利用深度学习系统筛查新冠病毒肺炎

实时逆转录聚合酶链反应(RT-PCR)检测早期新冠病毒肺炎(COVID-19)患者的痰液或鼻咽拭子中的病毒RNA阳性率较低.同时,COVID-19的计算机断层扫描(CT)影像学的临床表现有其自身的特点,不同于甲型流感病毒性肺炎(IAVP)等其他类型的病毒性肺炎.本研究旨在应用深度学习技术,建立COVID-19、IAVP及健康人群肺部CT的早期筛查模型.本研究共采集618份CT样本,其中219份样本来自110例COVID-19患者(平均年龄50岁,其中男性63例,占57.3%),224份样本来自224例IAVP患者(平均年龄61岁,其中男性156例,占69.6%),175份样本来自健康人群(平均...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:工程(英文) 2020, Vol.6 (10), p.1122-中插82
Hauptverfasser: 徐小微, 蒋贤高, 马春莲, 杜鹏, 李旭坤, 吕双志, 俞亮, 倪勤, 陈燕飞, 苏俊威, 郎观晶, 李永涛, 赵宏, 刘俊, 徐凯进, 阮凌翔, 盛吉芳, 裘云庆, 吴炜, 梁廷波, 李兰娟
Format: Artikel
Sprache:chi
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 中插82
container_issue 10
container_start_page 1122
container_title 工程(英文)
container_volume 6
creator 徐小微
蒋贤高
马春莲
杜鹏
李旭坤
吕双志
俞亮
倪勤
陈燕飞
苏俊威
郎观晶
李永涛
赵宏
刘俊
徐凯进
阮凌翔
盛吉芳
裘云庆
吴炜
梁廷波
李兰娟
description 实时逆转录聚合酶链反应(RT-PCR)检测早期新冠病毒肺炎(COVID-19)患者的痰液或鼻咽拭子中的病毒RNA阳性率较低.同时,COVID-19的计算机断层扫描(CT)影像学的临床表现有其自身的特点,不同于甲型流感病毒性肺炎(IAVP)等其他类型的病毒性肺炎.本研究旨在应用深度学习技术,建立COVID-19、IAVP及健康人群肺部CT的早期筛查模型.本研究共采集618份CT样本,其中219份样本来自110例COVID-19患者(平均年龄50岁,其中男性63例,占57.3%),224份样本来自224例IAVP患者(平均年龄61岁,其中男性156例,占69.6%),175份样本来自健康人群(平均年龄39岁,其中男性97例,占55.4%).所有CT样本均来自浙江省三家COVID-19定点收治医院.我们首先利用胸部CT图像集的三维(3D)深度学习模型分割出候选感染区域,然后利用位置敏感机制深度学习网络将这些分离的图像归类为COVID-19、IAVP以及与感染无关(ITI)的图像,并且输出相应置信度得分.最后,用Noisy-OR贝叶斯函数计算每份CT病例的感染类型及总置信度.测试数据集的实验结果表明,从整体CT病例来看,本研究利用深度学习系统建立的COVID-19患者的早期筛查模型的总体准确率为86.7%.该模型有望成为一线临床医生诊断COVID-19的一种有效的辅助方法.
