Article(id=1211269041751200394, tenantId=1146029695717560320, journalId=1189873630562394117, issueId=1211269034906088369, articleNumber=null, orderNo=null, doi=10.11855/j.issn.0577-7402.2021.03.12, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1594828800000, receivedDateStr=2020-07-16, revisedDate=1603641600000, revisedDateStr=2020-10-26, acceptedDate=null, acceptedDateStr=null, onlineDate=1766718643844, onlineDateStr=2025-12-26, pubDate=1616860800000, pubDateStr=2021-03-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1766718643844, onlineIssueDateStr=2025-12-26, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1766718643844, creator=13701087609, updateTime=1766718643844, updator=13701087609, issue=Issue{id=1211269034906088369, tenantId=1146029695717560320, journalId=1189873630562394117, year='2021', volume='46', issue='3', pageStart='213', pageEnd='318', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1766718642212, creator=13701087609, updateTime=1766718779849, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1211269612247838856, tenantId=1146029695717560320, journalId=1189873630562394117, issueId=1211269034906088369, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1211269612247838857, tenantId=1146029695717560320, journalId=1189873630562394117, issueId=1211269034906088369, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=286, endPage=293, ext={EN=ArticleExt(id=1211269042069967509, articleId=1211269041751200394, tenantId=1146029695717560320, journalId=1189873630562394117, language=EN, title=Application and progress of machine learning in coronary computed tomography angiography, columnId=1190243275882729994, journalTitle=Medical Journal of Chinese People’s Liberation Army, columnName=Review, runingTitle=null, highlight=null, articleAbstract=

Cardiac computed tomography angiography (CCTA) has become an important non-invasive method to evaluate coronary artery disease. With the extensive application and increased image analysis features, more demands on operational technique and efficiency are asked. Machine learning (ML) is the subarea of artificial intelligence (AI), which is completely data driven, by computer algorithm to identify and analyze the potential relationship of centralized variables in large data sets for realizing the prediction of external data. In the field of cardiac CT, the application of various ML algorithms would improve the efficiency and quality of CCTA, helping accurate lesion assessment and risk stratification. It also brings new applications in cardiac functional imaging. The applications of ML in cardiac CT have been reviewed in present paper including CT-image analysis, risk stratification, CT-myocardial perfusion and CT-fractional flow reserve.

, correspAuthors=Jun-Jie Yang, authorNote=null, correspAuthorsNote=
*E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Zi-Nuan Liu, Jun-Jie Yang, Yun-Dai Chen), CN=ArticleExt(id=1211269042464232119, articleId=1211269041751200394, tenantId=1146029695717560320, journalId=1189873630562394117, language=CN, title=机器学习在冠状动脉计算机断层扫描领域的应用及进展, columnId=1190243276029530637, journalTitle=解放军医学杂志, columnName=综述, runingTitle=null, highlight=null, articleAbstract=

心脏计算机断层扫描血管造影术(CCTA)已成为评估冠状动脉疾病的重要非侵入性手段,随着其在临床的广泛应用及图像分析特征的增加,CCTA图像评估对技术及时间的要求不断提高。机器学习(ML)是人工智能的分支领域,它完全由数据驱动,通过计算机算法对大型数据集中变量的潜在关系进行识别及分析,实现对外部数据的预测。在心脏CT领域,不同ML算法的应用可提高CCTA的成像效率及质量,有助于病变评估及风险分层,同时也为心脏功能学成像提供了新的应用。该文主要对ML在心脏CT图像分析、风险模型、CT心肌灌注及CT血流储备分数中的应用研究进展进行综述。

, correspAuthors=杨俊杰, authorNote=null, correspAuthorsNote=
杨俊杰,E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=+oGfpc0df0uZdxpdHQiYwA==, magXml=VTIK4aqEOUHrrOhWGYeEPQ==, pdfUrl=null, pdf=24Xieq4SZ+lMAFZotSFmtA==, pdfFileSize=2087717, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=P0uK9CqihQ6kQgPzQ2J5RQ==, mapNumber=null, authorCompany=null, fund=null, authors=

刘子暖,硕士研究生,主要从事冠状动脉计算机断层扫描方面的研究。E-mail:

, authorsList=刘子暖, 杨俊杰, 陈韵岱)}, authors=[Author(id=1211269042908828381, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liuzinuan1995@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1211269043026268901, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, authorId=1211269042908828381, language=EN, stringName=Zi-Nuan Liu, firstName=Zi-Nuan, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1Department of Cardiovascular Medicine, the First Medical Center of Chinese PLA General Hospital, Beijing 100853, China
2School of Medicine, Nankai University, Tianjin 300071, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1211269043126932207, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, authorId=1211269042908828381, language=CN, stringName=刘子暖, firstName=子暖, middleName=null, lastName=刘, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1解放军总医院第一医学中心心血管内科,北京 100853
2南开大学医学院,天津 300071, bio={"content":"

刘子暖,硕士研究生,主要从事冠状动脉计算机断层扫描方面的研究。E-mail:

