Comparison of neural network architectures for segmentation of the left ventricle on EchoCG images

This paper compares the quality of segmentation of echocardiographic images of the left ventricle of the heart using 5 architectures and 38 pre-trained encoders. As part of the study, we trained 1140 neural networks. On the test dataset, the accuracy was 93.18% according to the Dice metric, which is...

Full description

Saved in:
Bibliographic Details
Main Authors: Samun, V. S., Sheka, A. S., Chumarnaya, T. V., Solovyova, O. E.
Format: Conference Proceeding
Language:English
Subjects:
Coders
Computer architecture
Image quality
Image segmentation
Neural networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue 1
container_start_page
container_title
container_volume 2313
creator Samun, V. S.
Sheka, A. S.
Chumarnaya, T. V.
Solovyova, O. E.
description This paper compares the quality of segmentation of echocardiographic images of the left ventricle of the heart using 5 architectures and 38 pre-trained encoders. As part of the study, we trained 1140 neural networks. On the test dataset, the accuracy was 93.18% according to the Dice metric, which is more than our previous result at 92.78%. On cross-validation, the accuracy was 98.79%, which is higher than the previous result of 90.15%.
doi_str_mv 10.1063/5.0032165
format conference_proceeding
fullrecord <record><control><sourceid>proquest_scita</sourceid><recordid>TN_cdi_proquest_journals_2468427056</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2468427056</sourcerecordid><originalsourceid>FETCH-LOGICAL-p253t-785d2d1718ef2d29d41be4f78b65424da4c08ba1d91cbf4792294e156e1016063</originalsourceid><addsrcrecordid>eNotUMtOwzAQtBBIlMKBP7DEDSnF6_iRHFFUHlIlLiBxs5xk06akcbAdEH9PqvQ00u7M7swQcgtsBUylD3LFWMpByTOyACkh0QrUOVkwlouEi_TzklyFsGeM51pnC1IW7jBY3wbXU9fQHkdvuwnir_Nf1Ppq10as4ugx0MZ5GnB7wD7a2M6CuEPaYRPpzzT1bdUhnRbraueKZ9oe7BbDNblobBfw5oRL8vG0fi9eks3b82vxuEkGLtOY6EzWvAYNGTa85nktoETR6KxUUnBRW1GxrLRQ51CVjdA557lAkAqBgZqyL8ndfHfw7nvEEM3ejb6fXhouVCa4ZvLIup9ZoWrnGGbwk1H_Z4CZY4dGmlOH6T9-YGOM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype><pqid>2468427056</pqid></control><display><type>conference_proceeding</type><title>Comparison of neural network architectures for segmentation of the left ventricle on EchoCG images</title><source>American Institute of Physics:Jisc Collections:Transitional Journals Agreement 2021-23 (Reading list)</source><creator>Samun, V. S. ; Sheka, A. S. ; Chumarnaya, T. V. ; Solovyova, O. E.</creator><contributor>Smirnov, Andrey A ; Kashin, Ilya V ; Narkhov, Evgeniy D ; Volkovich, Vladimir A</contributor><creatorcontrib>Samun, V. S. ; Sheka, A. S. ; Chumarnaya, T. V. ; Solovyova, O. E. ; Smirnov, Andrey A ; Kashin, Ilya V ; Narkhov, Evgeniy D ; Volkovich, Vladimir A</creatorcontrib><description>This paper compares the quality of segmentation of echocardiographic images of the left ventricle of the heart using 5 architectures and 38 pre-trained encoders. As part of the study, we trained 1140 neural networks. On the test dataset, the accuracy was 93.18% according to the Dice metric, which is more than our previous result at 92.78%. On cross-validation, the accuracy was 98.79%, which is higher than the previous result of 90.15%.</description><identifier>ISSN: 0094-243X</identifier><identifier>EISSN: 1551-7616</identifier><identifier>DOI: 10.1063/5.0032165</identifier><identifier>CODEN: APCPCS</identifier><language>eng</language><publisher>Melville: American Institute of Physics</publisher><subject>Coders ; Computer architecture ; Image quality ; Image segmentation ; Neural networks</subject><ispartof>AIP Conference Proceedings, 2020, Vol.2313 (1)</ispartof><rights>Author(s)</rights><rights>2020 Author(s). Published by AIP Publishing.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>310,311,315,786,790,795,796,23958,23959,25170,27957,27958</link.rule.ids></links><search><contributor>Smirnov, Andrey A</contributor><contributor>Kashin, Ilya V</contributor><contributor>Narkhov, Evgeniy D</contributor><contributor>Volkovich, Vladimir A</contributor><creatorcontrib>Samun, V. S.</creatorcontrib><creatorcontrib>Sheka, A. S.</creatorcontrib><creatorcontrib>Chumarnaya, T. V.</creatorcontrib><creatorcontrib>Solovyova, O. E.