Assessment of encoder-decoder-based segmentation models for thyroid ultrasound images
Encoder-decoder-based semantic segmentation models classify image pixels into the corresponding class, such as the ROI (region of interest) or background. In the present study, simple / dilated convolution / series / directed acyclic graph (DAG)-based encoder-decoder semantic segmentation models hav...
Gespeichert in:
| Veröffentlicht in: | Medical & biological engineering & computing 2023-08, Vol.61 (8), p.2159-2195 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2195 |
|---|---|
| container_issue | 8 |
| container_start_page | 2159 |
| container_title | Medical & biological engineering & computing |
| container_volume | 61 |
| creator | Yadav, Niranjan Dass, Rajeshwar Virmani, Jitendra |
| description | Encoder-decoder-based semantic segmentation models classify image pixels into the corresponding class, such as the ROI (region of interest) or background. In the present study, simple / dilated convolution / series / directed acyclic graph (DAG)-based encoder-decoder semantic segmentation models have been implemented, i.e., SegNet (VGG16), SegNet (VGG19), U-Net, mobileNetv2, ResNet18, ResNet50, Xception and Inception networks for the segment TTUS(Thyroid Tumor Ultrasound) images. Transfer learning has been used to train these segmentation networks using original and despeckled TTUS images. The performance of the networks has been calculated using mIoU and mDC metrics. Based on the exhaustive experiments, it has been observed that ResNet50-based segmentation model obtained the best results objectively with values 0.87 for mIoU, 0.94 for mDC, and also according to radiologist opinion on shape, margin, and echogenicity characteristics of segmented lesions. It is noted that the segmentation model, namely ResNet50, provides better segmentation based on objective and subjective assessment. It may be used in the healthcare system to identify thyroid nodules accurately in real time.
Graphical Abstract |
| doi_str_mv | 10.1007/s11517-023-02849-4 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_3153156178</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2829431418</sourcerecordid><originalsourceid>FETCH-LOGICAL-c408t-c46588785885ba2e2d34eeb11bad06b7055dc38fca7abb4c79e88e99ffa5a2e93</originalsourceid><addsrcrecordid>eNqFkctKxTAQhoMoery8gAspuHFTzTRJky5FvIHgRtchbabHI22jmXbh25tjvYALhbks5pt_GH7GDoGfAuf6jAAU6JwXIqWRVS432AK0hJxLKTfZgoPkOQcwO2yX6JnzAlQht9mO0EKJslIL9nhOhEQ9DmMW2gyHJniMuce5147QZ4TLNeDGVRiyPg06ytoQs_HpLYaVz6ZujI7CNPhs1bsl0j7bal1HePDZ99jj1eXDxU1-d399e3F-lzeSmzHVUhmjTSqqdgUWXkjEGqB2npe15kr5Rpi2cdrVtWx0hcZgVbWtUwmvxB47mXVfYnidkEbbr6jBrnMDhomsAJWiBG3-RQtTVFKAhDV6_At9DlMc0iOJEqo0mguRqGKmmhiIIrb2Jabv45sFbtf-2Nkfm_yxH_5YmZaOPqWnukf_vfJlSALEDFAaDUuMP7f_kH0HviGbbw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2835687033</pqid></control><display><type>article</type><title>Assessment of encoder-decoder-based segmentation models for thyroid ultrasound images</title><source>MEDLINE</source><source>EBSCOhost Business Source Complete</source><source>SpringerLink Journals - AutoHoldings</source><creator>Yadav, Niranjan ; Dass, Rajeshwar ; Virmani, Jitendra</creator><creatorcontrib>Yadav, Niranjan ; Dass, Rajeshwar ; Virmani, Jitendra</creatorcontrib><description>Encoder-decoder-based semantic segmentation models classify image pixels into the corresponding class, such as the ROI (region of interest) or background. In the present study, simple / dilated convolution / series / directed acyclic graph (DAG)-based encoder-decoder semantic segmentation models have been implemented, i.e., SegNet (VGG16), SegNet (VGG19), U-Net, mobileNetv2, ResNet18, ResNet50, Xception and Inception networks for the segment TTUS(Thyroid Tumor Ultrasound) images. Transfer learning has been used to train these segmentation networks using original and despeckled TTUS images. The performance of the networks has been calculated using mIoU and mDC metrics. Based on the exhaustive experiments, it has been observed that ResNet50-based segmentation model obtained the best results objectively with values 0.87 for mIoU, 0.94 for mDC, and also according to radiologist opinion on shape, margin, and echogenicity characteristics of segmented lesions. It is noted that the segmentation model, namely ResNet50, provides better segmentation based on objective and subjective assessment. It may be used in the healthcare system to identify thyroid nodules accurately in real time.
Graphical Abstract</description><identifier>ISSN: 0140-0118</identifier><identifier>EISSN: 1741-0444</identifier><identifier>DOI: 10.1007/s11517-023-02849-4</identifier><identifier>PMID: 37353695</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Benchmarking ; Biomedical and Life Sciences ; Biomedical Engineering and Bioengineering ; Biomedicine ; class ; Coders ; Computer Applications ; Encoders-Decoders ; health services ; Human Physiology ; Humans ; Image classification ; Image processing ; Image Processing, Computer-Assisted ; Image segmentation ; Imaging ; Learning ; Networks ; Nodules ; Original Article ; Radiology ; Semantic segmentation ; Semantics ; Subjective assessment ; Thyroid ; Thyroid gland ; thyroid neoplasms ; Thyroid Nodule - diagnostic imaging ; Transfer learning ; Ultrasonic imaging ; ultrasonics ; ultrasonography ; Ultrasound</subject><ispartof>Medical & biological engineering & computing, 2023-08, Vol.61 (8), p.2159-2195</ispartof><rights>International Federation for Medical and Biological Engineering 2023. 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>2023. International Federation for Medical and Biological Engineering.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c408t-c46588785885ba2e2d34eeb11bad06b7055dc38fca7abb4c79e88e99ffa5a2e93</citedby><cites>FETCH-LOGICAL-c408t-c46588785885ba2e2d34eeb11bad06b7055dc38fca7abb4c79e88e99ffa5a2e93</cites><orcidid>0000-0002-1023-0438</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/s11517-023-02849-4$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11517-023-02849-4$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,777,781,27905,27906,41469,42538,51300</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37353695$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Yadav, Niranjan</creatorcontrib><creatorcontrib>Dass, Rajeshwar</creatorcontrib><creatorcontrib>Virmani, Jitendra</creatorcontrib><title>Assessment of encoder-decoder-based segmentation models for thyroid ultrasound images</title><title>Medical & biological engineering & computing</title><addtitle>Med Biol Eng Comput</addtitle><addtitle>Med Biol Eng Comput</addtitle><description>Encoder-decoder-based semantic segmentation models classify image pixels into the corresponding class, such as the ROI (region of interest) or background. In the present study, simple / dilated convolution / series / directed acyclic graph (DAG)-based encoder-decoder semantic segmentation models have been implemented, i.e., SegNet (VGG16), SegNet (VGG19), U-Net, mobileNetv2, ResNet18, ResNet50, Xception and Inception networks for the segment TTUS(Thyroid Tumor Ultrasound) images. Transfer learning has been used to train these segmentation networks using original and despeckled TTUS images. The performance of the networks has been calculated using mIoU and mDC metrics. Based on the exhaustive experiments, it has been observed that ResNet50-based segmentation model obtained the best results objectively with values 0.87 for mIoU, 0.94 for mDC, and also according to radiologist opinion on shape, margin, and echogenicity characteristics of segmented lesions. It is noted that the segmentation model, namely ResNet50, provides better segmentation based on objective and subjective assessment. It may be used in the healthcare system to identify thyroid nodules accurately in real time.