format Article
fullrecord <record><control><sourceid>wanfang_jour</sourceid><recordid>TN_cdi_wanfang_journals_gc_e202010012</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><wanfj_id>gc_e202010012</wanfj_id><sourcerecordid>gc_e202010012</sourcerecordid><originalsourceid>FETCH-wanfang_journals_gc_e2020100123</originalsourceid><addsrcrecordid>eNpjYeA0MrA01bUwsLTkYOAtLs5MMjAyNDMyMDAy4mQweNqx8vmUFc-2b3y6a9nTtcue7FzwfPPu57vnP187-9n8pc-mbXjatuD59NZn6ye9aNr1vKmPh4E1LTGnOJUXSnMzqLq5hjh76JYn5qUl5qXHZ-WXFuUBZeLTk-NTjQyMDAwNDAyNjIlVBwA-MkUk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>利用深度学习系统筛查新冠病毒肺炎</title><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><source>Alma/SFX Local Collection</source><creator>徐小微 ; 蒋贤高 ; 马春莲 ; 杜鹏 ; 李旭坤 ; 吕双志 ; 俞亮 ; 倪勤 ; 陈燕飞 ; 苏俊威 ; 郎观晶 ; 李永涛 ; 赵宏 ; 刘俊 ; 徐凯进 ; 阮凌翔 ; 盛吉芳 ; 裘云庆 ; 吴炜 ; 梁廷波 ; 李兰娟</creator><creatorcontrib>徐小微 ; 蒋贤高 ; 马春莲 ; 杜鹏 ; 李旭坤 ; 吕双志 ; 俞亮 ; 倪勤 ; 陈燕飞 ; 苏俊威 ; 郎观晶 ; 李永涛 ; 赵宏 ; 刘俊 ; 徐凯进 ; 阮凌翔 ; 盛吉芳 ; 裘云庆 ; 吴炜 ; 梁廷波 ; 李兰娟</creatorcontrib><description>实时逆转录聚合酶链反应(RT-PCR)检测早期新冠病毒肺炎(COVID-19)患者的痰液或鼻咽拭子中的病毒RNA阳性率较低.同时,COVID-19的计算机断层扫描(CT)影像学的临床表现有其自身的特点,不同于甲型流感病毒性肺炎(IAVP)等其他类型的病毒性肺炎.本研究旨在应用深度学习技术,建立COVID-19、IAVP及健康人群肺部CT的早期筛查模型.本研究共采集618份CT样本,其中219份样本来自110例COVID-19患者(平均年龄50岁,其中男性63例,占57.3%),224份样本来自224例IAVP患者(平均年龄61岁,其中男性156例,占69.6%),175份样本来自健康人群(平均年龄39岁,其中男性97例,占55.4%).所有CT样本均来自浙江省三家COVID-19定点收治医院.我们首先利用胸部CT图像集的三维(3D)深度学习模型分割出候选感染区域,然后利用位置敏感机制深度学习网络将这些分离的图像归类为COVID-19、IAVP以及与感染无关(ITI)的图像,并且输出相应置信度得分.最后,用Noisy-OR贝叶斯函数计算每份CT病例的感染类型及总置信度.测试数据集的实验结果表明,从整体CT病例来看,本研究利用深度学习系统建立的COVID-19患者的早期筛查模型的总体准确率为86.7%.该模型有望成为一线临床医生诊断COVID-19的一种有效的辅助方法.</description><identifier>ISSN: 2095-8099</identifier><language>chi</language><publisher>State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, National Clinical Research Center for Infectious Diseases, Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou 310003, China%Department of Infectious Disease, Wenzhou Central Hospital, Wenzhou 325000, China%Department of Infectious Disease, The First People's Hospital of Wenling, Wenling 317500, China%Artificial Intelligence Lab, Hangzhou AiSmartVision Co., Ltd., Hangzhou 310012, China%Department of Radiology, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou 310003, China%Department of Hepatobiliary and Pancreatic Surgery &amp; Key Lab of Pancreatic Diseases Research of Zhejiang Province &amp; The Innovation Centre for the Study of Pancreatic Diseases of Zhejiang Province &amp; Clinical Medical Research Center of Hepatobiliary and Pancreatic Diseases in Zhejiang Province &amp;Precision Innovation Center of the Diagnosis and Treatment of Hepatobiliary and Pancreatic Diseases of Zhejiang University, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou 310003, China</publisher><ispartof>工程(英文), 2020, Vol.6 (10), p.1122-中插82</ispartof><rights>Copyright © Wanfang Data Co. Ltd. All Rights Reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Uhttp://www.wanfangdata.com.cn/images/PeriodicalImages/gc-e/gc-e.jpg</thumbnail><link.rule.ids>314,780,784,4014</link.rule.ids></links><search><creatorcontrib>徐小微</creatorcontrib><creatorcontrib>蒋贤高</creatorcontrib><creatorcontrib>马春莲</creatorcontrib><creatorcontrib>杜鹏</creatorcontrib><creatorcontrib>李旭坤</creatorcontrib><creatorcontrib>吕双志</creatorcontrib><creatorcontrib>俞亮</creatorcontrib><creatorcontrib>倪勤</creatorcontrib><creatorcontrib>陈燕飞</creatorcontrib><creatorcontrib>苏俊威</creatorcontrib><creatorcontrib>郎观晶</creatorcontrib><creatorcontrib>李永涛</creatorcontrib><creatorcontrib>赵宏</creatorcontrib><creatorcontrib>刘俊</creatorcontrib><creatorcontrib>徐凯进</creatorcontrib><creatorcontrib>阮凌翔</creatorcontrib><creatorcontrib>盛吉芳</creatorcontrib><creatorcontrib>裘云庆</creatorcontrib><creatorcontrib>吴炜</creatorcontrib><creatorcontrib>梁廷波</creatorcontrib><creatorcontrib>李兰娟</creatorcontrib><title>利用深度学习系统筛查新冠病毒肺炎</title><title>工程(英文)</title><description>实时逆转录聚合酶链反应(RT-PCR)检测早期新冠病毒肺炎(COVID-19)患者的痰液或鼻咽拭子中的病毒RNA阳性率较低.同时,COVID-19的计算机断层扫描(CT)影像学的临床表现有其自身的特点,不同于甲型流感病毒性肺炎(IAVP)等其他类型的病毒性肺炎.本研究旨在应用深度学习技术,建立COVID-19、IAVP及健康人群肺部CT的早期筛查模型.本研究共采集618份CT样本,其中219份样本来自110例COVID-19患者(平均年龄50岁,其中男性63例,占57.3%),224份样本来自224例IAVP患者(平均年龄61岁,其中男性156例,占69.6%),175份样本来自健康人群(平均年龄39岁,其中男性97例,占55.4%).所有CT样本均来自浙江省三家COVID-19定点收治医院.我们首先利用胸部CT图像集的三维(3D)深度学习模型分割出候选感染区域,然后利用位置敏感机制深度学习网络将这些分离的图像归类为COVID-19、IAVP以及与感染无关(ITI)的图像,并且输出相应置信度得分.最后,用Noisy-OR贝叶斯函数计算每份CT病例的感染类型及总置信度.测试数据集的实验结果表明,从整体CT病例来看,本研究利用深度学习系统建立的COVID-19患者的早期筛查模型的总体准确率为86.7%.该模型有望成为一线临床医生诊断COVID-19的一种有效的辅助方法.</description><issn>2095-8099</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNpjYeA0MrA01bUwsLTkYOAtLs5MMjAyNDMyMDAy4mQweNqx8vmUFc-2b3y6a9nTtcue7FzwfPPu57vnP187-9n8pc-mbXjatuD59NZn6ye9aNr1vKmPh4E1LTGnOJUXSnMzqLq5hjh76JYn5qUl5qXHZ-WXFuUBZeLTk-NTjQyMDAwNDAyNjIlVBwA-MkUk</recordid><startdate>2020</startdate><enddate>2020</enddate><creator>徐小微</creator><creator>蒋贤高</creator><creator>马春莲</creator><creator>杜鹏</creator><creator>李旭坤</creator><creator>吕双志</creator><creator>俞亮</creator><creator>倪勤</creator><creator>陈燕飞</creator><creator>苏俊威</creator><creator>郎观晶</creator><creator>李永涛</creator><creator>赵宏</creator><creator>刘俊</creator><creator>徐凯进</creator><creator>阮凌翔</creator><creator>盛吉芳</creator><creator>裘云庆</creator><creator>吴炜</creator><creator>梁廷波</creator><creator>李兰娟</creator><general>State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, National Clinical Research Center for Infectious Diseases, Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou 310003, China%Department of Infectious Disease, Wenzhou Central Hospital, Wenzhou 325000, China%Department of Infectious Disease, The First People's Hospital