Automated detection of 3D midline shift in spontaneous supratentorial intracerebral haemorrhage with non-contrast computed tomography using deep convolutional neural networks

Deep learning (DL)-based convolutional neural networks facilitate more accurate detection and rapid analysis of MLS. Our objective was to assess the feasibility of applying a DL-based convolutional neural network to non-contrast computed tomography (CT) for automated 2D/3D brain midline shift measur...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:American journal of translational research 2021-01, Vol.13 (10), p.11513-11521
Hauptverfasser: Xia, Xiaona, Zhang, Xiaoqian, Huang, Zhaodi, Ren, Qingguo, Li, Hui, Li, Ye, Liang, Kongming, Wang, Hao, Han, Kai, Meng, Xiangshui
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 11521
container_issue 10
container_start_page 11513
container_title American journal of translational research
container_volume 13
creator Xia, Xiaona
Zhang, Xiaoqian
Huang, Zhaodi
Ren, Qingguo
Li, Hui
Li, Ye
Liang, Kongming
Wang, Hao
Han, Kai
Meng, Xiangshui
description Deep learning (DL)-based convolutional neural networks facilitate more accurate detection and rapid analysis of MLS. Our objective was to assess the feasibility of applying a DL-based convolutional neural network to non-contrast computed tomography (CT) for automated 2D/3D brain midline shift measurement and outcome prediction after spontaneous intracerebral haemorrhage. In this retrospective study, 140 consecutive patients were referred for CT assessment of sICH from January 2014 to April 2019. The level of consciousness of patients was evaluated using the Glasgow Coma Scale (GCS) score, and the Glasgow Outcome Scale (GOS) score was calculated to classify the outcome. The distance of midline shift (MLS-D) and volume of midline shift (MLS-V) were automatically measured via DL methods. Patients were divided into three groups based on GCS scores: mild degree (GCS score: 13-15), moderate degree (GCS score: 9-12), and severe degree (GCS score: 3-8). Spearman’s correlation analysis revealed statistically significant (P
format Article
fullrecord <record><control><sourceid>pubmedcentral</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8581948</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>pubmedcentral_primary_oai_pubmedcentral_nih_gov_8581948</sourcerecordid><originalsourceid>FETCH-LOGICAL-p210t-14d6ee06c56e08cd0cfb62f188653c77e18be116b4833559f361f6e7fb8ca83e3</originalsourceid><addsrcrecordid>eNpVkE1qwzAQhU2hNGnaO-gCBiuyZXlTCOkvBLpp10aWR7ZaWxL6ScilesbKbTddPYY3897HXGRr3JQkZ7jEq-za-4-ioFVDt1fZipQ1o0Vdr7OvXQxm5gF61EMAEZTRyEhE7tGs-klpQH5UMiClkbdGB67BRI98tC5d6WCc4lNyg-MCHHQuTSOH2Tg38gHQSYURaaNzYZYdH5Aws41LYSo2g-N2PKPolR4SAdhk66OZ4gKSojRE9yPhZNynv8kuJZ883P7pJnt_fHjbP-eH16eX_e6Q2y0uQo7LngIUVFQUCib6QsiObiVmjFZE1DVg1gHGtCsZIVXVSEKxpFDLjgnOCJBNdveba2M3Qy9gYZ9a69TM3bk1XLX_Ha3GdjDHllUsfZ2Rb6O7fWA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Automated detection of 3D midline shift in spontaneous supratentorial intracerebral haemorrhage with non-contrast computed tomography using deep convolutional neural networks</title><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central</source><creator>Xia, Xiaona ; Zhang, Xiaoqian ; Huang, Zhaodi ; Ren, Qingguo ; Li, Hui ; Li, Ye ; Liang, Kongming ; Wang, Hao ; Han, Kai ; Meng, Xiangshui</creator><creatorcontrib>Xia, Xiaona ; Zhang, Xiaoqian ; Huang, Zhaodi ; Ren, Qingguo ; Li, Hui ; Li, Ye ; Liang, Kongming ; Wang, Hao ; Han, Kai ; Meng, Xiangshui</creatorcontrib><description>Deep learning (DL)-based convolutional neural networks facilitate more accurate detection and rapid analysis of MLS. Our objective was to assess the feasibility of applying a DL-based convolutional neural network to non-contrast computed tomography (CT) for automated 2D/3D brain midline shift measurement and outcome prediction after spontaneous intracerebral haemorrhage. In this retrospective study, 140 consecutive patients were referred for CT assessment of sICH from January 2014 to April 2019. The level of consciousness of patients was evaluated using the Glasgow Coma Scale (GCS) score, and the Glasgow Outcome Scale (GOS) score was calculated to classify the outcome. The distance of midline shift (MLS-D) and volume of midline shift (MLS-V) were automatically measured via DL methods. Patients were divided into three groups based on GCS scores: mild degree (GCS score: 13-15), moderate degree (GCS score: 9-12), and severe degree (GCS score: 3-8). Spearman’s correlation analysis revealed statistically significant (P&lt;0.01) positive correlation between GCS and MLS-D (r=0.709) and MLS-V (r=0.754). The AUC of MLS-V was slightly larger than that of MLS-D (0.831 vs 0.799, P=0.318) in the midline shifting group. The AUC of MLS-V was significantly larger than that of MLS-D (0.854 vs 0.736, P=0.03) in patients with severe degree GCS scores. The DL-based measurements of both MLS-D and MLS-V enable the assessment of consciousness and the prediction of the outcome of sICH. Compared to MLS-D, MLS-V measurement can better indicate mass effect and predict outcomes, particularly in severe cases.