Artificial intelligence to improve cytology performances in bladder carcinoma detection: results of the VisioCyt test - Université Claude Bernard Lyon 1 Accéder directement au contenu
Article Dans Une Revue BJU International Année : 2021

Artificial intelligence to improve cytology performances in bladder carcinoma detection: results of the VisioCyt test

Résumé

Objective To explore the utility of artificial intelligence (AI) using the VisioCyt® test (VitaDX International, Rennes, France) to improve diagnosis of bladder carcinoma using voided urine cytology. Patients and Methods A national prospective multicentre trial (14 centres) was conducted on 1360 patients, divided in two groups. The first group included bladder carcinoma diagnosis with different histological grades and stages, and the second group included control patients based on negative cystoscopy and cytology results. The first step of this VISIOCYT1 trial focussed on algorithm development and the second step on validating this algorithm. A total of 598 patients were included in this first step, 449 patients with bladder tumours (219 high-grade and 230 low-grade) and 149 as negative controls. The VisioCyt test was compared to voided urine cytology performed by experienced uro-pathologists from each centre. Results Overall sensitivity was highly improved by the VisioCyt test compared to cytology (84.9% vs 43%). For high-grade tumours the VisioCyt test sensitivity was 92.6% vs 61.1% for the uro-pathologists. Regarding low-grade tumours, VisioCyt test sensitivity was 77% vs 26.3% for the uro-pathologists. Conclusion In comparison to routine cytology, the results of the first phase of the VISIOCYT1 trial show very clear progress in terms of sensitivity, which is particularly visible and interesting for low-grade tumours. If the validation cohort confirms these results, it could lead to the VisioCyt test being considered as a very useful aid for pathologists. Moreover, as this test is in fact software based on AI, it should become more and more efficient as more data are collected.

Mots clés

Fichier non déposé

Dates et versions

hal-03345229 , version 1 (15-09-2021)

Identifiants

Citer

Thierry Lebret, Geraldine Pignot, Marc Colombel, Laurent Guy, Xavier Rebillard, et al.. Artificial intelligence to improve cytology performances in bladder carcinoma detection: results of the VisioCyt test. BJU International, In press, ⟨10.1111/bju.15382⟩. ⟨hal-03345229⟩
62 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More