DEEP ENCODER-DECODER NETWORKS FOR ARTEFACTS SEGMENTATION IN ENDOSCOPY IMAGES

Guo, Yun Bo, Zheng, Qingshuo and Matuszewski, Bogdan orcid iconORCID: 0000-0001-7195-2509 (2020) DEEP ENCODER-DECODER NETWORKS FOR ARTEFACTS SEGMENTATION IN ENDOSCOPY IMAGES. In: 2nd International Workshop and Challenge on Computer Vision in Endoscopy (EndoCV2020), 3rd April 2020, Iowa, USA.

[thumbnail of Version of Record]
Preview
PDF (Version of Record) - Published Version
Available under License Creative Commons Attribution.

593kB

Official URL: http://ceur-ws.org/Vol-2595/endoCV2020_paper_id_12...

Abstract

Automated analysis of endoscopic images is becoming increasingly significant for an early detection of numerous cancers and minimally invasive surgical procedures. The paper briefly describes the methodology adopted for the 2020 Endoscopy Artefact Detection and Segmentation (EAD2020) challenge1. A number of novel variants of the DeepLab V3+
encoder-decoder architecture have been investigated, implemented and tested for the segmentation sub-challenge. Modifications were introduced to improve: selection of image futures, segmentation of small objects, and use of the encoder output information. The proposed methods achieved competitive segmentation score results on both release-I and releaseII test datasets. For the detection sub-challenge three off-theshelf deep detection networks have been optimised and evaluated on the EAD data.


Repository Staff Only: item control page