Deep Upscale U-Net for automatic tongue segmentation
In a treatment or diagnosis related to oral health conditions such as oral cancer and oropharyngeal cancer, an investigation of tongue’s movements is a major part. In an automatic measurement of such movement, it must first start with a task of tongue segmentation. This paper proposes a solution of...
Gespeichert in:
| Veröffentlicht in: | Medical & biological engineering & computing 2024-06, Vol.62 (6), p.1751-1762 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1762 |
|---|---|
| container_issue | 6 |
| container_start_page | 1751 |
| container_title | Medical & biological engineering & computing |
| container_volume | 62 |
| creator | Kusakunniran, Worapan Imaromkul, Thanandon Mongkolluksamee, Sophon Thongkanchorn, Kittikhun Ritthipravat, Panrasee Tuakta, Pimchanok Benjapornlert, Paitoon |
| description | In a treatment or diagnosis related to oral health conditions such as oral cancer and oropharyngeal cancer, an investigation of tongue’s movements is a major part. In an automatic measurement of such movement, it must first start with a task of tongue segmentation. This paper proposes a solution of tongue segmentation based on a decoder-encoder CNN-based structure i.e., U-Net. However, it could suffer from a problem of feature loss in deep layers. This paper proposes a Deep Upscale U-Net (DU-UNET). An additional up-sampling of the feature map from a contracting path is concatenated to an upper layer of an expansive path, based on an original U-Net structure. The segmentation model is constructed by training DU-UNET on the two publicly available datasets, and transferred to the self-collected dataset of tongue images with five tongue postures which were recorded at a far distance from a camera under a real-world scenario. The proposed DU-UNET outperforms the other existing methods in our literature reviews, with accuracy of 99.2%, mean IoU of 97.8%, Dice score of 96.8%, and Jaccard score of 96.8%.
Graphical abstract |
| doi_str_mv | 10.1007/s11517-024-03051-w |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2928584957</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3051754287</sourcerecordid><originalsourceid>FETCH-LOGICAL-c326t-66c47fab2ff66f87aeda37874cb8180d0a098148700054ef525b5f68406e853a3</originalsourceid><addsrcrecordid>eNp9kE1PwzAMhiMEYmPwBzigSly4BJw0abIjGp_SBBd2jtLOmTa1TUlaTfx7OjpA4sDJkv34tfUQcs7gmgGom8iYZIoCFxRSkIxuD8iYKcEoCCEOyRiYAAqM6RE5iXEDwJnk4piMUp0qPmUwJuIOsUkWTSxsicmCvmCbOB8S27W-su26SFpfrzpMIq4qrNu-5etTcuRsGfFsXydk8XD_Nnui89fH59ntnBYpz1qaZYVQzubcuSxzWllc2lRpJYpcMw1LsDDVTGgFAFKgk1zm0mVaQIZapjadkKshtwn-vcPYmmodCyxLW6PvouFTrqUWU6l69PIPuvFdqPvvzE6NkoLrHcUHqgg-xoDONGFd2fBhGJidUzM4Nb1T8-XUbPuli310l1e4_Fn5ltgD6QDEflSvMPze_if2E_Bif48</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3051754287</pqid></control><display><type>article</type><title>Deep Upscale U-Net for automatic tongue segmentation</title><source>MEDLINE</source><source>SpringerLink Journals - AutoHoldings</source><creator>Kusakunniran, Worapan ; Imaromkul, Thanandon ; Mongkolluksamee, Sophon ; Thongkanchorn, Kittikhun ; Ritthipravat, Panrasee ; Tuakta, Pimchanok ; Benjapornlert, Paitoon</creator><creatorcontrib>Kusakunniran, Worapan ; Imaromkul, Thanandon ; Mongkolluksamee, Sophon ; Thongkanchorn, Kittikhun ; Ritthipravat, Panrasee ; Tuakta, Pimchanok ; Benjapornlert, Paitoon</creatorcontrib><description>In a treatment or diagnosis related to oral health conditions such as oral cancer and oropharyngeal cancer, an investigation of tongue’s movements is a major part. In an automatic measurement of such movement, it must first start with a task of tongue segmentation. This paper proposes a solution of tongue segmentation based on a decoder-encoder CNN-based structure i.e., U-Net. However, it could suffer from a problem of feature loss in deep layers. This paper proposes a Deep Upscale U-Net (DU-UNET). An additional up-sampling of the feature map from a contracting path is concatenated to an upper layer of an expansive path, based on an original U-Net structure. The segmentation model is constructed by training DU-UNET on the two publicly available datasets, and transferred to the self-collected dataset of tongue images with five tongue postures which were recorded at a far distance from a camera under a real-world scenario. The proposed DU-UNET outperforms the other existing methods in our literature reviews, with accuracy of 99.2%, mean IoU of 97.8%, Dice score of 96.8%, and Jaccard score of 96.8%.
