Performance of a Region of Interest–based Algorithm in Diagnosing International Society of Urological Pathology Grade Group ≥2 Prostate Cancer on the MRI-FIRST Database—CAD-FIRST Study

• Published in: European urology oncology Vol. 7; no. 5; pp. 1113 - 1122
• Main Authors: Couchoux, Thibaut, Jaouen, Tristan, Melodelima-Gonindard, Christelle, Baseilhac, Pierre, Branchu, Arthur, Arfi, Nicolas, Aziza, Richard, Barry Delongchamps, Nicolas, Bladou, Franck, Bratan, Flavie, Brunelle, Serge, Colin, Pierre, Correas, Jean-Michel, Cornud, François, Descotes, Jean-Luc, Eschwege, Pascal, Fiard, Gaelle, Guillaume, Bénédicte, Grange, Rémi, Grenier, Nicolas, Lang, Hervé, Lefèvre, Frédéric, Malavaud, Bernard, Marcelin, Clément, Moldovan, Paul C., Mottet, Nicolas, Mozer, Pierre, Potiron, Eric, Portalez, Daniel, Puech, Philippe, Renard-Penna, Raphaele, Roumiguié, Matthieu, Roy, Catherine, Timsit, Marc-Olivier, Tricard, Thibault, Villers, Arnauld, Walz, Jochen, Debeer, Sabine, Mansuy, Adeline, Mège-Lechevallier, Florence, Decaussin-Petrucci, Myriam, Badet, Lionel, Colombel, Marc, Ruffion, Alain, Crouzet, Sébastien, Rabilloud, Muriel, Souchon, Rémi, Rouvière, Olivier
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.10.2024; Elsevier
• Subjects: Aged; Algorithms; Artificial intelligence; Databases, Factual; Humans; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Middle Aged; Multiparametric Magnetic Resonance Imaging; Neoplasm Grading; Prostate biopsy; Prostate cancer; Prostatic Neoplasms - diagnostic imaging; Prostatic Neoplasms - pathology; Radiomics; Retrospective Studies; Sensitivity and Specificity; Statistics; Magnetic resonance imaging; Prostate biopsy; Artificial intelligence; Prostate cancer; Radiomics
• ISSN: 2588-9311; 2588-9311
• DOI: 10.1016/j.euo.2024.03.003

The overall performance of the tested computer-aided diagnosis (CADx) system was similar to that of the Prostate Imaging Reporting and Data System version 2 score assigned prospectively at the time of biopsy. The CADx predefined diagnostic thresholds, which provided 90% sensitivity in the training dataset, yielded sensitivity of 86% (95% confidence interval: 76–94) and specificity of 64% (95% confidence interval: 55–74) in the test dataset. The CADx score could help stratify the risk of clinically significant prostate cancer in patients with positive magnetic resonance imaging and negative prostate-specific antigen density. Prostate multiparametric magnetic resonance imaging (MRI) shows high sensitivity for International Society of Urological Pathology grade group (GG) ≥2 cancers. Many artificial intelligence algorithms have shown promising results in diagnosing clinically significant prostate cancer on MRI. To assess a region-of-interest–based machine-learning algorithm aimed at characterising GG ≥2 prostate cancer on multiparametric MRI. The lesions targeted at biopsy in the MRI-FIRST dataset were retrospectively delineated and assessed using a previously developed algorithm. The Prostate Imaging-Reporting and Data System version 2 (PI-RADSv2) score assigned prospectively before biopsy and the algorithm score calculated retrospectively in the regions of interest were compared for diagnosing GG ≥2 cancer, using the areas under the curve (AUCs), and sensitivities and specificities calculated with predefined thresholds (PIRADSv2 scores ≥3 and ≥4; algorithm scores yielding 90% sensitivity in the training database). Ten predefined biopsy strategies were assessed retrospectively. After excluding 19 patients, we analysed 232 patients imaged on 16 different scanners; 85 had GG ≥2 cancer at biopsy. At patient level, AUCs of the algorithm and PI-RADSv2 were 77% (95% confidence interval [CI]: 70–82) and 80% (CI: 74–85; p = 0.36), respectively. The algorithm’s sensitivity and specificity were 86% (CI: 76–93) and 65% (CI: 54–73), respectively. PI-RADSv2 sensitivities and specificities were 95% (CI: 89–100) and 38% (CI: 26–47), and 89% (CI: 79–96) and 47% (CI: 35–57) for thresholds of ≥3 and ≥4, respectively. Using the PI-RADSv2 score to trigger a biopsy would have avoided 26–34% of biopsies while missing 5–11% of GG ≥2 cancers. Combining prostate-specific antigen density, the PI-RADSv2 and algorithm’s scores would have avoided 44–47% of biopsies while missing 6–9% of GG ≥2 cancers. Limitations include the retrospective nature of the study and a lack of PI-RADS version 2.1 assessment. The algorithm provided robust results in the multicentre multiscanner MRI-FIRST database and could help select patients for biopsy. An artificial intelligence–based algorithm aimed at diagnosing aggressive cancers on prostate magnetic resonance imaging showed results similar to expert human assessment in a prospectively acquired multicentre test database.