Large-scale screening to distinguish between COVID-19 and community-acquired pneumonia using infection size-aware classification
The worldwide spread of coronavirus disease (COVID-19) has become a threat to global public health. It is of great importance to rapidly and accurately screen and distinguish patients with COVID-19 from those with community-acquired pneumonia (CAP). In this study, a total of 1,658 patients with COVI...
Gespeichert in:
| Veröffentlicht in: | Physics in medicine & biology 2021-03, Vol.66 (6), p.065031-065031 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 065031 |
|---|---|
| container_issue | 6 |
| container_start_page | 065031 |
| container_title | Physics in medicine & biology |
| container_volume | 66 |
| creator | Shi, Feng Xia, Liming Shan, Fei Song, Bin Wu, Dijia Wei, Ying Yuan, Huan Jiang, Huiting He, Yichu Gao, Yaozong Sui, He Shen, Dinggang |
| description | The worldwide spread of coronavirus disease (COVID-19) has become a threat to global public health. It is of great importance to rapidly and accurately screen and distinguish patients with COVID-19 from those with community-acquired pneumonia (CAP). In this study, a total of 1,658 patients with COVID-19 and 1,027 CAP patients underwent thin-section CT and were enrolled. All images were preprocessed to obtain the segmentations of infections and lung fields. A set of handcrafted location-specific features was proposed to best capture the COVID-19 distribution pattern, in comparison to the conventional CT severity score (CT-SS) and radiomics features. An infection size-aware random forest method (iSARF) was proposed for discriminating COVID-19 from CAP. Experimental results show that the proposed method yielded its best performance when using the handcrafted features, with a sensitivity of 90.7%, a specificity of 87.2%, and an accuracy of 89.4% over state-of-the-art classifiers. Additional tests on 734 subjects, with thick slice images, demonstrates great generalizability. It is anticipated that our proposed framework could assist clinical decision making. |
| doi_str_mv | 10.1088/1361-6560/abe838 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_iop_j</sourceid><recordid>TN_cdi_iop_journals_10_1088_1361_6560_abe838</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2502807617</sourcerecordid><originalsourceid>FETCH-LOGICAL-c410t-d6f9dbdbc0b74849a4b6e9bc8546980c78296d94db40d643e9784f7a67633c3</originalsourceid><addsrcrecordid>eNp9kb9v1TAQxy0Eoq-FnQl5gwFTO3Yce0SvUCo9qQOI1fKPS3GVOKkdqyoTfzqJXumEmHzyfe4r3ecQesPoR0aVOmdcMiJbSc-tA8XVM7R7-nqOdpRyRjRr2xN0WsotpYypRrxEJ5x3jdZa7dDvg803QIq3A-DiM0CK6QYvEw6xLGtZY_mJHSz3awfvr39cXRCmsU0B-2kca4rLA7H-rsYMAc8J6jilaHEtW0xMPfglTgmX-AuIvbcZsB9sKbGP3m6dV-hFb4cCrx_fM_Tty-fv-6_kcH15tf90IF4wupAgex1ccJ66TiihrXAStPOqFVIr6jvVaBm0CE7QIAUH3SnRd1Z2knPPz9D7Y-qcp7sKZTFjLB6GwSaYajFNSxtFO8m6FaVH1OeplAy9mXMcbX4wjJrNutkUm02xOVpfR94-plc3Qnga-Kt5BT4cgTjN5naqOa2r_i_v3T_weXRGSiMNle16WDOHnv8BcTSatA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2502807617</pqid></control><display><type>article</type><title>Large-scale screening to distinguish between COVID-19 and community-acquired pneumonia using infection size-aware classification</title><source>Institute of Physics Journals</source><source>MEDLINE</source><creator>Shi, Feng ; Xia, Liming ; Shan, Fei ; Song, Bin ; Wu, Dijia ; Wei, Ying ; Yuan, Huan ; Jiang, Huiting ; He, Yichu ; Gao, Yaozong ; Sui, He ; Shen, Dinggang</creator><creatorcontrib>Shi, Feng ; Xia, Liming ; Shan, Fei ; Song, Bin ; Wu, Dijia ; Wei, Ying ; Yuan, Huan ; Jiang, Huiting ; He, Yichu ; Gao, Yaozong ; Sui, He ; Shen, Dinggang</creatorcontrib><description>The worldwide spread of coronavirus disease (COVID-19) has become a threat to global public health. It is of great importance to rapidly and accurately screen and distinguish patients with COVID-19 from those with community-acquired pneumonia (CAP). In this study, a total of 1,658 patients with COVID-19 and 1,027 CAP patients underwent thin-section CT and were enrolled. All images were preprocessed to obtain the segmentations of infections and lung fields. A set of handcrafted location-specific features was proposed to best capture the COVID-19 distribution pattern, in comparison to the conventional CT severity score (CT-SS) and radiomics features. An infection size-aware random forest method (iSARF) was proposed for discriminating COVID-19 from CAP. Experimental results show that the proposed method yielded its best performance when using the handcrafted features, with a sensitivity of 90.7%, a specificity of 87.2%, and an accuracy of 89.4% over state-of-the-art classifiers. Additional tests on 734 subjects, with thick slice images, demonstrates great generalizability. It is anticipated that our proposed framework could assist clinical decision making.</description><identifier>ISSN: 0031-9155</identifier><identifier>EISSN: 1361-6560</identifier><identifier>DOI: 10.1088/1361-6560/abe838</identifier><identifier>PMID: 33729998</identifier><identifier>CODEN: PHMBA7</identifier><language>eng</language><publisher>England: IOP Publishing</publisher><subject>Adult ; Aged ; Community-Acquired Infections - diagnostic imaging ; COVID-19 ; COVID-19 - diagnostic imaging ; decision tree ; Diagnosis, Computer-Assisted ; Diagnosis, Differential ; Female ; Humans ; Image Processing, Computer-Assisted ; Lung - diagnostic imaging ; Lung - virology ; Male ; Middle Aged ; pneumonia ; Pneumonia - diagnostic imaging ; random forest ; Reproducibility of Results ; Retrospective Studies ; Sensitivity and Specificity ; size-aware ; Tomography, X-Ray Computed</subject><ispartof>Physics in medicine & biology, 2021-03, Vol.66 (6), p.065031-065031</ispartof><rights>2021 Institute of Physics and Engineering in Medicine</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c410t-d6f9dbdbc0b74849a4b6e9bc8546980c78296d94db40d643e9784f7a67633c3</citedby><cites>FETCH-LOGICAL-c410t-d6f9dbdbc0b74849a4b6e9bc8546980c78296d94db40d643e9784f7a67633c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://iopscience.iop.org/article/10.1088/1361-6560/abe838/pdf$$EPDF$$P50$$Giop$$H</linktopdf><link.rule.ids>314,780,784,27915,27916,53837,53884</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33729998$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Shi, Feng</creatorcontrib><creatorcontrib>Xia, Liming</creatorcontrib><creatorcontrib>Shan, Fei</creatorcontrib><creatorcontrib>Song, Bin</creatorcontrib><creatorcontrib>Wu, Dijia</creatorcontrib><creatorcontrib>Wei, Ying</creatorcontrib><creatorcontrib>Yuan, Huan</creatorcontrib><creatorcontrib>Jiang, Huiting</creatorcontrib><creatorcontrib>He, Yichu</creatorcontrib><creatorcontrib>Gao, Yaozong</creatorcontrib><creatorcontrib>Sui, He</creatorcontrib><creatorcontrib>Shen, Dinggang</creatorcontrib><title>Large-scale screening to distinguish between COVID-19 and community-acquired pneumonia using infection size-aware classification</title><title>Physics in medicine & biology</title><addtitle>PMB</addtitle><addtitle>Phys. Med. Biol</addtitle><description>The worldwide spread of coronavirus disease (COVID-19) has become a threat to global public health. It is of great importance to rapidly and accurately screen and distinguish patients with COVID-19 from those with community-acquired pneumonia (CAP). In this study, a total of 1,658 patients with COVID-19 and 1,027 CAP patients underwent thin-section CT and were enrolled. All images were preprocessed to obtain the segmentations of infections and lung fields. A set of handcrafted location-specific features was proposed to best capture the COVID-19 distribution pattern, in comparison to the conventional CT severity score (CT-SS) and radiomics features. An infection size-aware random forest method (iSARF) was proposed for discriminating COVID-19 from CAP. Experimental results show that the proposed method yielded its best performance when using the handcrafted features, with a sensitivity of 90.7%, a specificity of 87.2%, and an accuracy of 89.4% over state-of-the-art classifiers. Additional tests on 734 subjects, with thick slice images, demonstrates great generalizability. It is anticipated that our proposed framework could assist clinical decision making.</description><subject>Adult</subject><subject>Aged</subject><subject>Community-Acquired Infections - diagnostic imaging</subject><subject>COVID-19</subject><subject>COVID-19 - diagnostic imaging</subject><subject>decision tree</subject><subject>Diagnosis, Computer-Assisted</subject><subject>Diagnosis, Differential</subject><subject>Female</subject><subject>Humans</subject><subject>Image Processing, Computer-Assisted</subject><subject>Lung - diagnostic imaging</subject><subject>Lung - virology</subject><subject>Male</subject><subject>Middle Aged</subject><subject>pneumonia</subject><subject>Pneumonia - diagnostic imaging</subject><subject>random forest</subject><subject>Reproducibility of Results</subject><subject>Retrospective Studies</subject><subject>Sensitivity and Specificity</subject><subject>size-aware</subject><subject>Tomography, X-Ray Computed</subject><issn>0031-9155</issn><issn>1361-6560</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp9kb9v1TAQxy0Eoq-FnQl5gwFTO3Yce0SvUCo9qQOI1fKPS3GVOKkdqyoTfzqJXumEmHzyfe4r3ecQesPoR0aVOmdcMiJbSc-tA8XVM7R7-nqOdpRyRjRr2xN0WsotpYypRrxEJ5x3jdZa7dDvg803QIq3A-DiM0CK6QYvEw6xLGtZY_mJHSz3awfvr39cXRCmsU0B-2kca4rLA7H-rsYMAc8J6jilaHEtW0xMPfglTgmX-AuIvbcZsB9sKbGP3m6dV-hFb4cCrx_fM_Tty-fv-6_kcH15tf90IF4wupAgex1ccJ66TiihrXAStPOqFVIr6jvVaBm0CE7QIAUH3SnRd1Z2knPPz9D7Y-qcp7sKZTFjLB6GwSaYajFNSxtFO8m6FaVH1OeplAy9mXMcbX4wjJrNutkUm02xOVpfR94-plc3Qnga-Kt5BT4cgTjN5naqOa2r_i_v3T_weXRGSiMNle16WDOHnv8BcTSatA</recordid><startdate>20210321</startdate><enddate>20210321</enddate><creator>Shi, Feng</creator><creator>Xia, Liming</creator><creator>Shan, Fei</creator><creator>Song, Bin</creator><creator>Wu, Dijia</creator><creator>Wei, Ying</creator><creator>Yuan, Huan</creator><creator>Jiang, Huiting</creator><creator>He, Yichu</creator><creator>Gao, Yaozong</creator><creator>Sui, He</creator><creator>Shen, Dinggang</creator><general>IOP Publishing</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>7X8</scope></search><sort><creationdate>20210321</creationdate><title>Large-scale screening to distinguish between COVID-19 and community-acquired pneumonia using infection size-aware classification</title><author>Shi, Feng ; Xia, Liming ; Shan, Fei ; Song, Bin ; Wu, Dijia ; Wei, Ying ; Yuan, Huan ; Jiang, Huiting ; He, Yichu ; Gao, Yaozong ; Sui, He ; Shen, Dinggang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c410t-d6f9dbdbc0b74849a4b6e9bc8546980c78296d94db40d643e9784f7a67633c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Adult</topic><topic>Aged</topic><topic>Community-Acquired Infections - diagnostic imaging</topic><topic>COVID-19</topic><topic>COVID-19 - diagnostic imaging</topic><topic>decision tree</topic><topic>Diagnosis, Computer-Assisted</topic><topic>Diagnosis, Differential</topic><topic>Female</topic><topic>Humans</topic><topic>Image Processing, Computer-Assisted</topic><topic>Lung - diagnostic imaging</topic><topic>Lung - virology</topic><topic>Male</topic><topic>Middle Aged</topic><topic>pneumonia</topic><topic>Pneumonia - diagnostic imaging</topic><topic>random forest</topic><topic>Reproducibility of Results</topic><topic>Retrospective Studies</topic><topic>Sensitivity and Specificity</topic><topic>size-aware</topic><topic>Tomography, X-Ray Computed</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Shi, Feng</creatorcontrib><creatorcontrib>Xia, Liming</creatorcontrib><creatorcontrib>Shan, Fei</creatorcontrib><creatorcontrib>Song, Bin</creatorcontrib><creatorcontrib>Wu, Dijia</creatorcontrib><creatorcontrib>Wei, Ying</creatorcontrib><creatorcontrib>Yuan, Huan</creatorcontrib><creatorcontrib>Jiang, Huiting</creatorcontrib><creatorcontrib>He, Yichu</creatorcontrib><creatorcontrib>Gao, Yaozong</creatorcontrib><creatorcontrib>Sui, He</creatorcontrib><creatorcontrib>Shen, Dinggang</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Physics in medicine & biology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shi, Feng</au><au>Xia, Liming</au><au>Shan, Fei</au><au>Song, Bin</au><au>Wu, Dijia</au><au>Wei, Ying</au><au>Yuan, Huan</au><au>Jiang, Huiting</au><au>He, Yichu</au><au>Gao, Yaozong</au><au>Sui, He</au><au>Shen, Dinggang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Large-scale screening to distinguish between COVID-19 and community-acquired pneumonia using infection size-aware classification</atitle><jtitle>Physics in medicine & biology</jtitle><stitle>PMB</stitle><addtitle>Phys. Med. Biol</addtitle><date>2021-03-21</date><risdate>2021</risdate><volume>66</volume><issue>6</issue><spage>065031</spage><epage>065031</epage><pages>065031-065031</pages><issn>0031-9155</issn><eissn>1361-6560</eissn><coden>PHMBA7</coden><abstract>The worldwide spread of coronavirus disease (COVID-19) has become a threat to global public health. It is of great importance to rapidly and accurately screen and distinguish patients with COVID-19 from those with community-acquired pneumonia (CAP). In this study, a total of 1,658 patients with COVID-19 and 1,027 CAP patients underwent thin-section CT and were enrolled. All images were preprocessed to obtain the segmentations of infections and lung fields. A set of handcrafted location-specific features was proposed to best capture the COVID-19 distribution pattern, in comparison to the conventional CT severity score (CT-SS) and radiomics features. An infection size-aware random forest method (iSARF) was proposed for discriminating COVID-19 from CAP. Experimental results show that the proposed method yielded its best performance when using the handcrafted features, with a sensitivity of 90.7%, a specificity of 87.2%, and an accuracy of 89.4% over state-of-the-art classifiers. Additional tests on 734 subjects, with thick slice images, demonstrates great generalizability. It is anticipated that our proposed framework could assist clinical decision making.</abstract><cop>England</cop><pub>IOP Publishing</pub><pmid>33729998</pmid><doi>10.1088/1361-6560/abe838</doi><tpages>11</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0031-9155 |
| ispartof | Physics in medicine & biology, 2021-03, Vol.66 (6), p.065031-065031 |
| issn | 0031-9155 1361-6560 |
| language | eng |
| recordid | cdi_iop_journals_10_1088_1361_6560_abe838 |
| source | Institute of Physics Journals; MEDLINE |
| subjects | Adult Aged Community-Acquired Infections - diagnostic imaging COVID-19 COVID-19 - diagnostic imaging decision tree Diagnosis, Computer-Assisted Diagnosis, Differential Female Humans Image Processing, Computer-Assisted Lung - diagnostic imaging Lung - virology Male Middle Aged pneumonia Pneumonia - diagnostic imaging random forest Reproducibility of Results Retrospective Studies Sensitivity and Specificity size-aware Tomography, X-Ray Computed |
| title | Large-scale screening to distinguish between COVID-19 and community-acquired pneumonia using infection size-aware classification |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T20%3A04%3A49IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_iop_j&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Large-scale%20screening%20to%20distinguish%20between%20COVID-19%20and%20community-acquired%20pneumonia%20using%20infection%20size-aware%20classification&rft.jtitle=Physics%20in%20medicine%20&%20biology&rft.au=Shi,%20Feng&rft.date=2021-03-21&rft.volume=66&rft.issue=6&rft.spage=065031&rft.epage=065031&rft.pages=065031-065031&rft.issn=0031-9155&rft.eissn=1361-6560&rft.coden=PHMBA7&rft_id=info:doi/10.1088/1361-6560/abe838&rft_dat=%3Cproquest_iop_j%3E2502807617%3C/proquest_iop_j%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2502807617&rft_id=info:pmid/33729998&rfr_iscdi=true |