Patch-based deep learning approaches for artefact detection of endoscopic images

Gao, Xiaohong W. ORCID: and Qian, Yu (2019) Patch-based deep learning approaches for artefact detection of endoscopic images. Proceedings of the EAD 2019 Workshop on Endoscopic Artefact Detection Challenge. In: Endoscopic artefact detection challenge 2019 (EAD2019), 08 Apr 2019, Venice, Italy. . ISSN 1613-0073 [Conference or Workshop Item]

PDF - Published version (with publisher's formatting)
Download (13MB) | Preview
[img] PDF - Final accepted version (with author's formatting)
Download (667kB)


This paper constitutes the work in EAD2019 competition. In this competition, for segmentation (task 2) of five types of artefact, patch-based fully convolutional neural network (FCN) allied to support vector machine (SVM) classifier is implemented, aiming to contend with smaller data sets (i.e., hundreds) and the characteristics of endoscopic images with limited regions capturing artefact (e.g. bubbles, specularity). In comparison with conventional CNN and other state of the art approaches (e.g. DeepLab) while processed on whole images, this patch-based FCN appears to achieve the best.

Item Type: Conference or Workshop Item (Speech)
Additional Information: Paper published in Proceedings of the 2019 Challenge on Endoscopy Artefacts Detection (EAD2019), co-located with the 16th International Symposium on Biomedical Imaging (ISBI) Edited by: Sharib Ali, Felix Zhou. CEUR Workshop Proceedings vol. 2366Published on CEUR-WS: 25-May-2019,
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 26886
Notes on copyright: Copyright © The authors. Copying permitted for private and academic purposes.
Useful Links:
Depositing User: Xiaohong Gao
Date Deposited: 26 Jun 2019 21:08
Last Modified: 26 Jun 2021 20:45

Actions (login required)

View Item View Item


Activity Overview

Additional statistics are available via IRStats2.