Graphical abstract</description><identifier>ISSN: 0140-0118</identifier><identifier>EISSN: 1741-0444</identifier><identifier>DOI: 10.1007/s11517-024-03051-w</identifier><identifier>PMID: 38372910</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Algorithms ; Biomedical and Life Sciences ; Biomedical Engineering and Bioengineering ; Biomedicine ; Cancer ; Computer Applications ; Datasets ; Deep Learning ; Encoders-Decoders ; Feature maps ; Human Physiology ; Humans ; Image Processing, Computer-Assisted - methods ; Imaging ; Literature reviews ; Neural Networks, Computer ; Original Article ; Oropharyngeal cancer ; Radiology ; Segmentation ; Tongue ; Tongue - diagnostic imaging</subject><ispartof>Medical & biological engineering & computing, 2024-06, Vol.62 (6), p.1751-1762</ispartof><rights>International Federation for Medical and Biological Engineering 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><rights>2024. International Federation for Medical and Biological Engineering.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c326t-66c47fab2ff66f87aeda37874cb8180d0a098148700054ef525b5f68406e853a3</cites><orcidid>0000-0002-2896-611X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11517-024-03051-w$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11517-024-03051-w$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27923,27924,41487,42556,51318</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38372910$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Kusakunniran, Worapan</creatorcontrib><creatorcontrib>Imaromkul, Thanandon</creatorcontrib><creatorcontrib>Mongkolluksamee, Sophon</creatorcontrib><creatorcontrib>Thongkanchorn, Kittikhun</creatorcontrib><creatorcontrib>Ritthipravat, Panrasee</creatorcontrib><creatorcontrib>Tuakta, Pimchanok</creatorcontrib><creatorcontrib>Benjapornlert, Paitoon</creatorcontrib><title>Deep Upscale U-Net for automatic tongue segmentation</title><title>Medical & biological engineering & computing</title><addtitle>Med Biol Eng Comput</addtitle><addtitle>Med Biol Eng Comput</addtitle><description>In a treatment or diagnosis related to oral health conditions such as oral cancer and oropharyngeal cancer, an investigation of tongue’s movements is a major part. In an automatic measurement of such movement, it must first start with a task of tongue segmentation. This paper proposes a solution of tongue segmentation based on a decoder-encoder CNN-based structure i.e., U-Net. However, it could suffer from a problem of feature loss in deep layers. This paper proposes a Deep Upscale U-Net (DU-UNET). An additional up-sampling of the feature map from a contracting path is concatenated to an upper layer of an expansive path, based on an original U-Net structure. The segmentation model is constructed by training DU-UNET on the two publicly available datasets, and transferred to the self-collected dataset of tongue images with five tongue postures which were recorded at a far distance from a camera under a real-world scenario. The proposed DU-UNET outperforms the other existing methods in our literature reviews, with accuracy of 99.2%, mean IoU of 97.8%, Dice score of 96.8%, and Jaccard score of 96.8%.
Graphical abstract</description><subject>Algorithms</subject><subject>Biomedical and Life Sciences</subject><subject>Biomedical Engineering and Bioengineering</subject><subject>Biomedicine</subject><subject>Cancer</subject><subject>Computer Applications</subject><subject>Datasets</subject><subject>Deep Learning</subject><subject>Encoders-Decoders</subject><subject>Feature maps</subject><subject>Human Physiology</subject><subject>Humans</subject><subject>Image Processing, Computer-Assisted - methods</subject><subject>Imaging</subject><subject>Literature reviews</subject><subject>Neural Networks, Computer</subject><subject>Original Article</subject><subject>Oropharyngeal cancer</subject><subject>Radiology</subject><subject>Segmentation</subject><subject>Tongue</subject><subject>Tongue - diagnostic imaging</subject><issn>0140-0118</issn><issn>1741-0444</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp9kE1PwzAMhiMEYmPwBzigSly4BJw0abIjGp_SBBd2jtLOmTa1TUlaTfx7OjpA4sDJkv34tfUQcs7gmgGom8iYZIoCFxRSkIxuD8iYKcEoCCEOyRiYAAqM6RE5iXEDwJnk4piMUp0qPmUwJuIOsUkWTSxsicmCvmCbOB8S27W-su26SFpfrzpMIq4qrNu-5etTcuRsGfFsXydk8XD_Nnui89fH59ntnBYpz1qaZYVQzubcuSxzWllc2lRpJYpcMw1LsDDVTGgFAFKgk1zm0mVaQIZapjadkKshtwn-vcPYmmodCyxLW6PvouFTrqUWU6l69PIPuvFdqPvvzE6NkoLrHcUHqgg-xoDONGFd2fBhGJidUzM4Nb1T8-XUbPuli310l1e4_Fn5ltgD6QDEflSvMPze_if2E_Bif48</recordid><startdate>20240601</startdate><enddate>20240601</enddate><creator>Kusakunniran, Worapan</creator><creator>Imaromkul, Thanandon</creator><creator>Mongkolluksamee, Sophon</creator><creator>Thongkanchorn, Kittikhun</creator><creator>Ritthipravat, Panrasee</creator><creator>Tuakta, Pimchanok</creator><creator>Benjapornlert, Paitoon</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7TB</scope><scope>7TS</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>K9.