Graph Neural Network and Superpixel Based Brain Tissue Segmentation

Convolutional neural networks (CNNs) are usually used as a backbone to design methods in biomedical image segmentation. However, the limitation of receptive field and large number of parameters limit the performance of these methods. In this paper, we propose a graph neural network (GNN) based metho...

Full description

Saved in:
Bibliographic Details
Main Authors: Wu, Chong, Feng, Zhenan, Zhang, Houwang, Yan, Hong
Format: Conference Proceeding
Language:English
Subjects:
Brain tissue segmentation
Graph neural network
Interaction mechanism
Superpixel
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 08
container_issue
container_start_page 01
container_title
container_volume
creator Wu, Chong
Feng, Zhenan
Zhang, Houwang
Yan, Hong
description Convolutional neural networks (CNNs) are usually used as a backbone to design methods in biomedical image segmentation. However, the limitation of receptive field and large number of parameters limit the performance of these methods. In this paper, we propose a graph neural network (GNN) based method named GNN-SEG for the segmentation of brain tissues. Different to conventional CNN based methods, GNN-SEG takes superpixels as basic processing units and uses GNNs to learn the structure of brain tissues. Besides, inspired by the interaction mechanism in biological vision systems, we propose two kinds of interaction modules for feature enhancement and integration. In the experiments, we compared GNN-SEG with state-of-the-art CNN based methods on four datasets of brain magnetic resonance images. The experimental results show the superiority of GNN-SEG.
doi_str_mv 10.1109/IJCNN55064.2022.9892580
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_9892580</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9892580</ieee_id><sourcerecordid>9892580</sourcerecordid><originalsourceid>FETCH-LOGICAL-i203t-e1f23464157854ad4bad417f4584e49f01a766e49c7e72c6ead79c744dd95d8a3</originalsourceid><addsrcrecordid>eNotj8tOwzAUBQ0SEm3hC1jgH0jw4_q1pBGUoiosWtaVqW_A0KaRnQj4eyLRxdHMaqRDyC1nJefM3S2fq7pWimkoBROidNYJZdkZmXIjLLfacDgnE8E1LwCYuSTTnD8ZE9I5OSHVIvnug9Y4JL8f0X8f0xf1baDrocPUxR_c07nPGOg8-djSTcx5QLrG9wO2ve_jsb0iF43fZ7w-cUZeHx821VOxelksq_tVEQWTfYG8ERI0cGWsAh_gbRw3DSgLCK5h3ButR9sZNGKn0QczOkAITgXr5Yzc_HcjIm67FA8-_W5Ph-UfVvRK-A</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Graph Neural Network and Superpixel Based Brain Tissue Segmentation</title><source>IEEE Xplore All Conference Series</source><creator>Wu, Chong ; Feng, Zhenan ; Zhang, Houwang ; Yan, Hong</creator><creatorcontrib>Wu, Chong ; Feng, Zhenan ; Zhang, Houwang ; Yan, Hong</creatorcontrib><description>Convolutional neural networks (CNNs) are usually used as a backbone to design methods in biomedical image segmentation. However, the limitation of receptive field and large number of parameters limit the performance of these methods. In this paper, we propose a graph neural network (GNN) based method named GNN-SEG for the segmentation of brain tissues. Different to conventional CNN based methods, GNN-SEG takes superpixels as basic processing units and uses GNNs to learn the structure of brain tissues. Besides, inspired by the interaction mechanism in biological vision systems, we propose two kinds of interaction modules for feature enhancement and integration. In the experiments, we compared GNN-SEG with state-of-the-art CNN based methods on four datasets of brain magnetic resonance images. The experimental results show the superiority of GNN-SEG.</description><identifier>EISSN: 2161-4407</identifier><identifier>EISBN: 1728186714</identifier><identifier>EISBN: 9781728186719</identifier><identifier>DOI: 10.1109/IJCNN55064.2022.9892580</identifier><language>eng</language><publisher>IEEE</publisher><subject>Brain tissue segmentation ; Graph neural network ; Interaction mechanism ; Superpixel</subject><ispartof>2022 International Joint Conference on Neural Networks (IJCNN), 2022, p.01-08</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9892580$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,23930,23931,25140,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9892580$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Wu, Chong</creatorcontrib><creatorcontrib>Feng, Zhenan</creatorcontrib><creatorcontrib>Zhang, Houwang</creatorcontrib><creatorcontrib>Yan, Hong</creatorcontrib><title>Graph Neural Network and Superpixel Based Brain Tissue Segmentation</title><title>2022 International Joint Conference on Neural Networks (IJCNN)</title><addtitle>IJCNN</addtitle><description>Convolutional neural networks (CNNs) are usually used as a backbone to design methods in biomedical image segmentation. However, the limitation of receptive field and large number of parameters limit the performance of these methods. In this paper, we propose a graph neural network (GNN) based method named GNN-SEG for the segmentation of brain tissues. Different to conventional CNN based methods, GNN-SEG takes superpixels as basic processing units and uses GNNs to learn the structure of brain tissues. Besides, inspired by the interaction mechanism in biological vision systems, we propose two kinds of interaction modules for feature enhancement and integration. In the experiments, we compared GNN-SEG with state-of-the-art CNN based methods on four datasets of brain magnetic resonance images. The experimental results show the superiority of GNN-SEG.