Multiparametric Magnetic Resonance Imaging in the follow-up of non-muscle-invasive bladder tumors after intravesical instillations: a promising tool.

PURPOSE: The standard follow-up for non-muscle-invasive bladder cancer is based on cystoscopy. Unfortunately, post-instillation inflammatory changes can make the interpretation of this exam difficult, with lower specificity. This study aimed to evaluate the interest of bladder MRI in the follow-up of patients following intravesical instillation. METHODS: Data from patients who underwent cystoscopy and bladder MRI in a post-intravesical instillation setting between February 2020 and March 2023 were retrospectively collected. Primary endpoint was to evaluate and compare the diagnostic performance of cystoscopy and bladder MRI in the overall cohort (n = 67) using the pathologic results of TURB as a reference. The secondary endpoint was to analyze the diagnostic accuracy of cystoscopy and bladder MRI according to the appearance of the lesion on cystoscopy [flat (n = 40) or papillary (n = 27)]. RESULTS: The diagnostic performance of bladder MRI was better than that of cystoscopy, with a specificity of 47% (vs. 6%, p < 0.001), a negative predictive value of 88% (vs. 40%, p = 0.03), and a positive predictive value of 66% (vs. 51%, p < 0.001), whereas the sensitivity did not significantly differ between the two exams. In patients with doubtful cystoscopy and negative MRI findings, inflammatory changes were found on TURB in most cases (17/19). The superiority in MRI bladder performance prevailed for "flat lesions", while no significant difference was found for "papillary lesions". CONCLUSIONS: In cases of doubtful cystoscopy after intravesical instillations, MRI appears to be relevant with good performance in differentiating post-therapeutic inflammatory changes from recurrent tumor lesions and could potentially allow avoiding unnecessary TURB.

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.

BACKGROUND AND OBJECTIVE: 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. METHODS: 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. KEY FINDINGS AND LIMITATIONS: 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. CONCLUSIONS AND CLINICAL IMPLICATIONS: The algorithm provided robust results in the multicentre multiscanner MRI-FIRST database and could help select patients for biopsy. PATIENT SUMMARY: 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.