</description><identifier>EISSN: 1943-8141</identifier><identifier>PMID: 34786077</identifier><language>eng</language><publisher>e-Century Publishing Corporation</publisher><subject>Original</subject><ispartof>American journal of translational research, 2021-01, Vol.13 (10), p.11513-11521</ispartof><rights>AJTR Copyright © 2021 2021</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8581948/pdf/$$EPDF$$P50$$Gpubmedcentral$$H</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8581948/$$EHTML$$P50$$Gpubmedcentral$$H</linktohtml><link.rule.ids>230,314,723,776,780,881,53766,53768</link.rule.ids></links><search><creatorcontrib>Xia, Xiaona</creatorcontrib><creatorcontrib>Zhang, Xiaoqian</creatorcontrib><creatorcontrib>Huang, Zhaodi</creatorcontrib><creatorcontrib>Ren, Qingguo</creatorcontrib><creatorcontrib>Li, Hui</creatorcontrib><creatorcontrib>Li, Ye</creatorcontrib><creatorcontrib>Liang, Kongming</creatorcontrib><creatorcontrib>Wang, Hao</creatorcontrib><creatorcontrib>Han, Kai</creatorcontrib><creatorcontrib>Meng, Xiangshui</creatorcontrib><title>Automated detection of 3D midline shift in spontaneous supratentorial intracerebral haemorrhage with non-contrast computed tomography using deep convolutional neural networks</title><title>American journal of translational research</title><description>Deep learning (DL)-based convolutional neural networks facilitate more accurate detection and rapid analysis of MLS. Our objective was to assess the feasibility of applying a DL-based convolutional neural network to non-contrast computed tomography (CT) for automated 2D/3D brain midline shift measurement and outcome prediction after spontaneous intracerebral haemorrhage. In this retrospective study, 140 consecutive patients were referred for CT assessment of sICH from January 2014 to April 2019. The level of consciousness of patients was evaluated using the Glasgow Coma Scale (GCS) score, and the Glasgow Outcome Scale (GOS) score was calculated to classify the outcome. The distance of midline shift (MLS-D) and volume of midline shift (MLS-V) were automatically measured via DL methods. Patients were divided into three groups based on GCS scores: mild degree (GCS score: 13-15), moderate degree (GCS score: 9-12), and severe degree (GCS score: 3-8). Spearman’s correlation analysis revealed statistically significant (P&lt;0.01) positive correlation between GCS and MLS-D (r=0.709) and MLS-V (r=0.754). The AUC of MLS-V was slightly larger than that of MLS-D (0.831 vs 0.799, P=0.318) in the midline shifting group. The AUC of MLS-V was significantly larger than that of MLS-D (0.854 vs 0.736, P=0.03) in patients with severe degree GCS scores. The DL-based measurements of both MLS-D and MLS-V enable the assessment of consciousness and the prediction of the outcome of sICH. Compared to MLS-D, MLS-V measurement can better indicate mass effect and predict outcomes, particularly in severe cases.</description><subject>Original</subject><issn>1943-8141</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNpVkE1qwzAQhU2hNGnaO-gCBiuyZXlTCOkvBLpp10aWR7ZaWxL6ScilesbKbTddPYY3897HXGRr3JQkZ7jEq-za-4-ioFVDt1fZipQ1o0Vdr7OvXQxm5gF61EMAEZTRyEhE7tGs-klpQH5UMiClkbdGB67BRI98tC5d6WCc4lNyg-MCHHQuTSOH2Tg38gHQSYURaaNzYZYdH5Aws41LYSo2g-N2PKPolR4SAdhk66OZ4gKSojRE9yPhZNynv8kuJZ883P7pJnt_fHjbP-eH16eX_e6Q2y0uQo7LngIUVFQUCib6QsiObiVmjFZE1DVg1gHGtCsZIVXVSEKxpFDLjgnOCJBNdveba2M3Qy9gYZ9a69TM3bk1XLX_Ha3GdjDHllUsfZ2Rb6O7fWA</recordid><startdate>20210101</startdate><enddate>20210101</enddate><creator>Xia, Xiaona</creator><creator>Zhang, Xiaoqian</creator><creator>Huang, Zhaodi</creator><creator>Ren, Qingguo</creator><creator>Li, Hui</creator><creator>Li, Ye</creator><creator>Liang, Kongming</creator><creator>Wang, Hao</creator><creator>Han, Kai</creator><creator>Meng, Xiangshui</creator><general>e-Century Publishing Corporation</general><scope>5PM</scope></search><sort><creationdate>20210101</creationdate><title>Automated detection of 3D midline shift in spontaneous supratentorial intracerebral haemorrhage with non-contrast computed tomography using deep convolutional neural networks</title><author>Xia, Xiaona ; Zhang, Xiaoqian ; Huang, Zhaodi ; Ren, Qingguo ; Li, Hui ; Li, Ye ; Liang, Kongming ; Wang, Hao ; Han, Kai ; Meng, Xiangshui</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p210t-14d6ee06c56e08cd0cfb62f188653c77e18be116b4833559f361f6e7fb8ca83e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Original</topic><toplevel>online_resources</toplevel><creatorcontrib>Xia, Xiaona</creatorcontrib><creatorcontrib>Zhang, Xiaoqian</creatorcontrib><creatorcontrib>Huang, Zhaodi</creatorcontrib><creatorcontrib>Ren, Qingguo</creatorcontrib><creatorcontrib>Li, Hui</creatorcontrib><creatorcontrib>Li, Ye</creatorcontrib><creatorcontrib>Liang, Kongming</creatorcontrib><creatorcontrib>Wang, Hao</creatorcontrib><creatorcontrib>Han, Kai</creatorcontrib><creatorcontrib>Meng, Xiangshui</creatorcontrib><collection>PubMed Central (Full Participant titles)</collection><jtitle>American journal of translational research</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Xia, Xiaona</au><au>Zhang, Xiaoqian</au><au>Huang, Zhaodi</au><au>Ren, Qingguo</au><au>Li, Hui</au><au>Li, Ye</au><au>Liang, Kongming</au><au>Wang, Hao</au><au>Han, Kai</au><au>Meng, Xiangshui</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automated detection of 3D midline shift in spontaneous supratentorial intracerebral haemorrhage with non-contrast computed tomography using deep convolutional neural networks</atitle><jtitle>American journal of translational research</jtitle><date>2021-01-01</date><risdate>2021</risdate><volume>13</volume><issue>10</issue><spage>11513</spage><epage>11521</epage><pages>11513-11521</pages><eissn>1943-8141</eissn><abstract>Deep learning (DL)-based convolutional neural networks facilitate more accurate detection and rapid analysis of MLS. Our objective was to assess the feasibility of applying a DL-based convolutional neural network to non-contrast computed tomography (CT) for automated 2D/3D brain midline shift measurement and outcome prediction after spontaneous intracerebral haemorrhage. In this retrospective study, 140 consecutive patients were referred for CT assessment of sICH from January 2014 to April 2019. The level of consciousness of patients was evaluated using the Glasgow Coma Scale (GCS) score, and the Glasgow Outcome Scale (GOS) score was calculated to classify the outcome. The distance of midline shift (MLS-D) and volume of midline shift (MLS-V) were automatically measured via DL methods. Patients were divided into three groups based on GCS scores: mild degree (GCS score: 13-15), moderate degree (GCS score: 9-12), and severe degree (GCS score: 3-8). Spearman’s correlation analysis revealed statistically significant (P&lt;0.01) positive correlation between GCS and MLS-D (r=0.709) and MLS-V (r=0.754). The AUC of MLS-V was slightly larger than that of MLS-D (0.831 vs 0.799, P=0.318) in the midline shifting group. The AUC of MLS-V was significantly larger than that of MLS-D (0.854 vs 0.736, P=0.03) in patients with severe degree GCS scores. The DL-based measurements of both MLS-D and MLS-V enable the assessment of consciousness and the prediction of the outcome of sICH. Compared to MLS-D, MLS-V measurement can better indicate mass effect and predict outcomes, particularly in severe cases.</abstract><pub>e-Century Publishing Corporation</pub><pmid>34786077</pmid><tpages>9</tpages></addata></record>
fulltext fulltext
identifier EISSN: 1943-8141
ispartof American journal of translational research, 2021-01, Vol.13 (10), p.11513-11521
issn 1943-8141
language eng
recordid cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8581948
source Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central
subjects Original
title Automated detection of 3D midline shift in spontaneous supratentorial intracerebral haemorrhage with non-contrast computed tomography using deep convolutional neural networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T06%3A26%3A26IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-pubmedcentral&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Automated%20detection%20of%203D%20midline%20shift%20in%20spontaneous%20supratentorial%20intracerebral%20haemorrhage%20with%20non-contrast%20computed%20tomography%20using%20deep%20convolutional%20neural%20networks&rft.jtitle=American%20journal%20of%20translational%20research&rft.au=Xia,%20Xiaona&rft.date=2021-01-01&rft.volume=13&rft.issue=10&rft.spage=11513&rft.epage=11521&rft.pages=11513-11521&rft.eissn=1943-8141&rft_id=info:doi/&rft_dat=%3Cpubmedcentral%3Epubmedcentral_primary_oai_pubmedcentral_nih_gov_8581948%3C/pubmedcentral%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/34786077&rfr_iscdi=true