"}, bioImg=null, bioContent=

刘子暖,硕士研究生,主要从事冠状动脉计算机断层扫描方面的研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1211269042690724552, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, xref=1, ext=[AuthorCompanyExt(id=1211269042694918858, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, companyId=1211269042690724552, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Cardiovascular Medicine, the First Medical Center of Chinese PLA General Hospital, Beijing 100853, China), AuthorCompanyExt(id=1211269042699113164, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, companyId=1211269042690724552, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1解放军总医院第一医学中心心血管内科,北京 100853)]), AuthorCompany(id=1211269042812359378, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, xref=2, ext=[AuthorCompanyExt(id=1211269042816553683, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, companyId=1211269042812359378, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Medicine, Nankai University, Tianjin 300071, China), AuthorCompanyExt(id=1211269042820747988, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, companyId=1211269042812359378, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2南开大学医学院,天津 300071)])]), Author(id=1211269043248567032, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=fearlessyang@126.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1211269043386979076, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, authorId=1211269043248567032, language=EN, stringName=Jun-Jie Yang, firstName=Jun-Jie, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1Department of Cardiovascular Medicine, the First Medical Center of Chinese PLA General Hospital, Beijing 100853, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1211269043496030989, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, authorId=1211269043248567032, language=CN, stringName=杨俊杰, firstName=俊杰, middleName=null, lastName=杨, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1解放军总医院第一医学中心心血管内科,北京 100853, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1211269042690724552, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, xref=1, ext=[AuthorCompanyExt(id=1211269042694918858, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, companyId=1211269042690724552, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Cardiovascular Medicine, the First Medical Center of Chinese PLA General Hospital, Beijing 100853, China), AuthorCompanyExt(id=1211269042699113164, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, companyId=1211269042690724552, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1解放军总医院第一医学中心心血管内科,北京 100853)])]), Author(id=1211269043571528469, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1211269043688968987, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, authorId=1211269043571528469, language=EN, stringName=Yun-Dai Chen, firstName=Yun-Dai, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Department of Cardiovascular Medicine, the First Medical Center of Chinese PLA General Hospital, Beijing 100853, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1211269043781243683, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, authorId=1211269043571528469, language=CN, stringName=陈韵岱, firstName=韵岱, middleName=null, lastName=陈, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1解放军总医院第一医学中心心血管内科,北京 100853, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1211269042690724552, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, xref=1, ext=[AuthorCompanyExt(id=1211269042694918858, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, companyId=1211269042690724552, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Cardiovascular Medicine, the First Medical Center of Chinese PLA General Hospital, Beijing 100853, China), AuthorCompanyExt(id=1211269042699113164, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, companyId=1211269042690724552, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1解放军总医院第一医学中心心血管内科,北京 100853)])])], keywords=[Keyword(id=1211269043932238643, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, language=EN, orderNo=1, keyword=artificial intelligence), Keyword(id=1211269044037096252, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, language=EN, orderNo=2, keyword=machine learning), Keyword(id=1211269044104205121, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, language=EN, orderNo=3, keyword=tomography, X-ray computed), Keyword(id=1211269044204868424, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, language=EN, orderNo=4, keyword=coronary artery disease), Keyword(id=1211269044284560208, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, language=CN, orderNo=1, keyword=人工智能), Keyword(id=1211269045547045719, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, language=CN, orderNo=2, keyword=机器学习), Keyword(id=1211269045647709019, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, language=CN, orderNo=3, keyword=体层摄影术,X线计算机), Keyword(id=1211269045744178019, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, language=CN, orderNo=4, keyword=冠状动脉疾病)], refs=[Reference(id=1211269046570455955, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=3, pageStart=407, pageEnd=477, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Knuuti J, Wijns W, Saraste A, journalName=Eur Heart J, refType=null, unstructuredReference=Knuuti J, Wijns W, Saraste A, et al. 2019 ESC Guidelines for the diagnosis and management of chronic coronary syndromes[J]. Eur Heart J, 2020, 41(3): 407-477., articleTitle=2019 ESC Guidelines for the diagnosis and management of chronic coronary syndromes, refAbstract=null), Reference(id=1211269046696285081, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2008, volume=52, issue=21, pageStart=1724, pageEnd=1732, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Budoff MJ, Dowe D, Jollis JG, journalName=J Am Coll Cardiol, refType=null, unstructuredReference=Budoff MJ, Dowe D, Jollis JG, et al. Diagnostic performance of 64-multidetector row coronary computed tomographic angiography for evaluation of coronary artery stenosis in individuals without known coronary artery disease: results from the prospective multicenter ACCURACY (Assessment by Coronary Computed Tomographic Angiography of Individuals Undergoing Invasive Coronary Angiography) trial[J]. J Am Coll Cardiol, 2008, 52(21): 1724-1732., articleTitle=Diagnostic performance of 64-multidetector row coronary computed tomographic angiography for evaluation of coronary artery stenosis in individuals without known coronary artery disease: results from the prospective multicenter ACCURACY (Assessment by Coronary Computed Tomographic Angiography of Individuals Undergoing Invasive Coronary Angiography) trial, refAbstract=null), Reference(id=1211269046822114204, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=12, issue=7 Pt 2, pageStart=1379, pageEnd=1387, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=Nakamura S, Kitagawa K, Goto Y, journalName=JACC Cardiovasc Imaging, refType=null, unstructuredReference=Nakamura S, Kitagawa K, Goto Y, et al. Incremental prognostic value of myocardial blood flow quantified with stress dynamic computed tomography perfusion imaging[J]. JACC Cardiovasc Imaging, 2019, 12(7 Pt 2): 1379-1387., articleTitle=Incremental prognostic value of myocardial blood flow quantified with stress dynamic computed tomography perfusion imaging, refAbstract=null), Reference(id=1211269046956331942, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2018, volume=11, issue=11, pageStart=1611, pageEnd=1621, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=Sørgaard MH, Linde JJ, Kühl JT, journalName=JACC Cardiovasc Imaging, refType=null, unstructuredReference=Sørgaard MH, Linde JJ, Kühl JT, et al. Value of myocardial perfusion assessment with coronary computed tomography angiography in patients with recent acute-onset chest pain[J]. JACC Cardiovasc Imaging, 2018, 11(11): 1611-1621., articleTitle=Value of myocardial perfusion assessment with coronary computed tomography angiography in patients with recent acute-onset chest pain, refAbstract=null), Reference(id=1211269047052800940, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=13, issue=3, pageStart=26, pageEnd=33, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=van Assen M, De Cecco CN, Eid M, journalName=J Cardiovasc Comput Tomogr, refType=null, unstructuredReference=van Assen M, De Cecco CN, Eid M, et al. Prognostic value of CT myocardial perfusion imaging and CT-derived fractional flow reserve for major adverse cardiac events in patients with coronary artery disease[J]. J Cardiovasc Comput Tomogr, 2019, 13(3): 26-33., articleTitle=Prognostic value of CT myocardial perfusion imaging and CT-derived fractional flow reserve for major adverse cardiac events in patients with coronary artery disease, refAbstract=null), Reference(id=1211269047195407286, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=45, issue=7, pageStart=735, pageEnd=741, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=Gong J, Du C, Zhong XG, journalName=Med J Chin PLA, refType=null, unstructuredReference=Gong J, Du C, Zhong XG, et al. Researches on the illness risk of essential hypertension complicated with coronary heart disease based on machine learning algorithm[J]. Med J Chin PLA, 2020, 45(7): 735-741., articleTitle=Researches on the illness risk of essential hypertension complicated with coronary heart disease based on machine learning algorithm, refAbstract=null), Reference(id=1211269047287681981, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=45, issue=7, pageStart=735, pageEnd=741, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=龚军, 杜超, 钟小钢, journalName=解放军医学杂志, refType=null, unstructuredReference=[龚军, 杜超, 钟小钢, 等. 基于机器学习算法的原发性高血压并发冠心病的患病风险研究[J]. 解放军医学杂志, 2020, 45(7): 735-741.], articleTitle=基于机器学习算法的原发性高血压并发冠心病的患病风险研究, refAbstract=null), Reference(id=1211269047384150978, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=29, issue=10, pageStart=5322, pageEnd=5329, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=Tatsugami F, Higaki T, Nakamura Y, journalName=Eur Radiol, refType=null, unstructuredReference=Tatsugami F, Higaki T, Nakamura Y, et al. Deep learning-based image restoration algorithm for coronary CT angiography[J]. Eur Radiol, 2019, 29(10): 5322-5329., articleTitle=Deep learning-based image restoration algorithm for coronary CT angiography, refAbstract=null), Reference(id=1211269047493202891, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=46, issue=2, pageStart=550, pageEnd=562, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=Kang E, Koo HJ, Yang DH, journalName=Med Phys, refType=null, unstructuredReference=Kang E, Koo HJ, Yang DH, et al. Cycle-consistent adversarial denoising network for multiphase coronary CT angiography[J]. Med Phys, 2019, 46(2): 550-562., articleTitle=Cycle-consistent adversarial denoising network for multiphase coronary CT angiography, refAbstract=null), Reference(id=1211269047606449101, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=184, issue=null, pageStart=105115, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=9, authorNames=Huang L, Jiang H, Li S, journalName=Comput Methods Programs Biomed, refType=null, unstructuredReference=Huang L, Jiang H, Li S, et al. Two stage residual CNN for texture denoising and structure enhancement on low dose CT image[J]. Comput Methods Programs Biomed, 2020, 184: 105115., articleTitle=Two stage residual CNN for texture denoising and structure enhancement on low dose CT image, refAbstract=null), Reference(id=1211269047723889620, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2017, volume=8, issue=2, pageStart=679, pageEnd=694, url=null, language=null, rfNumber=[10], rfOrder=10, authorNames=Chen H, Zhang Y, Zhang W, journalName=Biomed Opt Express, refType=null, unstructuredReference=Chen H, Zhang Y, Zhang W, et al. Low-dose CT via convolutional neural network[J]. Biomed Opt Express, 2017, 8(2): 679-694., articleTitle=Low-dose CT via convolutional neural network, refAbstract=null), Reference(id=1211269047837135834, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2018, volume=37, issue=6, pageStart=1522, pageEnd=1534, url=null, language=null, rfNumber=[11], rfOrder=11, authorNames=Shan H, Zhang Y, Yang Q, journalName=IEEE Trans Med Imaging, refType=null, unstructuredReference=Shan H, Zhang Y, Yang Q, et al. 3-D convolutional encoder-decoder network for low-dose CT via transfer learning from a 2-D trained network[J]. IEEE Trans Med Imaging, 2018, 37(6): 1522-1534., articleTitle=3-D convolutional encoder-decoder network for low-dose CT via transfer learning from a 2-D trained network, refAbstract=null), Reference(id=1211269047954576348, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2018, volume=37, issue=6, pageStart=1498, pageEnd=1510, url=null, language=null, rfNumber=[12], rfOrder=12, authorNames=Zheng X, Ravishankar S, Long Y, journalName=IEEE Trans Med Imaging, refType=null, unstructuredReference=Zheng X, Ravishankar S, Long Y, et al. PWLS-ULTRA: an efficient clustering and learning-based approach for low-dose 3D CT image reconstruction[J]. IEEE Trans Med Imaging, 2018, 37(6): 1498-1510., articleTitle=PWLS-ULTRA: an efficient clustering and learning-based approach for low-dose 3D CT image reconstruction, refAbstract=null), Reference(id=1211269048051045342, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=52, issue=null, pageStart=68, pageEnd=79, url=null, language=null, rfNumber=[13], rfOrder=13, authorNames=Lossau T, Nickisch H, Wissel T, journalName=Med Image Anal, refType=null, unstructuredReference=Lossau T, Nickisch H, Wissel T, et al. Motion artifact recognition and quantification in coronary CT angiography using convolutional neural networks[J]. Med Image Anal, 2019, 52: 68-79., articleTitle=Motion artifact recognition and quantification in coronary CT angiography using convolutional neural networks, refAbstract=null), Reference(id=1211269048164291554, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=76, issue=null, pageStart=101640, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=14, authorNames=Lossau Née Elss T, Nickisch H, Wissel T, journalName=Comput Med Imaging Graph, refType=null, unstructuredReference=Lossau Née Elss T, Nickisch H, Wissel T, et al. Motion estimation and correction in cardiac CT angiography images using convolutional neural networks[J]. Comput Med Imaging Graph, 2019, 76: 101640., articleTitle=Motion estimation and correction in cardiac CT angiography images using convolutional neural networks, refAbstract=null), Reference(id=1211269048239789031, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=61, issue=null, pageStart=101655, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=15, authorNames=Lossau Née Elss T, Nickisch H, Wissel T, journalName=Med Image Anal, refType=null, unstructuredReference=Lossau Née Elss T, Nickisch H, Wissel T, et al. Learning metal artifact reduction in cardiac CT images with moving pacemakers[J]. Med Image Anal, 2020, 61: 101655., articleTitle=Learning metal artifact reduction in cardiac CT images with moving pacemakers, refAbstract=null), Reference(id=1211269048361423851, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2018, volume=45, issue=12, pageStart=5376, pageEnd=5384, url=null, language=null, rfNumber=[15], rfOrder=16, authorNames=Park HS, Lee SM, Kim HP, journalName=Med Phys, refType=null, unstructuredReference=Park HS, Lee SM, Kim HP, et al. CT sinogram-consistency learning for metal-induced beam hardening correction[J]. Med Phys, 2018, 45(12): 5376-5384., articleTitle=CT sinogram-consistency learning for metal-induced beam hardening correction, refAbstract=null), Reference(id=1211269048453698544, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=1998, volume=208, issue=3, pageStart=807, pageEnd=814, url=null, language=null, rfNumber=[17], rfOrder=17, authorNames=Callister TQ, Cooil B, Raya SP, journalName=Radiology, refType=null, unstructuredReference=Callister TQ, Cooil B, Raya SP, et al. Coronary artery disease:improved reproducibility of calcium scoring with an electron-beam CT volumetric method[J]. Radiology, 1998, 208(3): 807-814., articleTitle=Coronary artery disease:improved reproducibility of calcium scoring with an electron-beam CT volumetric method, refAbstract=null), Reference(id=1211269048529196020, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2002, volume=223, issue=2, pageStart=474, pageEnd=480, url=null, language=null, rfNumber=[18], rfOrder=18, authorNames=Hong C, Becker CR, Schoepf UJ, journalName=Radiology, refType=null, unstructuredReference=Hong C, Becker CR, Schoepf UJ, et al. Coronary artery calcium:absolute quantification in nonenhanced and contrast-enhanced multi-detector row CT studies[J]. Radiology, 2002, 223(2): 474-480., articleTitle=Coronary artery calcium:absolute quantification in nonenhanced and contrast-enhanced multi-detector row CT studies, refAbstract=null), Reference(id=1211269048667608059, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=1990, volume=15, issue=4, pageStart=827, pageEnd=832, url=null, language=null, rfNumber=[19], rfOrder=19, authorNames=Agatston AS, Janowitz WR, Hildner FJ, journalName=J Am Coll Cardiol, refType=null, unstructuredReference=Agatston AS, Janowitz WR, Hildner FJ, et al. Quantification of coronary artery calcium using ultrafast computed tomography[J]. J Am Coll Cardiol, 1990, 15(4): 827-832., articleTitle=Quantification of coronary artery calcium using ultrafast computed tomography, refAbstract=null), Reference(id=1211269048768271359, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2015, volume=34, issue=9, pageStart=1867, pageEnd=1878, url=null, language=null, rfNumber=[20], rfOrder=20, authorNames=Wolterink JM, Leiner T, Takx RA, journalName=IEEE Trans Med Imaging, refType=null, unstructuredReference=Wolterink JM, Leiner T, Takx RA, et al. Automatic coronary calcium scoring in non-contrast-enhanced ECG-triggered cardiac CT with ambiguity detection[J]. IEEE Trans Med Imaging, 2015, 34(9): 1867-1878., articleTitle=Automatic coronary calcium scoring in non-contrast-enhanced ECG-triggered cardiac CT with ambiguity detection, refAbstract=null), Reference(id=1211269050001395717, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2016, volume=43, issue=5, pageStart=2174, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=21, authorNames=Yang G, Chen Y, Ning X, journalName=Med Phys, refType=null, unstructuredReference=Yang G, Chen Y, Ning X, et al. Automatic coronary calcium scoring using noncontrast and contrast CT images[J]. Med Phys, 2016, 43(5): 2174., articleTitle=Automatic coronary calcium scoring using noncontrast and contrast CT images, refAbstract=null), Reference(id=1211269050089476107, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2012, volume=31, issue=12, pageStart=2322, pageEnd=2334, url=null, language=null, rfNumber=[22], rfOrder=22, authorNames=Isgum I, Prokop M, Niemeijer M, journalName=IEEE Trans Med Imaging, refType=null, unstructuredReference=Isgum I, Prokop M, Niemeijer M, et al. Automatic coronary calcium scoring in low-dose chest computed tomography[J]. IEEE Trans Med Imaging, 2012, 31(12): 2322-2334., articleTitle=Automatic coronary calcium scoring in low-dose chest computed tomography, refAbstract=null), Reference(id=1211269050181750799, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2013, volume=20, issue=1, pageStart=1, pageEnd=9, url=null, language=null, rfNumber=[23], rfOrder=23, authorNames=Shahzad R, van Walsum T, Schaap M, journalName=Acad Radiol, refType=null, unstructuredReference=Shahzad R, van Walsum T, Schaap M, et al. Vessel specific coronary artery calcium scoring: an automatic system[J]. Acad Radiol, 2013, 20(1): 1-9., articleTitle=Vessel specific coronary artery calcium scoring: an automatic system, refAbstract=null), Reference(id=1211269050282414101, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2016, volume=34, issue=null, pageStart=123, pageEnd=136, url=null, language=null, rfNumber=[24], rfOrder=24, authorNames=Wolterink JM, Leiner T, de Vos BD, journalName=Med Image Anal, refType=null, unstructuredReference=Wolterink JM, Leiner T, de Vos BD, et al. Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks[J]. Med Image Anal, 2016, 34: 123-136., articleTitle=Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks, refAbstract=null), Reference(id=1211269050357911577, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2018, volume=37, issue=2, pageStart=615, pageEnd=625, url=null, language=null, rfNumber=[25], rfOrder=25, authorNames=Lessmann N, van Ginneken B, Zreik M, journalName=IEEE Trans Med Imaging, refType=null, unstructuredReference=Lessmann N, van Ginneken B, Zreik M, et al. Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions[J]. IEEE Trans Med Imaging, 2018, 37(2): 615-625., articleTitle=Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions, refAbstract=null), Reference(id=1211269050420826142, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=38, issue=9, pageStart=2127, pageEnd=2138, url=null, language=null, rfNumber=[26], rfOrder=26, authorNames=de Vos BD, Wolterink JM, Leiner T, journalName=IEEE Trans Med Imaging, refType=null, unstructuredReference=de Vos BD, Wolterink JM, Leiner T, et al. Direct automatic coronary calcium scoring in cardiac and chest CT[J]. IEEE Trans Med Imaging, 2019, 38(9): 2127-2138., articleTitle=Direct automatic coronary calcium scoring in cardiac and chest CT, refAbstract=null), Reference(id=1211269050487935009, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=295, issue=1, pageStart=66, pageEnd=79, url=null, language=null, rfNumber=[27], rfOrder=27, authorNames=van Velzen SGM, Lessmann N, Velthuis BK, journalName=Radiology, refType=null, unstructuredReference=van Velzen SGM, Lessmann N, Velthuis BK, et al. Deep learning for automatic calcium scoring in CT: validation using multiple cardiac CT and chest CT protocols[J]. Radiology, 2020, 295(1): 66-79., articleTitle=Deep learning for automatic calcium scoring in CT: validation using multiple cardiac CT and chest CT protocols, refAbstract=null), Reference(id=1211269050550849572, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=73, issue=19, pageStart=2413, pageEnd=2424, url=null, language=null, rfNumber=[28], rfOrder=28, authorNames=Lee JM, Choi KH, Koo BK, journalName=J Am Coll Cardiol, refType=null, unstructuredReference=Lee JM, Choi KH, Koo BK, et al. Prognostic implications of plaque characteristics and Stenosis severity in patients with coronary artery disease[J]. J Am Coll Cardiol, 2019, 73(19): 2413-2424., articleTitle=Prognostic implications of plaque characteristics and Stenosis severity in patients with coronary artery disease, refAbstract=null), Reference(id=1211269050630541351, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2014, volume=41, issue=8, pageStart=081912, pageEnd=null, url=null, language=null, rfNumber=[29], rfOrder=29, authorNames=Zhou C, Chan HP, Chughtai A, journalName=Med Phys, refType=null, unstructuredReference=Zhou C, Chan HP, Chughtai A, et al. Computerized analysis of coronary artery disease: performance evaluation of segmentation and tracking of coronary arteries in CT angiograms[J]. Med Phys, 2014, 41(8): 081912., articleTitle=Computerized analysis of coronary artery disease: performance evaluation of segmentation and tracking of coronary arteries in CT angiograms, refAbstract=null), Reference(id=1211269050731204653, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2014, volume=41, issue=8, pageStart=081901, pageEnd=null, url=null, language=null, rfNumber=[30], rfOrder=30, authorNames=Wei J, Zhou C, Chan HP, journalName=Med Phys, refType=null, unstructuredReference=Wei J, Zhou C, Chan HP, et al. Computerized detection of noncalcified plaques in coronary CT angiography: evaluation of topological soft gradient prescreening method and luminal analysis[J]. Med Phys, 2014, 41(8): 081901., articleTitle=Computerized detection of noncalcified plaques in coronary CT angiography: evaluation of topological soft gradient prescreening method and luminal analysis, refAbstract=null), Reference(id=1211269050815090737, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=9, issue=1, pageStart=47, pageEnd=null, url=null, language=null, rfNumber=[31], rfOrder=31, authorNames=Ghanem AM, Hamimi AH, Matta JR, journalName=Sci Rep, refType=null, unstructuredReference=Ghanem AM, Hamimi AH, Matta JR, et al. Automatic coronary wall and atherosclerotic plaque segmentation from 3D coronary CT angiography[J]. Sci Rep, 2019, 9(1): 47., articleTitle=Automatic coronary wall and atherosclerotic plaque segmentation from 3D coronary CT angiography, refAbstract=null), Reference(id=1211269050915754036, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2011, volume=6, issue=2, pageStart=163, pageEnd=174, url=null, language=null, rfNumber=[32], rfOrder=32, authorNames=Zuluaga MA, Magnin IE, Hernández Hoyos M, journalName=Int J Comput Assist Radiol Surg, refType=null, unstructuredReference=Zuluaga MA, Magnin IE, Hernández Hoyos M, et al. Automatic detection of abnormal vascular cross-sections based on density level detection and support vector machines[J]. Int J Comput Assist Radiol Surg, 2011, 6(2): 163-174., articleTitle=Automatic detection of abnormal vascular cross-sections based on density level detection and support vector machines, refAbstract=null), Reference(id=1211269051075137594, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=57, issue=1, pageStart=245, pageEnd=257, url=null, language=null, rfNumber=[33], rfOrder=33, authorNames=Zhao F, Wu B, Chen F, journalName=Med Biol Eng Comput, refType=null, unstructuredReference=Zhao F, Wu B, Chen F, et al. An automatic multi-class coronary atherosclerosis plaque detection and classification framework[J]. Med Biol Eng Comput, 2019, 57(1): 245-257., articleTitle=An automatic multi-class coronary atherosclerosis plaque detection and classification framework, refAbstract=null), Reference(id=1211269051184189504, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2017, volume=89, issue=null, pageStart=84, pageEnd=95, url=null, language=null, rfNumber=[34], rfOrder=34, authorNames=Jawaid MM, Riaz A, Rajani R, journalName=Comput Biol Med, refType=null, unstructuredReference=Jawaid MM, Riaz A, Rajani R, et al. Framework for detection and localization of coronary non-calcified plaques in cardiac CTA using mean radial profiles[J]. Comput Biol Med, 2017, 89: 84-95., articleTitle=Framework for detection and localization of coronary non-calcified plaques in cardiac CTA using mean radial profiles, refAbstract=null), Reference(id=1211269051259686980, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=38, issue=7, pageStart=1588, pageEnd=1598, url=null, language=null, rfNumber=[35], rfOrder=35, authorNames=Zreik M, van Hamersvelt RW, Wolterink JM, journalName=IEEE Trans Med Imaging, refType=null, unstructuredReference=Zreik M, van Hamersvelt RW, Wolterink JM, et al. A recurrent CNN for automatic detection and classification of coronary artery plaque and Stenosis in coronary CT angiography[J]. IEEE Trans Med Imaging, 2019, 38(7): 1588-1598., articleTitle=A recurrent CNN for automatic detection and classification of coronary artery plaque and Stenosis in coronary CT angiography, refAbstract=null), Reference(id=1211269051330990151, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2014, volume=18, issue=3, pageStart=939, pageEnd=945, url=null, language=null, rfNumber=[36], rfOrder=36, authorNames=Yamak D, Panse P, Pavlicek W, journalName=IEEE J Biomed Health Inform, refType=null, unstructuredReference=Yamak D, Panse P, Pavlicek W, et al. Non-calcified coronary atherosclerotic plaque characterization by dual energy computed tomography[J]. IEEE J Biomed Health Inform, 2014, 18(3): 939-945., articleTitle=Non-calcified coronary atherosclerotic plaque characterization by dual energy computed tomography, refAbstract=null), Reference(id=1211269051406487627, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=13, issue=2, pageStart=163, pageEnd=169, url=null, language=null, rfNumber=[37], rfOrder=37, authorNames=Masuda T, Nakaura T, Funama Y, journalName=J Cardiovasc Comput Tomogr, refType=null, unstructuredReference=Masuda T, Nakaura T, Funama Y, et al. Machine-learning integration of CT histogram analysis to evaluate the composition of atherosclerotic plaques: Validation with IB-IVUS[J]. J Cardiovasc Comput Tomogr, 2019, 13(2): 163-169., articleTitle=Machine-learning integration of CT histogram analysis to evaluate the composition of atherosclerotic plaques: Validation with IB-IVUS, refAbstract=null), Reference(id=1211269051469402189, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2018, volume=2018, issue=null, pageStart=834, pageEnd=837, url=null, language=null, rfNumber=[38], rfOrder=38, authorNames=Shi P, Xin J, Liu S, journalName=Annu Int Conf IEEE Eng Med Biol Soc, refType=null, unstructuredReference=Shi P, Xin J, Liu S, et al. Vulnerable plaque recognition based on attention model with deep convolutional neural network[J]. Annu Int Conf IEEE Eng Med Biol Soc, 2018, 2018: 834-837., articleTitle=Vulnerable plaque recognition based on attention model with deep convolutional neural network, refAbstract=null), Reference(id=1211269051586842706, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=293, issue=1, pageStart=89, pageEnd=96, url=null, language=null, rfNumber=[39], rfOrder=39, authorNames=Kolossváry M, Karády J, Kikuchi Y, journalName=Radiology, refType=null, unstructuredReference=Kolossváry M, Karády J, Kikuchi Y, et al. Radiomics versus visual and histogram-based assessment to identify atheromatous lesions at coronary CT angiography: an ex vivo study[J]. Radiology, 2019, 293(1): 89-96., articleTitle=Radiomics versus visual and histogram-based assessment to identify atheromatous lesions at coronary CT angiography: an ex vivo study, refAbstract=null), Reference(id=1211269051645562964, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2017, volume=38, issue=7, pageStart=500, pageEnd=507, url=null, language=null, rfNumber=[40], rfOrder=40, authorNames=Motwani M, Dey D, Berman DS, journalName=Eur Heart J, refType=null, unstructuredReference=Motwani M, Dey D, Berman DS, et al. Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis[J]. Eur Heart J, 2017, 38(7): 500-507., articleTitle=Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis, refAbstract=null), Reference(id=1211269051712671831, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2017, volume=121, issue=9, pageStart=1092, pageEnd=1101, url=null, language=null, rfNumber=[41], rfOrder=41, authorNames=Ambale-Venkatesh B, Yang XY, Wu CO, journalName=Circ Res, refType=null, unstructuredReference=Ambale-Venkatesh B, Yang XY, Wu CO, et al. Cardiovascular event prediction by machine learning: the multi-ethnic study of atherosclerosis[J]. Circ Res, 2017, 121(9): 1092-1101., articleTitle=Cardiovascular event prediction by machine learning: the multi-ethnic study of atherosclerosis, refAbstract=null), Reference(id=1211269051783975003, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2018, volume=12, issue=3, pageStart=204, pageEnd=209, url=null, language=null, rfNumber=[42], rfOrder=42, authorNames=van Rosendael AR, Maliakal G, Kolli KK, journalName=J Cardiovasc Comput Tomogr, refType=null, unstructuredReference=van Rosendael AR, Maliakal G, Kolli KK, et al. Maximization of the usage of coronary CTA derived plaque information using a machine learning based algorithm to improve risk stratification;insights from the CONFIRM registry[J]. J Cardiovasc Comput Tomogr, 2018, 12(3): 204-209., articleTitle=Maximization of the usage of coronary CTA derived plaque information using a machine learning based algorithm to improve risk stratification;insights from the CONFIRM registry, refAbstract=null), Reference(id=1211269051872055390, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=292, issue=2, pageStart=354, pageEnd=362, url=null, language=null, rfNumber=[43], rfOrder=43, authorNames=Johnson KM, Johnson HE, Zhao Y, journalName=Radiology, refType=null, unstructuredReference=Johnson KM, Johnson HE, Zhao Y, et al. Scoring of coronary artery disease characteristics on coronary CT angiograms by using machine learning[J]. Radiology, 2019, 292(2): 354-362., articleTitle=Scoring of coronary artery disease characteristics on coronary CT angiograms by using machine learning, refAbstract=null), Reference(id=1211269051972718692, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=3, pageStart=359, pageEnd=367, url=null, language=null, rfNumber=[44], rfOrder=44, authorNames=Al'Aref SJ, Maliakal G, Singh G, journalName=Eur Heart J, refType=null, unstructuredReference=Al'Aref SJ, Maliakal G, Singh G, et al. Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry[J]. Eur Heart J, 2020, 41(3): 359-367., articleTitle=Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry, refAbstract=null), Reference(id=1211269052077576294, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2015, volume=24, issue=1, pageStart=77, pageEnd=89, url=null, language=null, rfNumber=[45], rfOrder=45, authorNames=Xiong G, Kola D, Heo R, journalName=Med Image Anal, refType=null, unstructuredReference=Xiong G, Kola D, Heo R, et al. Myocardial perfusion analysis in cardiac computed tomography angiographic images at rest[J]. Med Image Anal, 2015, 24(1): 77-89., articleTitle=Myocardial perfusion analysis in cardiac computed tomography angiographic images at rest, refAbstract=null), Reference(id=1211269052161462379, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2018, volume=25, issue=1, pageStart=223, pageEnd=233, url=null, language=null, rfNumber=[46], rfOrder=46, authorNames=Han D, Lee JH, Rizvi A, journalName=J Nucl Cardiol, refType=null, unstructuredReference=Han D, Lee JH, Rizvi A, et al. Incremental role of resting myocardial computed tomography perfusion for predicting physiologically significant coronary artery disease: A machine learning approach[J]. J Nucl Cardiol, 2018, 25(1): 223-233., articleTitle=Incremental role of resting myocardial computed tomography perfusion for predicting physiologically significant coronary artery disease: A machine learning approach, refAbstract=null), Reference(id=1211269052249542766, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=29, issue=5, pageStart=2350, pageEnd=2359, url=null, language=null, rfNumber=[47], rfOrder=47, authorNames=van Hamersvelt RW, Zreik M, Voskuil M, journalName=Eur Radiol, refType=null, unstructuredReference=van Hamersvelt RW, Zreik M, Voskuil M, et al. Deep learning analysis of left ventricular myocardium in CT angiographic intermediate-degree coronary stenosis improves the diagnostic accuracy for identification of functionally significant stenosis[J]. Eur Radiol, 2019, 29(5): 2350-2359., articleTitle=Deep learning analysis of left ventricular myocardium in CT angiographic intermediate-degree coronary stenosis improves the diagnostic accuracy for identification of functionally significant stenosis, refAbstract=null), Reference(id=1211269052325040242, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=13, issue=1 Pt 1, pageStart=97, pageEnd=105, url=null, language=null, rfNumber=[48], rfOrder=48, authorNames=Patel MR, Nørgaard BL, Fairbairn TA, journalName=JACC Cardiovasc Imaging, refType=null, unstructuredReference=Patel MR, Nørgaard BL, Fairbairn TA, et al. 1-year impact on medical practice and clinical outcomes of FFRCT: the ADVANCE registry[J]. JACC Cardiovasc Imaging, 2020, 13(1 Pt 1): 97-105., articleTitle=1-year impact on medical practice and clinical outcomes of FFRCT: the ADVANCE registry, refAbstract=null), Reference(id=1211269052446675063, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=16, issue=1, pageStart=42, pageEnd=48, url=null, language=null, rfNumber=[49], rfOrder=49, authorNames=Wang ZQ, Zhou YJ, Zhao YX, journalName=J Geriatr Cardiol, refType=null, unstructuredReference=Wang ZQ, Zhou YJ, Zhao YX, et al. Diagnostic accuracy of a deep learning approach to calculate FFR from coronary CT angiography[J]. J Geriatr Cardiol, 2019, 16(1): 42-48., articleTitle=Diagnostic accuracy of a deep learning approach to calculate FFR from coronary CT angiography, refAbstract=null), Reference(id=1211269052526366842, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2016, volume=121, issue=1, pageStart=42, pageEnd=52, url=null, language=null, rfNumber=[50], rfOrder=50, authorNames=Itu L, Rapaka S, Passerini T, journalName=J Appl Physiol (1985), refType=null, unstructuredReference=Itu L, Rapaka S, Passerini T, et al. A machine-learning approach for computation of fractional flow reserve from coronary computed tomography[J]. J Appl Physiol (1985), 2016, 121(1): 42-52., articleTitle=A machine-learning approach for computation of fractional flow reserve from coronary computed tomography, refAbstract=null), Reference(id=1211269052601864318, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2018, volume=11, issue=6, pageStart=e007217, pageEnd=null, url=null, language=null, rfNumber=[51], rfOrder=51, authorNames=Coenen A, Kim YH, Kruk M, journalName=Circ Cardiovasc Imaging, refType=null, unstructuredReference=Coenen A, Kim YH, Kruk M, et al. Diagnostic accuracy of a machine-learning approach to coronary computed tomographic angiography-based fractional flow reserve: result from the MACHINE consortium[J]. Circ Cardiovasc Imaging, 2018, 11(6): e007217., articleTitle=Diagnostic accuracy of a machine-learning approach to coronary computed tomographic angiography-based fractional flow reserve: result from the MACHINE consortium, refAbstract=null), Reference(id=1211269052694139009, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2018, volume=288, issue=1, pageStart=64, pageEnd=72, url=null, language=null, rfNumber=[52], rfOrder=52, authorNames=Tesche C, De Cecco CN, Baumann S, journalName=Radiology, refType=null, unstructuredReference=Tesche C, De Cecco CN, Baumann S, et al. Coronary CT angiography-derived fractional flow reserve: machine learning algorithm versus computational fluid dynamics modeling[J]. Radiology, 2018, 288(1): 64-72., articleTitle=Coronary CT angiography-derived fractional flow reserve: machine learning algorithm versus computational fluid dynamics modeling, refAbstract=null), Reference(id=1211269052786413700, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=293, issue=2, pageStart=305, pageEnd=314, url=null, language=null, rfNumber=[53], rfOrder=53, authorNames=Li Y, Yu M, Dai X, journalName=Radiology, refType=null, unstructuredReference=Li Y, Yu M, Dai X, et al. Detection of hemodynamically significant coronary stenosis: CT myocardial perfusion versus machine learning CT fractional flow reserve[J]. Radiology, 2019, 293(2): 305-314., articleTitle=Detection of hemodynamically significant coronary stenosis: CT myocardial perfusion versus machine learning CT fractional flow reserve, refAbstract=null), Reference(id=1211269052887077000, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=9, issue=3, pageStart=714, pageEnd=null, url=null, language=null, rfNumber=[54], rfOrder=54, authorNames=Baumann S, Hirt M, Rott C, journalName=J Clin Med, refType=null, unstructuredReference=Baumann S, Hirt M, Rott C, et al. Comparison of machine learning computed tomography-based fractional flow reserve and coronary CT angiography-derived plaque characteristics with invasive resting full-cycle ratio[J]. J Clin Med, 2020, 9(3): 714., articleTitle=Comparison of machine learning computed tomography-based fractional flow reserve and coronary CT angiography-derived plaque characteristics with invasive resting full-cycle ratio, refAbstract=null), Reference(id=1211269052970963084, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=109, issue=6, pageStart=735, pageEnd=745, url=null, language=null, rfNumber=[55], rfOrder=55, authorNames=Baumann S, Hirt M, Schoepf UJ, journalName=Clin Res Cardiol, refType=null, unstructuredReference=Baumann S, Hirt M, Schoepf UJ, et al. Correlation of machine learning computed tomography-based fractional flow reserve with instantaneous wave free ratio to detect hemodynamically significant coronary stenosis[J]. Clin Res Cardiol, 2020, 109(6): 735-745., articleTitle=Correlation of machine learning computed tomography-based fractional flow reserve with instantaneous wave free ratio to detect hemodynamically significant coronary stenosis, refAbstract=null), Reference(id=1211269053071626383, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=35, issue=11, pageStart=1523, pageEnd=1533, url=null, language=null, rfNumber=[56], rfOrder=56, authorNames=Zhou F, Wang YN, Schoepf UJ, journalName=Can J Cardiol, refType=null, unstructuredReference=Zhou F, Wang YN, Schoepf UJ, et al. Diagnostic performance of machine learning based CT-FFR in detecting ischemia in myocardial bridging and concomitant proximal atherosclerotic disease[J]. Can J Cardiol, 2019, 35(11): 1523-1533., articleTitle=Diagnostic performance of machine learning based CT-FFR in detecting ischemia in myocardial bridging and concomitant proximal atherosclerotic disease, refAbstract=null), Reference(id=1211269053163901074, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=13, issue=3, pageStart=760, pageEnd=770, url=null, language=null, rfNumber=[57], rfOrder=57, authorNames=Tesche C, Otani K, De Cecco CN, journalName=JACC Cardiovasc Imaging, refType=null, unstructuredReference=Tesche C, Otani K, De Cecco CN, et al. Influence of coronary calcium on diagnostic performance of machine learning CTFFR: results from MACHINE registry[J]. JACC Cardiovasc Imaging, 2020, 13(3): 760-770., articleTitle=Influence of coronary calcium on diagnostic performance of machine learning CTFFR: results from MACHINE registry, refAbstract=null), Reference(id=1211269053239398550, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=9, issue=3, pageStart=676, pageEnd=null, url=null, language=null, rfNumber=[58], rfOrder=58, authorNames=Lossnitzer D, Chandra L, Rutsch M, journalName=J Clin Med, refType=null, unstructuredReference=Lossnitzer D, Chandra L, Rutsch M, et al. Additional value of machine-learning computed tomographic angiography-based fractional flow reserve compared to standard computed tomographic angiography[J]. J Clin Med, 2020, 9(3): 676., articleTitle=Additional value of machine-learning computed tomographic angiography-based fractional flow reserve compared to standard computed tomographic angiography, refAbstract=null), Reference(id=1211269054464135320, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=13, issue=4, pageStart=980, pageEnd=990, url=null, language=null, rfNumber=[59], rfOrder=59, authorNames=Tang CX, Liu CY, Lu MJ, journalName=JACC Cardiovasc Imaging, refType=null, unstructuredReference=Tang CX, Liu CY, Lu MJ, et al. CT FFR for ischemia-specific CAD with a new computational fluid dynamics algorithm: a Chinese multicenter study[J]. JACC Cardiovasc Imaging, 2020, 13(4): 980-990., articleTitle=CT FFR for ischemia-specific CAD with a new computational fluid dynamics algorithm: a Chinese multicenter study, refAbstract=null), Reference(id=1211269054543827099, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2019, volume=73, issue=1, pageStart=58, pageEnd=64, url=null, language=null, rfNumber=[60], rfOrder=60, authorNames=Takamura K, Fujimoto S, Kawaguchi Y, journalName=J Cardiol, refType=null, unstructuredReference=Takamura K, Fujimoto S, Kawaguchi Y, et al. The usefulness of low radiation dose subtraction coronary computed tomography angiography for patients with calcification using 320-row area detector CT[J]. J Cardiol, 2019, 73(1): 58-64., articleTitle=The usefulness of low radiation dose subtraction coronary computed tomography angiography for patients with calcification using 320-row area detector CT, refAbstract=null), Reference(id=1211269054631907487, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, doi=null, pmid=null, pmcid=null, year=2020, volume=21, issue=1, pageStart=728, pageEnd=null, url=null, language=null, rfNumber=[61], rfOrder=61, authorNames=Yang J, Shan D, Dong M, journalName=Trials, refType=null, unstructuredReference=Yang J, Shan D, Dong M, et al. The effect of on-site CT-derived fractional flow reserve on the management of decision making for patients with stable chest pain (TARGET trial): objective, rationale, and design[J]. Trials, 2020, 21(1): 728., articleTitle=The effect of on-site CT-derived fractional flow reserve on the management of decision making for patients with stable chest pain (TARGET trial): objective, rationale, and design, refAbstract=null)], funds=[Fund(id=1211269045890978665, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, awardId=2016YFC1300304, language=EN, fundingSource=National Key Research and Development Program of China(2016YFC1300304), fundOrder=null, country=null), Fund(id=1211269046000030575, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, awardId=2016YFC1300304, language=CN, fundingSource=国家重点研发计划(2016YFC1300304), fundOrder=null, country=null), Fund(id=1211269046100693878, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, awardId=Z181100006218055, language=EN, fundingSource=Beijing NOVA Program(Z181100006218055), fundOrder=null, country=null), Fund(id=1211269046209745791, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, awardId=Z181100006218055, language=CN, fundingSource=北京市科技新星计划(Z181100006218055), fundOrder=null, country=null), Fund(id=1211269046322992005, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, awardId=2019MBD035, language=EN, fundingSource=Medical Big Data Program of PLAGH(2019MBD035), fundOrder=null, country=null), Fund(id=1211269046444626825, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, awardId=2019MBD035, language=CN, fundingSource=解放军总医院医疗大数据与人工智能研发项目(2019MBD035), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1211269042690724552, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, xref=1, ext=[AuthorCompanyExt(id=1211269042694918858, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, companyId=1211269042690724552, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Department of Cardiovascular Medicine, the First Medical Center of Chinese PLA General Hospital, Beijing 100853, China), AuthorCompanyExt(id=1211269042699113164, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, companyId=1211269042690724552, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1解放军总医院第一医学中心心血管内科,北京 100853)]), AuthorCompany(id=1211269042812359378, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, xref=2, ext=[AuthorCompanyExt(id=1211269042816553683, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, companyId=1211269042812359378, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Medicine, Nankai University, Tianjin 300071, China), AuthorCompanyExt(id=1211269042820747988, tenantId=1146029695717560320, journalId=1189873630562394117, articleId=1211269041751200394, companyId=1211269042812359378, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2南开大学医学院,天津 300071)])], figs=null, attaches=null, journal=Journal(id=1146441329971666965, delFlag=0, nameCn=解放军医学杂志, nameEn=Medical Journal of Chinese People’s Liberation Army, nameHistory1=null, nameHistory2=null, issn=0577-7402, eissn=null, cn=11-1056/R, coden=null, periodic=0, language=CN, oaType=是, ccby=CC BY-NC-ND, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=6srot5PcoYX30Oa4xeTmeg==, journalPrice=null, startedYear=null, abbrevIsoEn=null, journalRemark=null, publicationField=null, createdTime=1751262512917, updatedTime=1761735725513, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=M, firstLetterEn=M, subjectCode=Life Sciences, subjectName=Life Sciences, subjectCodeEn=Life Sciences, subjectNameEn=null, picCn=6srot5PcoYX30Oa4xeTmeg==, picEn=ELwBh5xqrSTlIs7HmSNt2Q==, jcr=null, cjcr=null, exts=[JournalExt(id=1190369167564968109, language=CN, name=解放军医学杂志, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1761735725537, updatedTime=1761735725537, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=#, submissionEditorUrl=#, submissionReviewUrl=#, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1190369167615299758, language=EN, name=Medical Journal of Chinese People’s Liberation Army, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1761735725549, updatedTime=1761735725549, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=#, submissionEditorUrl=#, submissionReviewUrl=#, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1189873630562394117, websiteList=[Website(id=1189873845923287108, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189873630562394117, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jfjyxzz/CN, language=CN, createTime=1761617631655, createBy=18614031015, updateTime=1761622010471, updateBy=18614031015, name=解放军医学杂志-中文, tplId=1146099689490845704, title=解放军医学杂志, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189924939378520839, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=articleTextType, value=kx, createTime=1761629813284, updateTime=1761629813284, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939353355012, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=banner, value=null, createTime=1761629813278, updateTime=1761629813278, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939399492362, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=grayFlag, value=0, createTime=1761629813289, updateTime=1761629813289, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939344966403, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=logo, value=https://castjournals.cast.org.cn/joweb/jfjyxzz/CN/file/pic?fileId=+zXjYVhun8ZOAA6+aKx2hw==, createTime=1761629813276, updateTime=1761629813276, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939412075276, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=minRunFlag, value=0, createTime=1761629813292, updateTime=1761629813292, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939374326534, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jfjyxzz/CN/file/pic, createTime=1761629813283, updateTime=1761629813283, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939407880971, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=silenceFlag, value=0, createTime=1761629813291, updateTime=1761629813291, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939361743621, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1761629813280, updateTime=1761629813280, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939386909448, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=themeColor, value=null, createTime=1761629813286, updateTime=1761629813286, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924939395298057, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873845923287108, code=themeStyle, value=null, createTime=1761629813288, updateTime=1761629813288, creator=18614031015, updator=18614031015)]), Website(id=1189873846057504839, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189873630562394117, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jfjyxzz/EN, language=EN, createTime=1761617631687, createBy=18614031015, updateTime=1761622030030, updateBy=18614031015, name=解放军医学杂志-英文, tplId=1146101810881728533, title=Medical Journal of Chinese People’s Liberation Army, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1189924968168223505, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=articleTextType, value=kx, createTime=1761629820148, updateTime=1761629820148, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968147251982, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=banner, value=null, createTime=1761629820143, updateTime=1761629820143, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968185000724, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=grayFlag, value=0, createTime=1761629820152, updateTime=1761629820152, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968138863373, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=logo, value=https://castjournals.cast.org.cn/joweb/jfjyxzz/EN/file/pic?fileId=+zXjYVhun8ZOAA6+aKx2hw==, createTime=1761629820141, updateTime=1761629820141, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968197583638, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=minRunFlag, value=0, createTime=1761629820155, updateTime=1761629820155, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968159834896, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jfjyxzz/EN/file/pic, createTime=1761629820146, updateTime=1761629820146, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968193389333, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=silenceFlag, value=0, createTime=1761629820154, updateTime=1761629820154, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968155640591, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1761629820145, updateTime=1761629820145, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968172417810, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=themeColor, value=null, createTime=1761629820149, updateTime=1761629820149, creator=18614031015, updator=18614031015), WebsiteProps(id=1189924968180806419, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189873846057504839, code=themeStyle, value=null, createTime=1761629820151, updateTime=1761629820151, creator=18614031015, updator=18614031015)])], journalTitle=解放军医学杂志, weixinUrl=null, journalUrl=http://zh.jfjyxzz.org.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Medical Journal of Chinese People’s Liberation Army, journalPhotoCn=6srot5PcoYX30Oa4xeTmeg==, journalPhotoEn=ELwBh5xqrSTlIs7HmSNt2Q==, journalFirstLetter=M, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/jfjyxzz/CN/10.11855/j.issn.0577-7402.2021.03.12, detailUrlEn=https://castjournals.cast.org.cn/joweb/jfjyxzz/EN/10.11855/j.issn.0577-7402.2021.03.12, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jfjyxzz/CN/PDF/10.11855/j.issn.0577-7402.2021.03.12, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jfjyxzz/EN/PDF/10.11855/j.issn.0577-7402.2021.03.12, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
机器学习在冠状动脉计算机断层扫描领域的应用及进展
收藏切换
PDF下载
刘子暖 1, 2 , 杨俊杰 1, * , 陈韵岱 1
解放军医学杂志 | 综述 2021,46(3): 286-293
收起
收藏切换
解放军医学杂志 | 综述 2021, 46(3): 286-293
机器学习在冠状动脉计算机断层扫描领域的应用及进展
全屏
刘子暖1, 2 , 杨俊杰1, * , 陈韵岱1
作者信息
  • 1解放军总医院第一医学中心心血管内科,北京 100853
  • 2南开大学医学院,天津 300071
  • 刘子暖,硕士研究生,主要从事冠状动脉计算机断层扫描方面的研究。E-mail:

通讯作者:

杨俊杰,E-mail:
Application and progress of machine learning in coronary computed tomography angiography
Zi-Nuan Liu1, 2 , Jun-Jie Yang1, * , Yun-Dai Chen1
Affiliations
  • 1Department of Cardiovascular Medicine, the First Medical Center of Chinese PLA General Hospital, Beijing 100853, China
  • 2School of Medicine, Nankai University, Tianjin 300071, China
出版时间: 2021-03-28 doi: 10.11855/j.issn.0577-7402.2021.03.12
文章导航
收藏切换

心脏计算机断层扫描血管造影术(CCTA)已成为评估冠状动脉疾病的重要非侵入性手段,随着其在临床的广泛应用及图像分析特征的增加,CCTA图像评估对技术及时间的要求不断提高。机器学习(ML)是人工智能的分支领域,它完全由数据驱动,通过计算机算法对大型数据集中变量的潜在关系进行识别及分析,实现对外部数据的预测。在心脏CT领域,不同ML算法的应用可提高CCTA的成像效率及质量,有助于病变评估及风险分层,同时也为心脏功能学成像提供了新的应用。该文主要对ML在心脏CT图像分析、风险模型、CT心肌灌注及CT血流储备分数中的应用研究进展进行综述。

人工智能  /  机器学习  /  体层摄影术,X线计算机  /  冠状动脉疾病

Cardiac computed tomography angiography (CCTA) has become an important non-invasive method to evaluate coronary artery disease. With the extensive application and increased image analysis features, more demands on operational technique and efficiency are asked. Machine learning (ML) is the subarea of artificial intelligence (AI), which is completely data driven, by computer algorithm to identify and analyze the potential relationship of centralized variables in large data sets for realizing the prediction of external data. In the field of cardiac CT, the application of various ML algorithms would improve the efficiency and quality of CCTA, helping accurate lesion assessment and risk stratification. It also brings new applications in cardiac functional imaging. The applications of ML in cardiac CT have been reviewed in present paper including CT-image analysis, risk stratification, CT-myocardial perfusion and CT-fractional flow reserve.