of Wenling, Wenling 317500, China%Artificial Intelligence Lab, Hangzhou AiSmartVision Co., Ltd., Hangzhou 310012, China%Department of Radiology, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou 310003, China%Department of Hepatobiliary and Pancreatic Surgery &amp; Key Lab of Pancreatic Diseases Research of Zhejiang Province &amp; The Innovation Centre for the Study of Pancreatic Diseases of Zhejiang Province &amp; Clinical Medical Research Center of Hepatobiliary and Pancreatic Diseases in Zhejiang Province &amp;Precision Innovation Center of the Diagnosis and Treatment of Hepatobiliary and Pancreatic Diseases of Zhejiang University, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou 310003, China</general><scope>2B.</scope><scope>4A8</scope><scope>92I</scope><scope>93N</scope><scope>PSX</scope><scope>TCJ</scope></search><sort><creationdate>2020</creationdate><title>利用深度学习系统筛查新冠病毒肺炎</title><author>徐小微 ; 蒋贤高 ; 马春莲 ; 杜鹏 ; 李旭坤 ; 吕双志 ; 俞亮 ; 倪勤 ; 陈燕飞 ; 苏俊威 ; 郎观晶 ; 李永涛 ; 赵宏 ; 刘俊 ; 徐凯进 ; 阮凌翔 ; 盛吉芳 ; 裘云庆 ; 吴炜 ; 梁廷波 ; 李兰娟</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-wanfang_journals_gc_e2020100123</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>chi</language><creationdate>2020</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>徐小微</creatorcontrib><creatorcontrib>蒋贤高</creatorcontrib><creatorcontrib>马春莲</creatorcontrib><creatorcontrib>杜鹏</creatorcontrib><creatorcontrib>李旭坤</creatorcontrib><creatorcontrib>吕双志</creatorcontrib><creatorcontrib>俞亮</creatorcontrib><creatorcontrib>倪勤</creatorcontrib><creatorcontrib>陈燕飞</creatorcontrib><creatorcontrib>苏俊威</creatorcontrib><creatorcontrib>郎观晶</creatorcontrib><creatorcontrib>李永涛</creatorcontrib><creatorcontrib>赵宏</creatorcontrib><creatorcontrib>刘俊</creatorcontrib><creatorcontrib>徐凯进</creatorcontrib><creatorcontrib>阮凌翔</creatorcontrib><creatorcontrib>盛吉芳</creatorcontrib><creatorcontrib>裘云庆</creatorcontrib><creatorcontrib>吴炜</creatorcontrib><creatorcontrib>梁廷波</creatorcontrib><creatorcontrib>李兰娟</creatorcontrib><collection>Wanfang Data Journals - Hong Kong</collection><collection>WANFANG Data Centre</collection><collection>Wanfang Data Journals</collection><collection>万方数据期刊 - 香港版</collection><collection>China Online Journals (COJ)</collection><collection>China Online Journals (COJ)</collection><jtitle>工程(英文)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>徐小微</au><au>蒋贤高</au><au>马春莲</au><au>杜鹏</au><au>李旭坤</au><au>吕双志</au><au>俞亮</au><au>倪勤</au><au>陈燕飞</au><au>苏俊威</au><au>郎观晶</au><au>李永涛</au><au>赵宏</au><au>刘俊</au><au>徐凯进</au><au>阮凌翔</au><au>盛吉芳</au><au>裘云庆</au><au>吴炜</au><au>梁廷波</au><au>李兰娟</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>利用深度学习系统筛查新冠病毒肺炎</atitle><jtitle>工程(英文)</jtitle><date>2020</date><risdate>2020</risdate><volume>6</volume><issue>10</issue><spage>1122</spage><epage>中插82</epage><pages>1122-中插82</pages><issn>2095-8099</issn><abstract>实时逆转录聚合酶链反应(RT-PCR)检测早期新冠病毒肺炎(COVID-19)患者的痰液或鼻咽拭子中的病毒RNA阳性率较低.