CC BY-NC-ND 4.0 · Endosc Int Open 2020; 08(03): E415-E420
DOI: 10.1055/a-1035-9088
Original article
Owner and Copyright © Georg Thieme Verlag KG 2020

CAD-CAP: a 25,000-image database serving the development of artificial intelligence for capsule endoscopy

Romain Leenhardt
 1  Sorbonne University, Endoscopy Unit
,
Cynthia Li
 2  Drexel University, College of Arts & Sciences, Philadelphia, Pennsylvania, United States
,
Jean-Philippe Le Mouel
 3  Gastroenterology, Amiens University Hospital, Université de Picardie Jules Verne, Amiens, France
,
Gabriel Rahmi
 4  Georges Pompidou European Hospital, APHP, Department of Gastroenterology and Endoscopy, Paris, France
,
Jean Christophe Saurin
 5  Department of Endoscopy and Gastroenterology, Pavillon L, Hôpital Edouard Herriot, Lyon, France
,
Franck Cholet
 6  Digestive Endoscopy Unit, University Hospital, Brest, France
,
Arnaud Boureille
 7  Department of Hepato-Gastroenterology, Institut des Maladies de l'Appareil Digestif, Nantes, France
,
Xavier Amiot
 8  Tenon Hospital, Gastroenterology Department, Paris, France
,
Michel Delvaux
 9  CHU Strasbourg, Gastroenterology Department, Strasbourg, France
,
Clotilde Duburque
10  Lomme Hospital, Gastroenterology Department, Lomme, France
,
Chloé Leandri
11  Cochin Hospital Gastroenterology Department, Paris, France
,
Romain Gérard
12  CHRU Lille, Gastroenterology Department, Lille, France
,
Stéphane Lecleire
13  CHU Rouen, Gastroenterology Department, Rouen, France
,
Farida Mesli
14  CHU Henri Mondor, Gastroenterology Department, Creteil, France
,
Isabelle Nion-Larmurier
 1  Sorbonne University, Endoscopy Unit
,
Olivier Romain
15  ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise Cedex, France
,
Sylvie Sacher-Huvelin
 7  Department of Hepato-Gastroenterology, Institut des Maladies de l'Appareil Digestif, Nantes, France
,
Camille Simon-Shane
15  ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise Cedex, France
,
Geoffroy Vanbiervliet
16  CHU Nice, Gastroenterology and Endoscopy Unit, Nice, France
,
Philippe Marteau
 1  Sorbonne University, Endoscopy Unit
,
Aymeric Histace
15  ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise Cedex, France
,
Xavier Dray
 1  Sorbonne University, Endoscopy Unit
15  ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise Cedex, France
› Author Affiliations
Further Information

Publication History

submitted 05 April 2019

accepted after revision 16 September 2019

Publication Date:
21 February 2020 (online)

Abstract

Background and study aims Capsule endoscopy (CE) is the preferred method for small bowel (SB) exploration. With a mean number of 50,000 SB frames per video, SBCE reading is time-consuming and tedious (30 to 60 minutes per video). We describe a large, multicenter database named CAD-CAP (Computer-Assisted Diagnosis for CAPsule Endoscopy, CAD-CAP). This database aims to serve the development of CAD tools for CE reading.

Materials and methods Twelve French endoscopy centers were involved. All available third-generation SB-CE videos (Pillcam, Medtronic) were retrospectively selected from these centers and deidentified. Any pathological frame was extracted and included in the database. Manual segmentation of findings within these frames was performed by two pre-med students trained and supervised by an expert reader. All frames were then classified by type and clinical relevance by a panel of three expert readers. An automated extraction process was also developed to create a dataset of normal, proofread, control images from normal, complete, SB-CE videos.

Results Four-thousand-one-hundred-and-seventy-four SB-CE were included. Of them, 1,480 videos (35 %) containing at least one pathological finding were selected. Findings from 5,184 frames (with their short video sequences) were extracted and delimited: 718 frames with fresh blood, 3,097 frames with vascular lesions, and 1,369 frames with inflammatory and ulcerative lesions. Twenty-thousand normal frames were extracted from 206 SB-CE normal videos. CAD-CAP has already been used for development of automated tools for angiectasia detection and also for two international challenges on medical computerized analysis.