Hospices Civils de Lyon, Lyon, 69003, France.
- INSERM, LabTAU, U1032, Lyon, 69003 , France.
- Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Imaging, Lyon, 69003, France; INSERM, LabTAU, U1032, Lyon, 69003 , France; Université Lyon 1, Lyon, 69003, France.
- Hospices Civils de Lyon, Department of Urology, Hôpital Edouard Herriot, Lyon, 69437 , France; Université Lyon 1, Lyon, 69003, France.
- Université Lyon 1, Lyon, 69003, France; Hospices Civils de Lyon, Department of Urology, Centre Hospitalier Lyon Sud, Pierre Bénite, 69310, France.
- INSERM, LabTAU, U1032, Lyon, 69003 , France; Hospices Civils de Lyon, Department of Urology, Hôpital Edouard Herriot, Lyon, 69437 , France; Université Lyon 1, Lyon, 69003, France.
- Pôle Santé Publique, Service de Biostatistique et Bioinformatique, Hospices Civils de Lyon, Lyon, 69003, France; Université Lyon 1, Lyon, 69003, France; CNRS, UMR 5558, Laboratoire de Biométrie et Biologie Évolutive, Équipe Biostatistique-Santé, Villeurbanne, 69100, France.
- Hospices Civils de Lyon, Hôpital Edouard Herriot, Department of Imaging, Lyon, 69003, France; INSERM, LabTAU, U1032, Lyon, 69003 , France; Université Lyon 1, Lyon, 69003, France. Electronic address: [email protected].
Abstract
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). 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<sub>3</sub> and PI-RADS<sub>4</sub> strategies triggered biopsy in PI-RADSv2.1 ≥ 3 and PI-RADSv2.1 ≥ 4 lesions respectively. Combined<sub>3</sub> and Combined<sub>4</sub> strategies triggered biopsy when at least two of the following conditions were fulfilled: positive PI-RADSv2.1 score (≥ 3 for Combined<sub>3</sub>; ≥ 4 for Combined<sub>4</sub>), positive Q-CAD score (≥ 0.45 in peripheral zone; ≥ 0.79 in transition zone), PSAd ≥ 0.15 ng/mL/cm<sup>3</sup>. A total of 232 lesions were included. Using lesions' delineations by Expert 1 for the three readers' experience groups, the Combined<sub>3</sub> 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<sub>3</sub> strategy. The Combined<sub>4</sub> strategy was less sensitive than the PI-RADS<sub>4</sub> 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<sub>4</sub> strategy provided the highest net benefit for risk thresholds >12%-16%. Using lesions' delineations by Expert 2 yielded similar results. The combined strategies significantly increased specificity, at the cost of slightly reducing sensitivity for GG ≥ 2 cancers.