Endoscopic Artefact Detection (EAD) is a core challenge in facilitating diagnosis and treatment of diseases in hollow organs. Precise detection of specific artefacts like pixel saturations, motion blur, specular reflections, bubbles and debris is essential for high-quality frame restoration and is crucial for realising reliable computer-assisted tools for improved patient care.
EAD2019 challenge is sub-divided into three tasks:
1. Multi-class artefact detection: Localization of bounding boxes and class labels for 6 artefact classes for given frames.
2. Region segmentation: Precise boundary delineation of detected artefacts.
3. Detection generalization: Detection performance independent of specific data type and source.
This challenge has been launched through grand-challenge.org (https://ead2019.grand-challenge.org/EAD2019/) and accepted at IEEE International Symposium on Biomedical Imaging (ISBI’19, https://biomedicalimaging.org/2019/challenges/).
EAD2019 – Home
Endoscopic Artefact Detection (EAD) is a core problem and needed for realising robust computer-assisted tools. The EAD challenge has 3 tasks: 1) Multi-class artefact detection, 2) Region segmentation, 3) Detection generalisation.
The challenge workshop will be held in Venice, Italy on 8th April, 2019. This workshop will be kicked-off with 2 keynote speeches by high-impact researchers in the field and presentations by top participating teams. This workshop also aims at publishing a joint high-impact peer reviewed journal paper.
With this challenge, we aim to establish a first large and comprehensive database in endoscopy utilizing data obtained from 6 different data centres. Nearly, 3000 image frames with ground-truth annotations for this purpose will be released. Regarding data releases and other information please look-up at the EAD2019 challenge website.