Endoscopy 2022; 54(S 01): S25
DOI: 10.1055/s-0042-1744607
Abstracts | ESGE Days 2022
ESGE Days 2022 Oral presentations
13:30–14:30 Thursday, 28 April 2022 Club A. Esophageal early cancer: Is ESD ready to take on the challenge?

EFFICACY OF A COMPUTER AIDED DETECTION (CADE) SYSTEM IN A FIT-BASED ORGANIZED COLORECTAL CANCER SCREENING PROGRAM: A RANDOMIZED CONTROLLED TRIAL

Authors

  • D. Di Paolo

    1   Valduce Hospital, Gastroenterology Unit, Como, Italy
    2   Foundation IRCCS Ca’ Granda Ospedale Maggiore Policlinico, Department of Gastroenterology and Hepatology, Milan, Italy

  • E. Rondonotti

    1   Valduce Hospital, Gastroenterology Unit, Como, Italy

  • S. Paggi

    1   Valduce Hospital, Gastroenterology Unit, Como, Italy

  • E. Rosa Rizzotto

    3   St. Antonio Hospital, Azienda Ospedaliera Universitaria, Padova, Italy

  • C. Alvisi

    4   ASST Pavia, USD Endoscopia Digestiva, Pavia, Italy

  • E. Buscarini

    5   Azienda Ospedaliera “Ospedale Maggiore”, Gastroenterology Unit, Crema, Italy

  • M. Spadaccini

    6   Humanitas University, Department of Biomedical Sciences, Pieve Emanuele, Italy
    7   Humanitas Research Hospital – IRCCS, Department of Gastroenterology, Rozzano, Italy

  • G. Tamanini

    1   Valduce Hospital, Gastroenterology Unit, Como, Italy

  • A. Amato

    1   Valduce Hospital, Gastroenterology Unit, Como, Italy

  • G. Scardino

    1   Valduce Hospital, Gastroenterology Unit, Como, Italy

  • G. Mandelli

    1   Valduce Hospital, Gastroenterology Unit, Como, Italy

  • N. Lenoci

    1   Valduce Hospital, Gastroenterology Unit, Como, Italy

  • N. Terreni

    1   Valduce Hospital, Gastroenterology Unit, Como, Italy

  • S. Romeo

    8   Azienda Ospedaliera “Ospedale Maggiore”, Crema, Italy

  • S. Alicante

    5   Azienda Ospedaliera “Ospedale Maggiore”, Gastroenterology Unit, Crema, Italy

  • F. Ancona

    3   St. Antonio Hospital, Azienda Ospedaliera Universitaria, Padova, Italy

  • E. Guido

    3   St. Antonio Hospital, Azienda Ospedaliera Universitaria, Padova, Italy

  • V. Marzo

    4   ASST Pavia, USD Endoscopia Digestiva, Pavia, Italy

  • F. Chicco

    4   ASST Pavia, USD Endoscopia Digestiva, Pavia, Italy

  • S. Agazzi

    4   ASST Pavia, USD Endoscopia Digestiva, Pavia, Italy

  • A. Repici

    6   Humanitas University, Department of Biomedical Sciences, Pieve Emanuele, Italy
    7   Humanitas Research Hospital – IRCCS, Department of Gastroenterology, Rozzano, Italy

  • L. Ambrosini

    9   Valduce Hospital, Pathology Department, Como, Italy

  • E. Filippi

    9   Valduce Hospital, Pathology Department, Como, Italy

  • R. Sassatelli

    10   IRCCS-Arcispedale Santa Maria Nuova, AUSL Reggio Emilia, Reggio Emilia, Italy

  • G. Sereni

    10   IRCCS-Arcispedale Santa Maria Nuova, AUSL Reggio Emilia, Reggio Emilia, Italy

  • K. Khalaf

    7   Humanitas Research Hospital – IRCCS, Department of Gastroenterology, Rozzano, Italy

  • C. Hassan

    6   Humanitas University, Department of Biomedical Sciences, Pieve Emanuele, Italy
    7   Humanitas Research Hospital – IRCCS, Department of Gastroenterology, Rozzano, Italy

  • F. Radaelli

    1   Valduce Hospital, Gastroenterology Unit, Como, Italy
Weitere Informationen
Auch verfügbar auf
 

Aims Computer Aided Detection (CADe) increases adenoma detection in primary screening colonoscopy. The potential benefit of CADe in FIT-based screening programs, where the prevalence of neoplasia is high, has never been evaluated.

Methods In a multicentre, randomized trial, 50-74 years old subjects undergoing screening colonoscopy, following a positive FIT, were randomized (1:1) to receive high-definition white light (HD-WL) colonoscopy with (study arm) or without (control arm) a real-time deep-learning CADe (CADEYETM Fujifilm Co., Tokyo, Japan). Main outcome measures were ADR (primary outcome), number of adenomas per colonoscopy (APC) and detection rate of advanced adenomas (Advanced-ADR). Subgroup analysis on ADR according to baseline endoscopists ’ADR (group 1:<40%, group 2: 41-45%, group 3>46%) was also performed.

Results Eight hundred subjects (61.2±7.3 years old; 409 men) were included. Of them, 405 underwent CADe-assisted and 395 HD-WL colonoscopy, respectively. ADR and APC were significantly higher in the study arm than in the control one: ADR: 53.6% vs. 45.3% (RR: 1.180, 95%CI: 1.026-1.361; p=0.019); APC: 1.126+1.540 vs. 0.904+1.320 (p=0.028). No significant difference in advanced-ADR (18.5% vs. 15.9%; p=0.386) was found. An absolute increase in ADR was observed in all endoscopists' groups regardless of baseline ADR.

Conclusions Incorporating the use of a CADe system significantly increases ADR and APC in the framework of a FIT-based CRC screening program. The impact of artificial intelligence appears to be consistent regardless of the endoscopist baseline ADR.



Publikationsverlauf

Artikel online veröffentlicht:
14. April 2022

© 2022. European Society of Gastrointestinal Endoscopy. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany