Development of a deep learning model to identify hyperdense MCA sign in patients with acute ischemic stroke
Purpose The aim of this study was to develop an interactive deep learning-assisted identification of the hyperdense middle cerebral artery (MCA) sign (HMCAS) on non-contrast computed tomography (CT) among patients with acute ischemic stroke. Materials and methods 35 HMCAS-positive and 39 HMCAS-negat...
Gespeichert in:
| Veröffentlicht in: | Japanese journal of radiology 2020-02, Vol.38 (2), p.112-117 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 117 |
|---|---|
| container_issue | 2 |
| container_start_page | 112 |
| container_title | Japanese journal of radiology |
| container_volume | 38 |
| creator | Shinohara, Yuki Takahashi, Noriyuki Lee, Yongbum Ohmura, Tomomi Kinoshita, Toshibumi |
| description | Purpose
The aim of this study was to develop an interactive deep learning-assisted identification of the hyperdense middle cerebral artery (MCA) sign (HMCAS) on non-contrast computed tomography (CT) among patients with acute ischemic stroke.
Materials and methods
35 HMCAS-positive and 39 HMCAS-negative samples extracted by 50-pixel-diameter circular regions of interest were obtained as training and validation datasets according to the consensus decisions of two experienced neuroradiologists. Data augmentation was performed to increase the number of training samples. A deep convolutional neural network (DCNN) (Xception) was used to classify input images as HMCAS-positive or -negative. Leave-one-case-out cross-validation was achieved to estimate sensitivity, specificity, and accuracy of the deep learning-based training model for identifying HMCAS.
Results
In terms of diagnostic performance, DCNN for HMCAS offered 82.9% sensitivity, 89.7% specificity, and 86.5% accuracy in leave-one-case-out cross-validation. Area under the receiver operating characteristic curve for HMCAS was 0.947 (95% confidence interval 0.895–0.998;
P |
| doi_str_mv | 10.1007/s11604-019-00894-4 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2311638648</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2351332277</sourcerecordid><originalsourceid>FETCH-LOGICAL-c399t-23252acbcc233ec3af166ae4e635ad4c69b45f0c3e01efb79bbf1df3913d9a373</originalsourceid><addsrcrecordid>eNp9kU9P3DAQxa0K1F22_QIckCUuXAJ2xuskx9VS_kggLq3Um-U4411DEqd2UrTfvoalVOqB03jk37x5mkfIMWfnnLHiInIumcgYrzLGykpk4hOZ81IWGWflz4P3d8Fn5CjGR8akACE-kxlwWUBVlXPydIm_sfVDh_1IvaWaNogDbVGH3vUb2vkGWzp66ppEOLuj292AITUR6f16RaPb9NT1dNCjS0Skz27cUm2mEamLZoudMzSOwT_hF3JodRvx61tdkB9X376vb7K7h-vb9eouM8nTmOWQL3NtamNyADSgLZdSo0AJS90II6taLC0zgIyjrYuqri1vLFQcmkpDAQtyttcdgv81YRxVl5xg2-oe_RRVDulwUEpRJvT0P_TRT6FP7hK15AB5XrwI5nvKBB9jQKuG4Doddooz9RKF2kehUhTqNQol0tDJm_RUd9i8j_y9fQJgD8T01W8w_Nv9gewfseeVCA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2351332277</pqid></control><display><type>article</type><title>Development of a deep learning model to identify hyperdense MCA sign in patients with acute ischemic stroke</title><source>SpringerLink Journals</source><creator>Shinohara, Yuki ; Takahashi, Noriyuki ; Lee, Yongbum ; Ohmura, Tomomi ; Kinoshita, Toshibumi</creator><creatorcontrib>Shinohara, Yuki ; Takahashi, Noriyuki ; Lee, Yongbum ; Ohmura, Tomomi ; Kinoshita, Toshibumi</creatorcontrib><description>Purpose
The aim of this study was to develop an interactive deep learning-assisted identification of the hyperdense middle cerebral artery (MCA) sign (HMCAS) on non-contrast computed tomography (CT) among patients with acute ischemic stroke.