Graphical Abstract</description><subject>Benchmarking</subject><subject>Biomedical and Life Sciences</subject><subject>Biomedical Engineering and Bioengineering</subject><subject>Biomedicine</subject><subject>class</subject><subject>Coders</subject><subject>Computer Applications</subject><subject>Encoders-Decoders</subject><subject>health services</subject><subject>Human Physiology</subject><subject>Humans</subject><subject>Image classification</subject><subject>Image processing</subject><subject>Image Processing, Computer-Assisted</subject><subject>Image segmentation</subject><subject>Imaging</subject><subject>Learning</subject><subject>Networks</subject><subject>Nodules</subject><subject>Original Article</subject><subject>Radiology</subject><subject>Semantic segmentation</subject><subject>Semantics</subject><subject>Subjective assessment</subject><subject>Thyroid</subject><subject>Thyroid gland</subject><subject>thyroid neoplasms</subject><subject>Thyroid Nodule - diagnostic imaging</subject><subject>Transfer learning</subject><subject>Ultrasonic imaging</subject><subject>ultrasonics</subject><subject>ultrasonography</subject><subject>Ultrasound</subject><issn>0140-0118</issn><issn>1741-0444</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNqFkctKxTAQhoMoery8gAspuHFTzTRJky5FvIHgRtchbabHI22jmXbh25tjvYALhbks5pt_GH7GDoGfAuf6jAAU6JwXIqWRVS432AK0hJxLKTfZgoPkOQcwO2yX6JnzAlQht9mO0EKJslIL9nhOhEQ9DmMW2gyHJniMuce5147QZ4TLNeDGVRiyPg06ytoQs_HpLYaVz6ZujI7CNPhs1bsl0j7bal1HePDZ99jj1eXDxU1-d399e3F-lzeSmzHVUhmjTSqqdgUWXkjEGqB2npe15kr5Rpi2cdrVtWx0hcZgVbWtUwmvxB47mXVfYnidkEbbr6jBrnMDhomsAJWiBG3-RQtTVFKAhDV6_At9DlMc0iOJEqo0mguRqGKmmhiIIrb2Jabv45sFbtf-2Nkfm_yxH_5YmZaOPqWnukf_vfJlSALEDFAaDUuMP7f_kH0HviGbbw</recordid><startdate>20230801</startdate><enddate>20230801</enddate><creator>Yadav, Niranjan</creator><creator>Dass, Rajeshwar</creator><creator>Virmani, Jitendra</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>3V.</scope><scope>7RV</scope><scope>7SC</scope><scope>7TB</scope><scope>7TS</scope><scope>7WY</scope><scope>7WZ</scope><scope>7X7</scope><scope>7XB</scope><scope>87Z</scope><scope>88A</scope><scope>88E</scope><scope>88I</scope><scope>8AL</scope><scope>8AO</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FH</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>8FL</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BEZIV</scope><scope>BGLVJ</scope><scope>BHPHI</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FR3</scope><scope>FRNLG</scope><scope>FYUFA</scope><scope>F~G</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K60</scope><scope>K6~</scope><scope>K7-</scope><scope>K9.</scope><scope>KB0</scope><scope>L.-</scope><scope>L7M</scope><scope>LK8</scope><scope>L~C</scope><scope>L~D</scope><scope>M0C</scope><scope>M0N</scope><scope>M0S</scope><scope>M1P</scope><scope>M2P</scope><scope>M7P</scope><scope>M7Z</scope><scope>NAPCQ</scope><scope>P5Z</scope><scope>P62</scope><scope>P64</scope><scope>PQBIZ</scope><scope>PQBZA</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>Q9U</scope><scope>7X8</scope><scope>7S9</scope><scope>L.6</scope><orcidid>https://orcid.org/0000-0002-1023-0438</orcidid></search><sort><creationdate>20230801</creationdate><title>Assessment of encoder-decoder-based segmentation models for thyroid ultrasound images</title><author>Yadav, Niranjan ; Dass, Rajeshwar ; Virmani, Jitendra</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c408t-c46588785885ba2e2d34eeb11bad06b7055dc38fca7abb4c79e88e99ffa5a2e93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Benchmarking</topic><topic>Biomedical and Life Sciences</topic><topic>Biomedical Engineering and Bioengineering</topic><topic>Biomedicine</topic><topic>class</topic><topic>Coders</topic><topic>Computer Applications</topic><topic>Encoders-Decoders</topic><topic>health services</topic><topic>Human Physiology</topic><topic>Humans</topic><topic>Image classification</topic><topic>Image processing</topic><topic>Image Processing, Computer-Assisted</topic><topic>Image segmentation</topic><topic>Imaging</topic><topic>Learning</topic><topic>Networks</topic><topic>Nodules</topic><topic>Original Article</topic><topic>Radiology</topic><topic>Semantic segmentation</topic><topic>Semantics</topic><topic>Subjective assessment</topic><topic>Thyroid</topic><topic>Thyroid gland</topic><topic>thyroid neoplasms</topic><topic>Thyroid Nodule - diagnostic imaging</topic><topic>Transfer learning</topic><topic>Ultrasonic imaging</topic><topic>ultrasonics</topic><topic>ultrasonography</topic><topic>Ultrasound</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yadav, Niranjan</creatorcontrib><creatorcontrib>Dass, Rajeshwar</creatorcontrib><creatorcontrib>Virmani, Jitendra</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Nursing & Allied Health Database</collection><collection>Computer and Information Systems Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Physical Education Index</collection><collection>ABI/INFORM Collection</collection><collection>ABI/INFORM Global (PDF only)</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ABI/INFORM Global (Alumni Edition)</collection><collection>Biology Database (Alumni Edition)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Science Database (Alumni Edition)</collection><collection>Computing Database (Alumni