</description><subject>Brain tissue segmentation</subject><subject>Graph neural network</subject><subject>Interaction mechanism</subject><subject>Superpixel</subject><issn>2161-4407</issn><isbn>1728186714</isbn><isbn>9781728186719</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2022</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj8tOwzAUBQ0SEm3hC1jgH0jw4_q1pBGUoiosWtaVqW_A0KaRnQj4eyLRxdHMaqRDyC1nJefM3S2fq7pWimkoBROidNYJZdkZmXIjLLfacDgnE8E1LwCYuSTTnD8ZE9I5OSHVIvnug9Y4JL8f0X8f0xf1baDrocPUxR_c07nPGOg8-djSTcx5QLrG9wO2ve_jsb0iF43fZ7w-cUZeHx821VOxelksq_tVEQWTfYG8ERI0cGWsAh_gbRw3DSgLCK5h3ButR9sZNGKn0QczOkAITgXr5Yzc_HcjIm67FA8-_W5Ph-UfVvRK-A</recordid><startdate>20220718</startdate><enddate>20220718</enddate><creator>Wu, Chong</creator><creator>Feng, Zhenan</creator><creator>Zhang, Houwang</creator><creator>Yan, Hong</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20220718</creationdate><title>Graph Neural Network and Superpixel Based Brain Tissue Segmentation</title><author>Wu, Chong ; Feng, Zhenan ; Zhang, Houwang ; Yan, Hong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i203t-e1f23464157854ad4bad417f4584e49f01a766e49c7e72c6ead79c744dd95d8a3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Brain tissue segmentation</topic><topic>Graph neural network</topic><topic>Interaction mechanism</topic><topic>Superpixel</topic><toplevel>online_resources</toplevel><creatorcontrib>Wu, Chong</creatorcontrib><creatorcontrib>Feng, Zhenan</creatorcontrib><creatorcontrib>Zhang, Houwang</creatorcontrib><creatorcontrib>Yan, Hong</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEL</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Wu, Chong</au><au>Feng, Zhenan</au><au>Zhang, Houwang</au><au>Yan, Hong</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Graph Neural Network and Superpixel Based Brain Tissue Segmentation</atitle><btitle>2022 International Joint Conference on Neural Networks (IJCNN)</btitle><stitle>IJCNN</stitle><date>2022-07-18</date><risdate>2022</risdate><spage>01</spage><epage>08</epage><pages>01-08</pages><eissn>2161-4407</eissn><eisbn>1728186714</eisbn><eisbn>9781728186719</eisbn><abstract>Convolutional neural networks (CNNs) are usually used as a backbone to design methods in biomedical image segmentation. However, the limitation of receptive field and large number of parameters limit the performance of these methods. In this paper, we propose a graph neural network (GNN) based method named GNN-SEG for the segmentation of brain tissues. Different to conventional CNN based methods, GNN-SEG takes superpixels as basic processing units and uses GNNs to learn the structure of brain tissues. Besides, inspired by the interaction mechanism in biological vision systems, we propose two kinds of interaction modules for feature enhancement and integration. In the experiments, we compared GNN-SEG with state-of-the-art CNN based methods on four datasets of brain magnetic resonance images. The experimental results show the superiority of GNN-SEG.</abstract><pub>IEEE</pub><doi>10.1109/IJCNN55064.2022.9892580</doi><tpages>8</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2161-4407
ispartof 2022 International Joint Conference on Neural Networks (IJCNN), 2022, p.01-08
issn 2161-4407
language eng
recordid cdi_ieee_primary_9892580
source IEEE Xplore All Conference Series
subjects Brain tissue segmentation
Graph neural network
Interaction mechanism
Superpixel
title Graph Neural Network and Superpixel Based Brain Tissue Segmentation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T01%3A36%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Graph%20Neural%20Network%20and%20Superpixel%20Based%20Brain%20Tissue%20Segmentation&rft.btitle=2022%20International%20Joint%20Conference%20on%20Neural%20Networks%20(IJCNN)&rft.au=Wu,%20Chong&rft.date=2022-07-18&rft.spage=01&rft.epage=08&rft.pages=01-08&rft.eissn=2161-4407&rft_id=info:doi/10.1109/IJCNN55064.2022.9892580&rft.eisbn=1728186714&rft.eisbn_list=9781728186719&rft_dat=%3Cieee_CHZPO%3E9892580%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i203t-e1f23464157854ad4bad417f4584e49f01a766e49c7e72c6ead79c744dd95d8a3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=9892580&rfr_iscdi=true