Materials and methods
35 HMCAS-positive and 39 HMCAS-negative samples extracted by 50-pixel-diameter circular regions of interest were obtained as training and validation datasets according to the consensus decisions of two experienced neuroradiologists. Data augmentation was performed to increase the number of training samples. A deep convolutional neural network (DCNN) (Xception) was used to classify input images as HMCAS-positive or -negative. Leave-one-case-out cross-validation was achieved to estimate sensitivity, specificity, and accuracy of the deep learning-based training model for identifying HMCAS.
Results
In terms of diagnostic performance, DCNN for HMCAS offered 82.9% sensitivity, 89.7% specificity, and 86.5% accuracy in leave-one-case-out cross-validation. Area under the receiver operating characteristic curve for HMCAS was 0.947 (95% confidence interval 0.895–0.998;
P
< 0.05).
Conclusion
The deep learning method appears potentially beneficial for identifying HMCAS on non-contrast CT in patients with acute ischemic stroke.</description><identifier>ISSN: 1867-1071</identifier><identifier>EISSN: 1867-108X</identifier><identifier>DOI: 10.1007/s11604-019-00894-4</identifier><identifier>PMID: 31673998</identifier><language>eng</language><publisher>Tokyo: Springer Japan</publisher><subject>Artificial neural networks ; Computed tomography ; Confidence intervals ; Deep learning ; Diagnostic systems ; Image classification ; Imaging ; Ischemia ; Machine learning ; Medicine ; Medicine & Public Health ; Model accuracy ; Neural networks ; Nuclear Medicine ; Original Article ; Radiology ; Radiotherapy ; Sensitivity ; Stroke ; Training</subject><ispartof>Japanese journal of radiology, 2020-02, Vol.38 (2), p.112-117</ispartof><rights>Japan Radiological Society 2019</rights><rights>Japanese Journal of Radiology is a copyright of Springer, (2019). All Rights Reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c399t-23252acbcc233ec3af166ae4e635ad4c69b45f0c3e01efb79bbf1df3913d9a373</citedby><cites>FETCH-LOGICAL-c399t-23252acbcc233ec3af166ae4e635ad4c69b45f0c3e01efb79bbf1df3913d9a373</cites><orcidid>0000-0001-6586-4086</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/s11604-019-00894-4$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11604-019-00894-4$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,776,780,27901,27902,41464,42533,51294</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/31673998$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Shinohara, Yuki</creatorcontrib><creatorcontrib>Takahashi, Noriyuki</creatorcontrib><creatorcontrib>Lee, Yongbum</creatorcontrib><creatorcontrib>Ohmura, Tomomi</creatorcontrib><creatorcontrib>Kinoshita, Toshibumi</creatorcontrib><title>Development of a deep learning model to identify hyperdense MCA sign in patients with acute ischemic stroke</title><title>Japanese journal of radiology</title><addtitle>Jpn J Radiol</addtitle><addtitle>Jpn J Radiol</addtitle><description>Purpose
The aim of this study was to develop an interactive deep learning-assisted identification of the hyperdense middle cerebral artery (MCA) sign (HMCAS) on non-contrast computed tomography (CT) among patients with acute ischemic stroke.
Materials and methods
35 HMCAS-positive and 39 HMCAS-negative samples extracted by 50-pixel-diameter circular regions of interest were obtained as training and validation datasets according to the consensus decisions of two experienced neuroradiologists. Data augmentation was performed to increase the number of training samples. A deep convolutional neural network (DCNN) (Xception) was used to classify input images as HMCAS-positive or -negative. Leave-one-case-out cross-validation was achieved to estimate sensitivity, specificity, and accuracy of the deep learning-based training model for identifying HMCAS.
Results
In terms of diagnostic performance, DCNN for HMCAS offered 82.9% sensitivity, 89.7% specificity, and 86.5% accuracy in leave-one-case-out cross-validation. Area under the receiver operating characteristic curve for HMCAS was 0.947 (95% confidence interval 0.895–0.998;
P
< 0.05).
