Towards a robust and compact deep learning system for primary detection of early Barrett's neoplasia: Initial image-based results of training on a multi-center retrospectively collected data set.
Kiki N FockensJelmer B JukemaTim BoersMartijn R JongJoost A van der PuttenR Roos E PouwBas L A M WeustenLorenza Alvarez HerreroMartin H M G HoubenWouter Bastiaan NagengastJessie WesterhofAlaa AlkhalafRosalie MallantKrish RagunathStefan SeewaldPeter ElbeMaximilien BarretJacobo Ortiz Fernández-SordoOliver PechTorsten BeynaFons van der SommenPeter H de WithA Jeroen de GroofJacques J BergmanPublished in: United European gastroenterology journal (2023)
This study describes the first steps towards the establishment of an unprecedented data infrastructure for using machine learning to improve the endoscopic detection of Barrett's neoplasia. The CADe system detected neoplasia reliably and outperformed a large group of endoscopists in terms of sensitivity.