同时,COVID-19的计算机断层扫描(CT)影像学的临床表现有其自身的特点,不同于甲型流感病毒性肺炎(IAVP)等其他类型的病毒性肺炎.本研究旨在应用深度学习技术,建立COVID-19、IAVP及健康人群肺部CT的早期筛查模型.本研究共采集618份CT样本,其中219份样本来自110例COVID-19患者(平均年龄50岁,其中男性63例,占57.3%),224份样本来自224例IAVP患者(平均年龄61岁,其中男性156例,占69.6%),175份样本来自健康人群(平均年龄39岁,其中男性97例,占55.4%).所有CT样本均来自浙江省三家COVID-19定点收治医院.我们首先利用胸部CT图像集的三维(3D)深度学习模型分割出候选感染区域,然后利用位置敏感机制深度学习网络将这些分离的图像归类为COVID-19、IAVP以及与感染无关(ITI)的图像,并且输出相应置信度得分.最后,用Noisy-OR贝叶斯函数计算每份CT病例的感染类型及总置信度.测试数据集的实验结果表明,从整体CT病例来看,本研究利用深度学习系统建立的COVID-19患者的早期筛查模型的总体准确率为86.7%.该模型有望成为一线临床医生诊断COVID-19的一种有效的辅助方法.</abstract><pub>State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, National Clinical Research Center for Infectious Diseases, Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou 310003, China%Department of Infectious Disease, Wenzhou Central Hospital, Wenzhou 325000, China%Department of Infectious Disease, The First People's Hospital of Wenling, Wenling 317500, China%Artificial Intelligence Lab, Hangzhou AiSmartVision Co., Ltd., Hangzhou 310012, China%Department of Radiology, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou 310003, China%Department of Hepatobiliary and Pancreatic Surgery &amp; Key Lab of Pancreatic Diseases Research of Zhejiang Province &amp; The Innovation Centre for the Study of Pancreatic Diseases of Zhejiang Province &amp; Clinical Medical Research Center of Hepatobiliary and Pancreatic Diseases in Zhejiang Province &amp;Precision Innovation Center of the Diagnosis and Treatment of Hepatobiliary and Pancreatic Diseases of Zhejiang University, The First Affiliated Hospital, College of Medicine, Zhejiang University, Hangzhou 310003, China</pub></addata></record>
fulltext fulltext
identifier ISSN: 2095-8099
ispartof 工程(英文), 2020, Vol.6 (10), p.1122-中插82
issn 2095-8099
language chi
recordid cdi_wanfang_journals_gc_e202010012
source DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals; Alma/SFX Local Collection
title 利用深度学习系统筛查新冠病毒肺炎
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T00%3A03%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-wanfang_jour&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=%E5%88%A9%E7%94%A8%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E7%B3%BB%E7%BB%9F%E7%AD%9B%E6%9F%A5%E6%96%B0%E5%86%A0%E7%97%85%E6%AF%92%E8%82%BA%E7%82%8E&rft.jtitle=%E5%B7%A5%E7%A8%8B%EF%BC%88%E8%8B%B1%E6%96%87%EF%BC%89&rft.au=%E5%BE%90%E5%B0%8F%E5%BE%AE&rft.date=2020&rft.volume=6&rft.issue=10&rft.spage=1122&rft.epage=%E4%B8%AD%E6%8F%9282&rft.pages=1122-%E4%B8%AD%E6%8F%9282&rft.issn=2095-8099&rft_id=info:doi/&rft_dat=%3Cwanfang_jour%3Egc_e202010012%3C/wanfang_jour%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_wanfj_id=gc_e202010012&rfr_iscdi=true