</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>M7Z</scope><scope>NAPCQ</scope><scope>P64</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-2896-611X</orcidid></search><sort><creationdate>20240601</creationdate><title>Deep Upscale U-Net for automatic tongue segmentation</title><author>Kusakunniran, Worapan ; Imaromkul, Thanandon ; Mongkolluksamee, Sophon ; Thongkanchorn, Kittikhun ; Ritthipravat, Panrasee ; Tuakta, Pimchanok ; Benjapornlert, Paitoon</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c326t-66c47fab2ff66f87aeda37874cb8180d0a098148700054ef525b5f68406e853a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Biomedical and Life Sciences</topic><topic>Biomedical Engineering and Bioengineering</topic><topic>Biomedicine</topic><topic>Cancer</topic><topic>Computer Applications</topic><topic>Datasets</topic><topic>Deep Learning</topic><topic>Encoders-Decoders</topic><topic>Feature maps</topic><topic>Human Physiology</topic><topic>Humans</topic><topic>Image Processing, Computer-Assisted - methods</topic><topic>Imaging</topic><topic>Literature reviews</topic><topic>Neural Networks, Computer</topic><topic>Original Article</topic><topic>Oropharyngeal cancer</topic><topic>Radiology</topic><topic>Segmentation</topic><topic>Tongue</topic><topic>Tongue - diagnostic imaging</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kusakunniran, Worapan</creatorcontrib><creatorcontrib>Imaromkul, Thanandon</creatorcontrib><creatorcontrib>Mongkolluksamee, Sophon</creatorcontrib><creatorcontrib>Thongkanchorn, Kittikhun</creatorcontrib><creatorcontrib>Ritthipravat, Panrasee</creatorcontrib><creatorcontrib>Tuakta, Pimchanok</creatorcontrib><creatorcontrib>Benjapornlert, Paitoon</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Physical Education Index</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Biochemistry Abstracts 1</collection><collection>Nursing & Allied Health Premium</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>Medical & biological engineering & computing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kusakunniran, Worapan</au><au>Imaromkul, Thanandon</au><au>Mongkolluksamee, Sophon</au><au>Thongkanchorn, Kittikhun</au><au>Ritthipravat, Panrasee</au><au>Tuakta, Pimchanok</au><au>Benjapornlert, Paitoon</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep Upscale U-Net for automatic tongue segmentation</atitle><jtitle>Medical & biological engineering & computing</jtitle><stitle>Med Biol Eng Comput</stitle><addtitle>Med Biol Eng Comput</addtitle><date>2024-06-01</date><risdate>2024</risdate><volume>62</volume><issue>6</issue><spage>1751</spage><epage>1762</epage><pages>1751-1762</pages><issn>0140-0118</issn><eissn>1741-0444</eissn><abstract>In a treatment or diagnosis related to oral health conditions such as oral cancer and oropharyngeal cancer, an investigation of tongue’s movements is a major part. In an automatic measurement of such movement, it must first start with a task of tongue segmentation. This paper proposes a solution of tongue segmentation based on a decoder-encoder CNN-based structure i.e., U-Net. However, it could suffer from a problem of feature loss in deep layers. This paper proposes a Deep Upscale U-Net (DU-UNET). An additional up-sampling of the feature map from a contracting path is concatenated to an upper layer of an expansive path, based on an original U-Net structure. The segmentation model is constructed by training DU-UNET on the two publicly available datasets, and transferred to the self-collected dataset of tongue images with five tongue postures which were recorded at a far distance from a camera under a real-world scenario. The proposed DU-UNET outperforms the other existing methods in our literature reviews, with accuracy of 99.2%, mean IoU of 97.8%, Dice score of 96.8%, and Jaccard score of 96.8%.
Graphical abstract</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><pmid>38372910</pmid><doi>10.1007/s11517-024-03051-w</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-2896-611X</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0140-0118 |
| ispartof | Medical & biological engineering & computing, 2024-06, Vol.62 (6), p.1751-1762 |
| issn | 0140-0118 1741-0444 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2928584957 |
| source | MEDLINE; SpringerLink Journals - AutoHoldings |
| subjects | Algorithms Biomedical and Life Sciences Biomedical Engineering and Bioengineering Biomedicine Cancer Computer Applications Datasets Deep Learning Encoders-Decoders Feature maps Human Physiology Humans Image Processing, Computer-Assisted - methods Imaging Literature reviews Neural Networks, Computer Original Article Oropharyngeal cancer Radiology Segmentation Tongue Tongue - diagnostic imaging |
| title | Deep Upscale U-Net for automatic tongue segmentation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T22%3A44%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%20Upscale%20U-Net%20for%20automatic%20tongue%20segmentation&rft.jtitle=Medical%20&%20biological%20engineering%20&%20computing&rft.au=Kusakunniran,%20Worapan&rft.date=2024-06-01&rft.volume=62&rft.issue=6&rft.spage=1751&rft.epage=1762&rft.pages=1751-1762&rft.issn=0140-0118&rft.eissn=1741-0444&rft_id=info:doi/10.1007/s11517-024-03051-w&rft_dat=%3Cproquest_cross%3E3051754287%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3051754287&rft_id=info:pmid/38372910&rfr_iscdi=true |