Conclusion
The deep learning method appears potentially beneficial for identifying HMCAS on non-contrast CT in patients with acute ischemic stroke.</description><subject>Artificial neural networks</subject><subject>Computed tomography</subject><subject>Confidence intervals</subject><subject>Deep learning</subject><subject>Diagnostic systems</subject><subject>Image classification</subject><subject>Imaging</subject><subject>Ischemia</subject><subject>Machine learning</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Model accuracy</subject><subject>Neural networks</subject><subject>Nuclear Medicine</subject><subject>Original Article</subject><subject>Radiology</subject><subject>Radiotherapy</subject><subject>Sensitivity</subject><subject>Stroke</subject><subject>Training</subject><issn>1867-1071</issn><issn>1867-108X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNp9kU9P3DAQxa0K1F22_QIckCUuXAJ2xuskx9VS_kggLq3Um-U4411DEqd2UrTfvoalVOqB03jk37x5mkfIMWfnnLHiInIumcgYrzLGykpk4hOZ81IWGWflz4P3d8Fn5CjGR8akACE-kxlwWUBVlXPydIm_sfVDh_1IvaWaNogDbVGH3vUb2vkGWzp66ppEOLuj292AITUR6f16RaPb9NT1dNCjS0Skz27cUm2mEamLZoudMzSOwT_hF3JodRvx61tdkB9X376vb7K7h-vb9eouM8nTmOWQL3NtamNyADSgLZdSo0AJS90II6taLC0zgIyjrYuqri1vLFQcmkpDAQtyttcdgv81YRxVl5xg2-oe_RRVDulwUEpRJvT0P_TRT6FP7hK15AB5XrwI5nvKBB9jQKuG4Doddooz9RKF2kehUhTqNQol0tDJm_RUd9i8j_y9fQJgD8T01W8w_Nv9gewfseeVCA</recordid><startdate>20200201</startdate><enddate>20200201</enddate><creator>Shinohara, Yuki</creator><creator>Takahashi, Noriyuki</creator><creator>Lee, Yongbum</creator><creator>Ohmura, Tomomi</creator><creator>Kinoshita, Toshibumi</creator><general>Springer Japan</general><general>Springer Nature B.V</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7QO</scope><scope>7RV</scope><scope>7TK</scope><scope>7U7</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</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>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BHPHI</scope><scope>C1K</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FR3</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>K9.</scope><scope>KB0</scope><scope>LK8</scope><scope>M0S</scope><scope>M1P</scope><scope>M7P</scope><scope>NAPCQ</scope><scope>P5Z</scope><scope>P62</scope><scope>P64</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-6586-4086</orcidid></search><sort><creationdate>20200201</creationdate><title>Development of a deep learning model to identify hyperdense MCA sign in patients with acute ischemic stroke</title><author>Shinohara, Yuki ; Takahashi, Noriyuki ; Lee, Yongbum ; Ohmura, Tomomi ; Kinoshita, Toshibumi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c399t-23252acbcc233ec3af166ae4e635ad4c69b45f0c3e01efb79bbf1df3913d9a373</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Artificial neural networks</topic><topic>Computed tomography</topic><topic>Confidence intervals</topic><topic>Deep learning</topic><topic>Diagnostic systems</topic><topic>Image classification</topic><topic>Imaging</topic><topic>Ischemia</topic><topic>Machine learning</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Model accuracy</topic><topic>Neural networks</topic><topic>Nuclear Medicine</topic><topic>Original Article</topic><topic>Radiology</topic><topic>Radiotherapy</topic><topic>Sensitivity</topic><topic>Stroke</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Shinohara, Yuki</creatorcontrib><creatorcontrib>Takahashi, Noriyuki</creatorcontrib><creatorcontrib>Lee, Yongbum</creatorcontrib><creatorcontrib>Ohmura, Tomomi</creatorcontrib><creatorcontrib>Kinoshita, Toshibumi</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Biotechnology Research Abstracts</collection><collection>Nursing & Allied Health Database</collection><collection>Neurosciences Abstracts</collection><collection>Toxicology Abstracts</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical 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>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>Technology Collection</collection><collection>Natural Science Collection</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Engineering Research Database</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Database (Alumni Edition)</collection><collection>ProQuest Biological Science Collection</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Biological Science Database</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>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>MEDLINE - Academic</collection><jtitle>Japanese journal of radiology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shinohara, Yuki</au><au>Takahashi, Noriyuki</au><au>Lee, Yongbum</au><au>Ohmura, Tomomi</au><au>Kinoshita, Toshibumi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Development of a deep learning model to identify hyperdense MCA sign in patients with acute ischemic stroke</atitle><jtitle>Japanese journal of radiology</jtitle><stitle>Jpn J Radiol</stitle><addtitle>Jpn J Radiol</addtitle><date>2020-02-01</date><risdate>2020</risdate><volume>38</volume><issue>2</issue><spage>112</spage><epage>117</epage><pages>112-117</pages><issn>1867-1071</issn><eissn>1867-108X</eissn><abstract>Purpose
The aim of this study was to develop an interactive deep learning-assisted identification of the hyperdense middle cerebral artery (MCA) sign (HMCAS) on non-contrast computed tomography (CT) among patients with acute ischemic stroke.
Materials and methods
35 HMCAS-positive and 39 HMCAS-negative samples extracted by 50-pixel-diameter circular regions of interest were obtained as training and validation datasets according to the consensus decisions of two experienced neuroradiologists. Data augmentation was performed to increase the number of training samples. A deep convolutional neural network (DCNN) (Xception) was used to classify input images as HMCAS-positive or -negative. Leave-one-case-out cross-validation was achieved to estimate sensitivity, specificity, and accuracy of the deep learning-based training model for identifying HMCAS.
Results
In terms of diagnostic performance, DCNN for HMCAS offered 82.9% sensitivity, 89.7% specificity, and 86.5% accuracy in leave-one-case-out cross-validation. Area under the receiver operating characteristic curve for HMCAS was 0.947 (95% confidence interval 0.895–0.998;
P
< 0.05).
Conclusion
The deep learning method appears potentially beneficial for identifying HMCAS on non-contrast CT in patients with acute ischemic stroke.</abstract><cop>Tokyo</cop><pub>Springer Japan</pub><pmid>31673998</pmid><doi>10.1007/s11604-019-00894-4</doi><tpages>6</tpages><orcidid>https://orcid.org/0000-0001-6586-4086</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1867-1071 |
| ispartof | Japanese journal of radiology, 2020-02, Vol.38 (2), p.112-117 |
| issn | 1867-1071 1867-108X |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2311638648 |
| source | SpringerLink Journals |
| subjects | Artificial neural networks Computed tomography Confidence intervals Deep learning Diagnostic systems Image classification Imaging Ischemia Machine learning Medicine Medicine & Public Health Model accuracy Neural networks Nuclear Medicine Original Article Radiology Radiotherapy Sensitivity Stroke Training |
| title | Development of a deep learning model to identify hyperdense MCA sign in patients with acute ischemic stroke |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T04%3A10%3A57IST&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=Development%20of%20a%20deep%20learning%20model%20to%20identify%20hyperdense%20MCA%20sign%20in%20patients%20with%20acute%20ischemic%20stroke&rft.jtitle=Japanese%20journal%20of%20radiology&rft.au=Shinohara,%20Yuki&rft.date=2020-02-01&rft.volume=38&rft.issue=2&rft.spage=112&rft.epage=117&rft.pages=112-117&rft.issn=1867-1071&rft.eissn=1867-108X&rft_id=info:doi/10.1007/s11604-019-00894-4&rft_dat=%3Cproquest_cross%3E2351332277%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=2351332277&rft_id=info:pmid/31673998&rfr_iscdi=true |