</creatorcontrib><title>Comparison of neural network architectures for segmentation of the left ventricle on EchoCG images</title><title>AIP Conference Proceedings</title><description>This paper compares the quality of segmentation of echocardiographic images of the left ventricle of the heart using 5 architectures and 38 pre-trained encoders. As part of the study, we trained 1140 neural networks. On the test dataset, the accuracy was 93.18% according to the Dice metric, which is more than our previous result at 92.78%. On cross-validation, the accuracy was 98.79%, which is higher than the previous result of 90.15%.</description><subject>Coders</subject><subject>Computer architecture</subject><subject>Image quality</subject><subject>Image segmentation</subject><subject>Neural networks</subject><issn>0094-243X</issn><issn>1551-7616</issn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2020</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNotUMtOwzAQtBBIlMKBP7DEDSnF6_iRHFFUHlIlLiBxs5xk06akcbAdEH9PqvQ00u7M7swQcgtsBUylD3LFWMpByTOyACkh0QrUOVkwlouEi_TzklyFsGeM51pnC1IW7jBY3wbXU9fQHkdvuwnir_Nf1Ppq10as4ugx0MZ5GnB7wD7a2M6CuEPaYRPpzzT1bdUhnRbraueKZ9oe7BbDNblobBfw5oRL8vG0fi9eks3b82vxuEkGLtOY6EzWvAYNGTa85nktoETR6KxUUnBRW1GxrLRQ51CVjdA557lAkAqBgZqyL8ndfHfw7nvEEM3ejb6fXhouVCa4ZvLIup9ZoWrnGGbwk1H_Z4CZY4dGmlOH6T9-YGOM</recordid><startdate>20201209</startdate><enddate>20201209</enddate><creator>Samun, V. S.</creator><creator>Sheka, A. S.</creator><creator>Chumarnaya, T. V.</creator><creator>Solovyova, O. E.</creator><general>American Institute of Physics</general><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope></search><sort><creationdate>20201209</creationdate><title>Comparison of neural network architectures for segmentation of the left ventricle on EchoCG images</title><author>Samun, V. S. ; Sheka, A. S. ; Chumarnaya, T. V. ; Solovyova, O. E.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p253t-785d2d1718ef2d29d41be4f78b65424da4c08ba1d91cbf4792294e156e1016063</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Coders</topic><topic>Computer architecture</topic><topic>Image quality</topic><topic>Image segmentation</topic><topic>Neural networks</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Samun, V. S.</creatorcontrib><creatorcontrib>Sheka, A. S.</creatorcontrib><creatorcontrib>Chumarnaya, T. V.</creatorcontrib><creatorcontrib>Solovyova, O. E.</creatorcontrib><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Samun, V. S.</au><au>Sheka, A. S.</au><au>Chumarnaya, T. V.</au><au>Solovyova, O. E.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Comparison of neural network architectures for segmentation of the left ventricle on EchoCG images</atitle><btitle>AIP Conference Proceedings</btitle><date>2020-12-09</date><risdate>2020</risdate><volume>2313</volume><issue>1</issue><issn>0094-243X</issn><eissn>1551-7616</eissn><coden>APCPCS</coden><abstract>This paper compares the quality of segmentation of echocardiographic images of the left ventricle of the heart using 5 architectures and 38 pre-trained encoders. As part of the study, we trained 1140 neural networks. On the test dataset, the accuracy was 93.18% according to the Dice metric, which is more than our previous result at 92.78%. On cross-validation, the accuracy was 98.79%, which is higher than the previous result of 90.15%.</abstract><cop>Melville</cop><pub>American Institute of Physics</pub><doi>10.1063/5.0032165</doi><tpages>6</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0094-243X
ispartof AIP Conference Proceedings, 2020, Vol.2313 (1)
issn 0094-243X
1551-7616
language eng
recordid cdi_proquest_journals_2468427056
source American Institute of Physics:Jisc Collections:Transitional Journals Agreement 2021-23 (Reading list)
subjects Coders
Computer architecture
Image quality
Image segmentation
Neural networks
title Comparison of neural network architectures for segmentation of the left ventricle on EchoCG images
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T04%3A48%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_scita&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Comparison%20of%20neural%20network%20architectures%20for%20segmentation%20of%20the%20left%20ventricle%20on%20EchoCG%20images&rft.btitle=AIP%20Conference%20Proceedings&rft.au=Samun,%20V.%20S.&rft.date=2020-12-09&rft.volume=2313&rft.issue=1&rft.issn=0094-243X&rft.eissn=1551-7616&rft.coden=APCPCS&rft_id=info:doi/10.1063/5.0032165&rft_dat=%3Cproquest_scita%3E2468427056%3C/proquest_scita%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-p253t-785d2d1718ef2d29d41be4f78b65424da4c08ba1d91cbf4792294e156e1016063%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2468427056&rft_id=info:pmid/&rfr_iscdi=true