Article Dans Une Revue World Journal of Urology Année : 2023

Zone-specific computer-aided diagnosis system aimed at characterizing ISUP ≥ 2 prostate cancers on multiparametric magnetic resonance images: evaluation in a cohort of patients on active surveillance

Marc Colombel

Résumé

Purpose: To assess a region-of-interest-based computer-assisted diagnosis system (CAD) in characterizing aggressive prostate cancer on magnetic resonance imaging (MRI) from patients under active surveillance (AS). Methods: A prospective biopsy database was retrospectively searched for patients under AS who underwent MRI and subsequent biopsy at our institution. MRI lesions targeted at baseline biopsy were retrospectively delineated to calculate the CAD score that was compared to the Prostate Imaging-Reporting and Data System (PI-RADS) version 2 score assigned at baseline biopsy. Results: 186 patients were selected. At baseline biopsy, 51 and 15 patients had International Society of Urological Pathology (ISUP) grade ≥ 2 and ≥ 3 cancer respectively. The CAD score had significantly higher specificity for ISUP ≥ 2 cancers (60% [95% confidence interval (CI): 51–68]) than the PI-RADS score (≥ 3 dichotomization: 24% [CI: 17–33], p = 0.0003; ≥ 4 dichotomization: 32% [CI: 24–40], p = 0.0003). It had significantly lower sensitivity than the PI-RADS ≥ 3 dichotomization (85% [CI: 74–92] versus 98% [CI: 91–100], p = 0.015) but not than the PI-RADS ≥ 4 dichotomization (94% [CI:85–98], p = 0.104). Combining CAD findings and PSA density could have avoided 47/184 (26%) baseline biopsies, while missing 3/51 (6%) ISUP 2 and no ISUP ≥ 3 cancers. Patients with baseline negative CAD findings and PSAd < 0.15 ng/mL2 who stayed on AS after baseline biopsy had a 9% (4/44) risk of being diagnosed with ISUP ≥ 2 cancer during a median follow-up of 41 months, as opposed to 24% (18/74) for the others. Conclusion: The CAD could help define AS patients with low risk of aggressive cancer at baseline assessment and during subsequent follow-up.

Fichier principal
Vignette du fichier
Revised Manuscript.pdf (278.84 Ko) Télécharger le fichier
Fig 1.tif (100.09 Ko) Télécharger le fichier
Revised Online Resources.pdf (289.1 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05267436 , version 1 (24-09-2025)

Licence

Identifiants

Citer

Théo Arber, Tristan Jaouen, Séphora Campoy, Muriel Rabilloud, Rémi Souchon, et al.. Zone-specific computer-aided diagnosis system aimed at characterizing ISUP ≥ 2 prostate cancers on multiparametric magnetic resonance images: evaluation in a cohort of patients on active surveillance. World Journal of Urology, 2023, 41 (12), pp.3527-3533. ⟨10.1007/s00345-023-04643-1⟩. ⟨hal-05267436⟩
247 Consultations
118 Téléchargements

Altmetric

Partager

  • More