AuthorsK. Pogorelov, O. Ostroukhova, A. Petlund, P. Halvorsen, H. Espeland, T. Kupka, T. de Lange, C. Griwodz and M. Riegler
TitleAutomatic Detection of Angiectasia: Evaluation of Deep Learning and Handcrafted Approaches
AfilliationCommunication Systems
Project(s)Efficient EONS: Execution of Large Workloads on Elastic Heterogeneous Resources
StatusAccepted
Publication TypeProceedings, refereed
Year of Publication2018
Conference Name IEEE Conference on Biomedical and Health Informatics (BHI) 2018
Abstract

Angiectasia, formerly called angiodysplasia, is one of the most frequent vascular lesions and often the cause of gastrointestinal bleedings. Medical specialists assessing videos of examinations reach a detection performance of 16% for the detection of bleeding to 69% for the detection of angiectasia. In this paper, we present several machine-learning-based approaches for angiectasia detection in wireless video capsule endoscopy images. The most promising results for pixel-wise localization and frame-wise detection are obtained by the proposed deep learning approach using generative adversarial networks (GANs) with a sensitivity of 88% and specificity of 99.9% for pixel-wise localization and a sensitivity of 98% and a specificity of 100% for frame-wise detection, which fits the requirements for automatic angiectasia detection in real clinical settings.

Citation Key25795