Edition)</collection><collection>ProQuest Pharma Collection</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ABI/INFORM Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Business Premium Collection</collection><collection>Technology Collection</collection><collection>Natural Science Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Engineering Research Database</collection><collection>Business Premium Collection (Alumni)</collection><collection>Health Research Premium Collection</collection><collection>ABI/INFORM Global (Corporate)</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Business Collection (Alumni Edition)</collection><collection>ProQuest Business Collection</collection><collection>Computer Science Database</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Database (Alumni Edition)</collection><collection>ABI/INFORM Professional Advanced</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>ProQuest Biological Science Collection</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>ABI/INFORM Global</collection><collection>Computing Database</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Science Database</collection><collection>Biological Science Database</collection><collection>Biochemistry Abstracts 1</collection><collection>Nursing & Allied Health Premium</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>One Business (ProQuest)</collection><collection>ProQuest One Business (Alumni)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central Basic</collection><collection>MEDLINE - Academic</collection><collection>AGRICOLA</collection><collection>AGRICOLA - Academic</collection><jtitle>Medical & biological engineering & computing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yadav, Niranjan</au><au>Dass, Rajeshwar</au><au>Virmani, Jitendra</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Assessment of encoder-decoder-based segmentation models for thyroid ultrasound images</atitle><jtitle>Medical & biological engineering & computing</jtitle><stitle>Med Biol Eng Comput</stitle><addtitle>Med Biol Eng Comput</addtitle><date>2023-08-01</date><risdate>2023</risdate><volume>61</volume><issue>8</issue><spage>2159</spage><epage>2195</epage><pages>2159-2195</pages><issn>0140-0118</issn><eissn>1741-0444</eissn><abstract>Encoder-decoder-based semantic segmentation models classify image pixels into the corresponding class, such as the ROI (region of interest) or background. In the present study, simple / dilated convolution / series / directed acyclic graph (DAG)-based encoder-decoder semantic segmentation models have been implemented, i.e., SegNet (VGG16), SegNet (VGG19), U-Net, mobileNetv2, ResNet18, ResNet50, Xception and Inception networks for the segment TTUS(Thyroid Tumor Ultrasound) images. Transfer learning has been used to train these segmentation networks using original and despeckled TTUS images. The performance of the networks has been calculated using mIoU and mDC metrics. Based on the exhaustive experiments, it has been observed that ResNet50-based segmentation model obtained the best results objectively with values 0.87 for mIoU, 0.94 for mDC, and also according to radiologist opinion on shape, margin, and echogenicity characteristics of segmented lesions. It is noted that the segmentation model, namely ResNet50, provides better segmentation based on objective and subjective assessment. It may be used in the healthcare system to identify thyroid nodules accurately in real time.
Graphical Abstract</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><pmid>37353695</pmid><doi>10.1007/s11517-023-02849-4</doi><tpages>37</tpages><orcidid>https://orcid.org/0000-0002-1023-0438</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0140-0118 |
| ispartof | Medical & biological engineering & computing, 2023-08, Vol.61 (8), p.2159-2195 |
| issn | 0140-0118 1741-0444 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_3153156178 |
| source | MEDLINE; EBSCOhost Business Source Complete; SpringerLink Journals - AutoHoldings |
| subjects | Benchmarking Biomedical and Life Sciences Biomedical Engineering and Bioengineering Biomedicine class Coders Computer Applications Encoders-Decoders health services Human Physiology Humans Image classification Image processing Image Processing, Computer-Assisted Image segmentation Imaging Learning Networks Nodules Original Article Radiology Semantic segmentation Semantics Subjective assessment Thyroid Thyroid gland thyroid neoplasms Thyroid Nodule - diagnostic imaging Transfer learning Ultrasonic imaging ultrasonics ultrasonography Ultrasound |
| title | Assessment of encoder-decoder-based segmentation models for thyroid ultrasound images |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T23%3A48%3A02IST&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=Assessment%20of%20encoder-decoder-based%20segmentation%20models%20for%20thyroid%20ultrasound%20images&rft.jtitle=Medical%20&%20biological%20engineering%20&%20computing&rft.au=Yadav,%20Niranjan&rft.date=2023-08-01&rft.volume=61&rft.issue=8&rft.spage=2159&rft.epage=2195&rft.pages=2159-2195&rft.issn=0140-0118&rft.eissn=1741-0444&rft_id=info:doi/10.1007/s11517-023-02849-4&rft_dat=%3Cproquest_cross%3E2829431418%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=2835687033&rft_id=info:pmid/37353695&rfr_iscdi=true |