The Argos project: The development of a computer‐aided detection system to improve detection of Barrett's neoplasia on white light endoscopy. Issue 4 (1st May 2019)

• Record Type: Journal Article
• Authors: de Groof, Jeroen; van der Sommen, Fons; van der Putten, Joost; Struyvenberg, Maarten R; Zinger, Sveta; Curvers, Wouter L; Pech, Oliver; Meining, Alexander; Neuhaus, Horst; Bisschops, Raf; Schoon, Erik J; de With, Peter H; Bergman, Jacques J
• Is Part Of: United European Gastroenterology journal. Volume 7:Issue 4(2019)
• Page Start: 538
• Page End: 547
• Publication Date: 2019-05-01
• Subjects: Barrett's oesophagus -- endoscopy -- computer-aided detection -- Barrett's neoplasia -- artificial intelligence; Gastroenterology -- Periodicals; Periodicals; 616.33005
• DOI: 10.1177/2050640619837443
• Languages: English
• ISSNs: 2050-6406

Abstract

Abstract : Background: Computer‐aided detection (CAD) systems might assist endoscopists in the recognition of Barrett's neoplasia. Aim: To develop a CAD system using endoscopic images of Barrett's neoplasia. Methods: White light endoscopy (WLE) overview images of 40 neoplastic Barrett's lesions and 20 non‐dysplastic Barret's oesophagus (NDBO) patients were prospectively collected. Experts delineated all neoplastic images. The overlap area of at least four delineations was labelled as the 'sweet spot'. The area with at least one delineation was labelled as the 'soft spot'. The CAD system was trained on colour and texture features. Positive features were taken from the sweet spot and negative features from NDBO images. Performance was evaluated using leave‐one‐out cross‐validation. Outcome parameters were diagnostic accuracy of the CAD system per image, and localization of the expert soft spot by CAD delineation (localization score) and its indication of preferred biopsy location (red‐flag indication score). Results: Accuracy, sensitivity and specificity for detection were 92, 95 and 85%, respectively. The system localized and red‐flagged the soft spot in 100 and 90%, respectively. Conclusion: This uniquely trained and validated CAD system detected and localized early Barrett's neoplasia on WLE images with high accuracy. This is an important step towards real‐time automated detection of Barrett's neoplasia.