Computer-aided detection-assisted colonoscopy: classification and relevance of false positives - 21/09/20

Doi : 10.1016/j.gie.2020.06.021

Cesare Hassan, MD ^1,^{^{∗
Drs Hassan and Badalamenti contributed equally to this article.}}, Matteo Badalamenti, MD ^2,^{^{∗
Drs Hassan and Badalamenti contributed equally to this article.}}, Roberta Maselli, MD, PhD ², Loredana Correale ², Andrea Iannone, MD ³, Franco Radaelli, MD ⁴, Emanuele Rondonotti, MD ⁴, Elisa Ferrara, MD ², Marco Spadaccini, MD ^2,⁵, Asma Alkandari, MD ⁶, Alessandro Fugazza, MD ², Andrea Anderloni, PhD ², Piera Alessia Galtieri, MD ², Gaia Pellegatta, MD ², Silvia Carrara, MD ², Milena Di Leo, MD ², Vincenzo Craviotto, MD ^2,⁵, Laura Lamonaca, MD ^2,⁵, Roberto Lorenzetti, MD ¹, Alida Andrealli, MD ⁴, Giulio Antonelli, MD ¹, Michael Wallace, MD ⁷, Prateek Sharma, MD ⁸, Thomas Rösch, MD ⁹, Alessandro Repici, MD ^2,^5,^⁎
¹ Digestive Endoscopy, Nuovo Regina Margherita Hospital, Rome
² Humanitas Clinical and Research Center IRCCS, Digestive Endoscopy Unit, Division of Gastroenterology, Rozzano, Milan
³ Section of Gastroenterology, Department of Emergency and Organ Transplantation, University of “Aldo Moro” of Bari, Bari
⁴ Gastroenterology Department, Valduce Hospital, Como
⁵ Humanitas University, Department of Biomedical Sciences, Pieve Emanuele, Milan, Italy
⁶ Thanyan Alghanim Center for Gastroenterology and Hepatology, Alamiri Hospital, Kuwait City, Kuwait
⁷ Mayo Clinic, Jacksonville, Florida
⁸ Kansas City Veterans Affairs Hospital, Kansas City, Kansas, USA
⁹ Department of Interdisciplinary Endoscopy, University Hospital Hamburg-Eppendorf, Hamburg, Germany

^∗Reprint requests: Prof. Alessandro Repici, MD, Digestive Endoscopy Unit, IRCCS Istituto Clinico Humanitas, Via Manzoni 56, 20089 Rozzano Milano, Italy.Digestive Endoscopy UnitIRCCS Istituto Clinico HumanitasVia Manzoni 56Rozzano Milano20089Italy

Abstract

Background and Aims

False positive (FP) results by computer-aided detection (CADe) hamper the efficiency of colonoscopy by extending examination time. Our aim was to develop a classification of the causes and clinical relevance of CADe FPs, and to assess the relative distribution of FPs in a real-life setting.

Methods

In a post-hoc analysis of a randomized trial comparing colonoscopy with and without CADe (NCT: 04079478), we extracted 40 CADe colonoscopy videos. Using a modified Delphi process, 4 expert endoscopists identified the main domains for the reasons and clinical relevance of FPs. Then, 2 expert endoscopists manually examined each FP and classified it according to the proposed domains. The analysis was limited to the withdrawal phase.

Results

The 2 main domains for the causes of CADe FPs were identified as artifacts due to either the mucosal wall or bowel content, and clinical relevance was defined as the time spent on FPs and the FP rate per minute. The mean number of FPs per colonoscopy was 27.3 ± 13.1, of which 24 ± 12 (88%) and 3.2 ± 2.6 (12%) were due to artifacts in the bowel wall and bowel content, respectively. Of the 27.3 FPs per colonoscopy, 1.6 (5.7%) required additional exploration time of 4.8 ± 6.2 seconds per FP (ie, 0.7% of the mean withdrawal time). In detail, 15 (24.2%), 33 (53.2%), and 14 (22.6%) FPs were classified as being of mild, moderate, or severe clinical relevance. The rate of FPs per minute of withdrawal time was 2.4 ± 1.2, and was higher for FPs due to artifacts from the bowel wall than for those from bowel content (2.4 ± 0.6 vs 0.3 ± 0.2, P < .001).

Conclusions

FPs by CADe are primarily due to artifacts from the bowel wall. Despite a high frequency, FPs result in a negligible 1% increase in the total withdrawal time because most of them are immediately discarded by the endoscopist.

Le texte complet de cet article est disponible en PDF.

Abbreviations : CADe, CI, CRF, FP

Plan

Introduction

Methods

Study setting

Classification of FPs according to clinical relevance

Frequency of FPs

Results

Classification of FPs

Frequency of FPs according to the cause

Clinical relevance of FPs

FP time rate

Discussion

DISCLOSURE: Dr Hassan, consultant for Medtronic; Dr Repici, consultant for Medtronic; Dr Sharma, consultant for Olympus, Boston Scientific, Bausch, Medtronic, Fujifilm; grant support from Olympus, Medtronic, Fujifilm, US Endoscopy, Ironwood, Erbe, Docbot, Cosmo Pharmaceuticals; Dr Wallace, research grants from Boston Scientific, Olympus, Medtronic, Ninepoint Medical, Cosmo/Aries Pharmaceuticals; stock options from Virgo Inc; consultant for GI Supply, Endokey, Endostart, Boston Scientific, Microtek; general payments/minor food and beverage from Synergy Pharmaceuticals, Boston Scientific, and Cook Medical. All authors benefited from loan of equipment from Medtronic.

See CME section, p. 960.

Export

Vol 92 - N° 4

P. 900 - octobre 2020 Retour au numéro

Article précédent

Computer-aided diagnosis for characterization of colorectal lesions: comprehensive software that includes differentiation of serrated lesions
Leonardo Zorron Cheng Tao Pu, Gabriel Maicas, Yu Tian, Takeshi Yamamura, Masanao Nakamura, Hiroto Suzuki, Gurfarmaan Singh, Khizar Rana, Yoshiki Hirooka, Alastair D. Burt, Mitsuhiro Fujishiro, Gustavo Carneiro, Rajvinder Singh

| Article suivant

Cost savings in colonoscopy with artificial intelligence-aided polyp diagnosis: an add-on analysis of a clinical trial (with video)
Yuichi Mori, Shin-ei Kudo, James E. East, Amit Rastogi, Michael Bretthauer, Masashi Misawa, Masau Sekiguchi, Takahisa Matsuda, Yutaka Saito, Hiroaki Ikematsu, Kinichi Hotta, Kazuo Ohtsuka, Toyoki Kudo, Kensaku Mori

Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.

Déjà abonné à cette revue ?

connectez-vous ou créez un compte

Computer-aided detection-assisted colonoscopy: classification and relevance of false positives - 21/09/20

Abstract

Background and Aims

Methods

Results

Conclusions

Plan

Export citations

Fichier

Contenu

Accès rapides

Mon compte

Aide & support

Plateformes Elsevier Masson

Déclaration CNIL