Staff View: An embedded recurrent neural network-based model for endoscopic semantic segmentation

An embedded recurrent neural network-based model for endoscopic semantic segmentation

Detecting cancers at their early stage would decrease mortality rate. For instance, detecting all polyps during colonoscopy would increase the chances of a better prognoses. However, endoscopists are facing difficulties due to the heavy workload of analyzing endoscopic images. Hence, assisting endos...

Full description

Saved in:

Bibliographic Details
Main Authors:	Haithami, M., Ahmed, A., Liao, I.Y., Jalab, Hamid A.
Format:	Conference or Workshop Item
Published:	2021
Subjects:	QA75 Electronic computers. Computer science
Online Access:	http://eprints.um.edu.my/35506/ https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108846020&partnerID=40&md5=71fc160223491a1e755642d427493881
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.um.eprints.35506
record_format	eprints
spelling	my.um.eprints.355062023-10-11T04:24:37Z http://eprints.um.edu.my/35506/ An embedded recurrent neural network-based model for endoscopic semantic segmentation Haithami, M. Ahmed, A. Liao, I.Y. Jalab, Hamid A. QA75 Electronic computers. Computer science Detecting cancers at their early stage would decrease mortality rate. For instance, detecting all polyps during colonoscopy would increase the chances of a better prognoses. However, endoscopists are facing difficulties due to the heavy workload of analyzing endoscopic images. Hence, assisting endoscopist while screening would decrease polyp miss rate. In this study, we propose a new deep learning segmentation model to segment polyps found in endoscopic images extracted during Colonoscopy screening. The propose model modifies SegNet architecture to embed Gated recurrent units (GRU) units within the convolution layers to collect contextual information. Therefore, both global and local information are extracted and propagated through the entire layers. This has led to better segmentation performance compared to that of using state of the art SegNet. Four experiments were conducted and the proposed model achieved a better intersection over union “IoU” by 1.36, 1.71, and 1.47 on validation sets and 0.24 on a test set, compared to the state of the art SegNet. © 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). 2021 Conference or Workshop Item PeerReviewed Haithami, M. and Ahmed, A. and Liao, I.Y. and Jalab, Hamid A. (2021) An embedded recurrent neural network-based model for endoscopic semantic segmentation. In: 3rd International Workshop and Challenge on Computer Vision in Endoscopy, EndoCV 2021, 13 April 2021, Nice. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108846020&partnerID=40&md5=71fc160223491a1e755642d427493881
institution	Universiti Malaya
building	UM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Malaya
content_source	UM Research Repository
url_provider	http://eprints.um.edu.my/
topic	QA75 Electronic computers. Computer science
spellingShingle	QA75 Electronic computers. Computer science Haithami, M. Ahmed, A. Liao, I.Y. Jalab, Hamid A. An embedded recurrent neural network-based model for endoscopic semantic segmentation
description	Detecting cancers at their early stage would decrease mortality rate. For instance, detecting all polyps during colonoscopy would increase the chances of a better prognoses. However, endoscopists are facing difficulties due to the heavy workload of analyzing endoscopic images. Hence, assisting endoscopist while screening would decrease polyp miss rate. In this study, we propose a new deep learning segmentation model to segment polyps found in endoscopic images extracted during Colonoscopy screening. The propose model modifies SegNet architecture to embed Gated recurrent units (GRU) units within the convolution layers to collect contextual information. Therefore, both global and local information are extracted and propagated through the entire layers. This has led to better segmentation performance compared to that of using state of the art SegNet. Four experiments were conducted and the proposed model achieved a better intersection over union “IoU” by 1.36, 1.71, and 1.47 on validation sets and 0.24 on a test set, compared to the state of the art SegNet. © 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
format	Conference or Workshop Item
author	Haithami, M. Ahmed, A. Liao, I.Y. Jalab, Hamid A.
author_facet	Haithami, M. Ahmed, A. Liao, I.Y. Jalab, Hamid A.
author_sort	Haithami, M.
title	An embedded recurrent neural network-based model for endoscopic semantic segmentation
title_short	An embedded recurrent neural network-based model for endoscopic semantic segmentation
title_full	An embedded recurrent neural network-based model for endoscopic semantic segmentation
title_fullStr	An embedded recurrent neural network-based model for endoscopic semantic segmentation
title_full_unstemmed	An embedded recurrent neural network-based model for endoscopic semantic segmentation
title_sort	embedded recurrent neural network-based model for endoscopic semantic segmentation
publishDate	2021
url	http://eprints.um.edu.my/35506/ https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108846020&partnerID=40&md5=71fc160223491a1e755642d427493881
_version_	1781704476630974464
score	13.211869

An embedded recurrent neural network-based model for endoscopic semantic segmentation

Similar Items