Endoscopy 2016; 48(07): 617-624
DOI: 10.1055/s-0042-105284
Original article
© Georg Thieme Verlag KG Stuttgart · New York

Computer-aided detection of early neoplastic lesions in Barrett’s esophagus

Fons van der Sommen
1  Department of Electrical Engineering, Eindhoven University of Technology, the Netherlands
,
Svitlana Zinger
1  Department of Electrical Engineering, Eindhoven University of Technology, the Netherlands
,
Wouter L. Curvers
2  Department of Gastroenterology, Catharina Hospital, Eindhoven, the Netherlands
,
Raf Bisschops
3  Department of Gastroenterology, University Hospitals Leuven, KU Leuven, Leuven, Belgium
,
Oliver Pech
4  Gastroenterology and Interventional Endoscopy, St. John of God Hospital, Regensburg, Germany
,
Bas L. A. M. Weusten
5  Department of Gastroenterology, St. Antonius Hospital, Nieuwegein, the Netherlands
,
Jacques J. G. H. M. Bergman
6  Department of Gastroenterology, Amsterdam Medical Center, Amsterdam, the Netherlands
,
Peter H. N. de With
1  Department of Electrical Engineering, Eindhoven University of Technology, the Netherlands
,
Erik J. Schoon
2  Department of Gastroenterology, Catharina Hospital, Eindhoven, the Netherlands
› Author Affiliations
Further Information

Publication History

submitted 09 July 2015

accepted after revision 23 February 2016

Publication Date:
21 April 2016 (online)

Background and study aims: Early neoplasia in Barrett’s esophagus is difficult to detect and often overlooked during Barrett’s surveillance. An automatic detection system could be beneficial, by assisting endoscopists with detection of early neoplastic lesions. The aim of this study was to assess the feasibility of a computer system to detect early neoplasia in Barrett’s esophagus.

Patients and methods: Based on 100 images from 44 patients with Barrett’s esophagus, a computer algorithm, which employed specific texture, color filters, and machine learning, was developed for the detection of early neoplastic lesions in Barrett’s esophagus. The evaluation by one endoscopist, who extensively imaged and endoscopically removed all early neoplastic lesions and was not blinded to the histological outcome, was considered the gold standard. For external validation, four international experts in Barrett’s neoplasia, who were blinded to the pathology results, reviewed all images.

Results: The system identified early neoplastic lesions on a per-image analysis with a sensitivity and specificity of 0.83. At the patient level, the system achieved a sensitivity and specificity of 0.86 and 0.87, respectively. A trade-off between the two performance metrics could be made by varying the percentage of training samples that showed neoplastic tissue.

Conclusion: The automated computer algorithm developed in this study was able to identify early neoplastic lesions with reasonable accuracy, suggesting that automated detection of early neoplasia in Barrett’s esophagus is feasible. Further research is required to improve the accuracy of the system and prepare it for real-time operation, before it can be applied in clinical practice.