artificial intelligence  /  machine learning  /  tomography, X-ray computed  /  coronary artery disease
刘子暖, 杨俊杰, 陈韵岱. 机器学习在冠状动脉计算机断层扫描领域的应用及进展. 解放军医学杂志, 2021 , 46 (3) : 286 -293 . DOI: 10.11855/j.issn.0577-7402.2021.03.12
Zi-Nuan Liu, Jun-Jie Yang, Yun-Dai Chen. Application and progress of machine learning in coronary computed tomography angiography[J]. Medical Journal of Chinese People’s Liberation Army, 2021 , 46 (3) : 286 -293 . DOI: 10.11855/j.issn.0577-7402.2021.03.12
过去20年,心脏计算机断层扫描血管造影(cardiac computed tomography angiography,CCTA)设备与技术水平不断提高,逐渐成为评估冠状动脉疾病(coronary artery disease,CAD)的重要手段。2019年欧洲心脏病学会发表的《慢性冠脉综合征诊断与管理指南》推荐将CCTA作为疑似胸痛患者排除阻塞性CAD的初始检查手段(Ⅰ类推荐),对可疑或新诊断的CAD患者,可应用CCTA进行危险分层(Ⅰ类推荐)[1]。由于较高的阴性预测值及诊断准确性,CCTA被视为冠脉介入手术前可靠的CAD筛查手段[2]。此外,随着CT心肌灌注(computed tomography perfusion,CTP)及CT血流储备分数(computed tomography-fractional flow reserve,CT-FFR)等功能学评估手段的持续发展与深入研究,解剖学联合功能学诊断可有效减少下游的侵入性检查及治疗[3-5]
伴随着功能学成像的发展,人工智能(artificial intelligence,AI)在心血管领域的应用急剧增多。AI是对人类智能进行模拟、拓展及延伸的一门新兴学科,可以实现数据的自动解读,并在短时间内对大量数据集进行分析,建立并评估复杂模型的区分度及校准度。机器学习(machine learning,ML)是AI的一个分支,可从给定的训练数据集中运用不同的算法进行数据解析及学习,并以此为基础构建模型,从而对外部结果进行预判[6]。深度学习是一种利用人工神经网络实现机器学习的技术。当应用多层神经元节点进行计算时,整个体系获得的参数越多,对真实关系的模拟程度越强,该技术被称为深度神经网络(deep neural network,DNN)技术。
随着CCTA的广泛使用及图像分析特征的增加,图像后处理对技术及时间的要求不断提高,而ML不仅可以对此进行优化,还可增加图像预处理、风险分层等方面的新应用。目前,ML在心脏CT领域的相关循证医学证据迅速增多,本文对近年来ML在心脏CT领域,包括心脏CT图像分析、风险模型建立、CTP及CT-FFR等方面的应用进行综述。
ML是一门完全由数据驱动的计算机学科,它与普通算法的主要区别在于,普通算法只能接受给定的模式及关系,而ML可通过学习对数据中多维变量的潜在关系进行自动识别并建模,实现对外部数据的预判,使工作效率大大提高。根据训练数据集是否有学习标准,ML可分为监督学习、非监督学习、半监督学习及强化学习。监督学习主要用于解决分类及回归问题,常见算法包括k近邻(k-nearest neighbor,k-NN)、随机森林(random forest,RF)、支持向量机(support vector machines,SVM)、决策树(decision tree,DF)、逻辑回归及大部分神经网络。其中卷积神经网络(convolutional neural network,CNN)及DNN默认图像为输入层,通过卷积提取图像特征,配合若干全连接层完成图像特征分类,其容错能力好,泛化能力强,常用于处理图像相关问题。非监督学习无明确的学习目标,通过聚类算法寻找数据集中的规律性并进行分析,常用于无人工注释的数据。半监督学习的训练数据同时包括标注数据及非标注数据,可视为监督与非监督学习的结合。强化学习则主要解决序贯决策问题,在目前的临床研究中并不常用。
在图像重建及预处理中,对图像进行降噪处理及伪影修正可有效提高图像质量,为后续进一步图像分析提供保障。图像修正一般通过不同的滤波算法完成,根据应用域不同,可分为基于空间域及基于频域的降噪方法,通过在二维空间内对图像像素进行处理或在频域中识别噪声信息频谱差异,达到去噪的目的。这些算法多基于系统模型及数学统计模型,计算复杂,且涉及CT投影的原始数据,在实际研究中较难获得。ML对此进行简化,通过不同算法学习目标图像与标准图像间的非线性映射,进行端对端的直接学习,以此建立降噪模型。如Tatsugami等[7]提出的去噪过滤器,以高质量全模型迭代重建图像为目标,训练DNN模型,提高了混合迭代重建图像的质量,使得图像噪声由(23.0±4.6) HU降至(18.5±2.8) HU。当缺乏标准图像不能匹配样本对时,仍可使用非监督学习方法,如Kang等[8]提出的循环一致性生成对抗网络(cycle consistent generative adversarial network,Cycle GAN),通过对多相CCTA高、低剂量图像的映射关系进行学习,建立了降噪模型。
CT辐射剂量一直是CT研究领域的热点问题,辐射剂量的下降可减轻对人体的辐射伤害,但与此相伴的是图像信噪比的降低。降噪模型为此问题提供了一种可靠的解决方案。一些研究致力于运用ML算法构建低剂量CT降噪器,尤其是CNN[9-10]及生成对抗网络结构[11]。如Shan等[11]描述的GAN模型、Chen等[10]描述的3层CNN模型、Huang等[9]提出的两阶段残差CNN等。最近,还有研究将ML算法直接用于图像重建中,省去了重建后的降噪处理[12]
除了与CT系统设备及重建算法相关的噪声外,运动伪影及高密度伪影也是导致图像质量较差的常见因素。Lossau等[13]提出一种名为CoMoFACT的模型,将合成运动伪影用于监督学习,实现对冠脉伪影的识别及量化。在此基础上,训练后的CNN模型实现了对伪影的校正[14]。最近,该团队还提出了应用3组CNN对起搏器造成的金属伪影进行消除的方法[15],该方法已在9例临床案例中完成了测试,结果显示金属伪影明显减少。除了卷积网络外,还有研究使用U-net网络修正正弦图以达到抑制金属伪影的目的[16]
虽然ML在CT降噪及伪影校正方面取得了可喜的结果,但仍面临一些挑战。ML模型需要基于大量有代表性的数据进行训练,而部分研究对训练数据的质量要求较高,获取成本也较高,如上述金属伪影案例,这限制了训练数据集的样本量及多样性,导致训练后的模型泛化能力不足。Lossau等[13]通过人工模拟伪影解决了样本量不足的问题,但这种人为合成数据并不能代表所有真实的情况,样本多样性难以保证,在此情形下建立的模型是否会出现过度拟合问题令人担忧。此外,对于常见影响CCTA图像判读的严重钙化伪影及高密度支架伪影问题,相关研究较少。由于部分容积效应的影响,高CT衰减值区域的管腔边界不清,无法对其进一步评估,往往会导致无效检测或诊断准确性下降。如何在高CT衰减值背景下实现管腔识别及分割可能是该领域未来的最大挑战。
冠脉钙化检测作为一种CAD的筛查工具,是心血管事件的有力预测因子。其检测通常在非对比增强的心脏CT图像中进行,以质量分数[17]、体积分数[18]或Agatston评分[19]来定量表示钙化负荷,其中Agatston评分是最常用的冠脉钙化积分(coronary artery calcium score,CACS)计算方法。目前已有许多半自动化冠脉钙化检测方法,但仍离不开人工手动标注,而ML的引入为冠脉钙化自动检测提供了更多可能性。
冠脉钙化检测一般以130 HU为阈值对钙化斑块进行识别及分割,其中对非冠脉钙化的区分及钙化位置特征的描述一直是两大核心问题,特别是在非对比增强CT中,冠脉难以与周围组织相区分。目前一些ML算法通过对病变纹理、体积、形状等图像特征进行学习,使用k-NN、SVM、CNN等分类器实现了对冠脉钙化的识别。对于位置特征,Wolterink等[20]及Yang等[21]通过使用匹配的CCTA图集进行配准,获取非对比增强图像上的冠脉位置信息;Isgum等[22]通过设计地图集为冠脉钙化的空间特征提供概率信息;Shahzad等[23]将CCTA地图集注册到CT扫描中进行冠脉位置估计,引入标准化空间以获得位置特征。
与非对比增强CT不同,CCTA中由于对比剂的应用使血管显像更加明显,其位置特征可以不必通过提取冠脉树获得。Wolterink等[24]通过在心脏周围设置边界框,使用CNN分类器直接对该区域中所有体素进行识别,将体素在该区域内的坐标确定为位置特征。Lessmann等[25]提出的方法与之类似,但该方法主要应用于低剂量胸部CT扫描而非CCTA扫描图集中。最近还有研究回避了冠脉钙化分割问题[26],利用CNN结构直接回归计算CACS,将该方法应用于903例心脏CT及1687例胸部CT扫描图像中,获得的CACS与人工测量的CACS的类内相关系数达0.98,同时,该方法可在0.3 s内完成,计算效率远远超过其他方法。
目前已有的研究多致力于开发不同的ML算法解决冠脉钙化自动识别问题,这些方法大多仅应用于少量特定扫描图集中,当更换不同的扫描协议或CT扫描方案时,其性能尚不可知。van Velzen等[27]在最新研究中纳入用于低剂量肺癌筛查、正电子发射计算机断层扫描(PET)衰减校正、放射治疗计划及常规诊断目的的扫描图集,证实了深度学习算法在大量、多样化CT检查中的有效性。目前,临床中应用的冠脉钙化检测大多为半自动检测,需人工手动校正。基于ML算法的冠脉钙化全自动检测尚无统一的标准及规范化应用,难以在临床广泛开展,尤其是在缺少大量手动注释影像作为训练集且扫描协议难以统一的背景下,这对ML在该领域的下一步应用提出了巨大挑战。
CCTA的主要作用是对冠脉斑块进行分析,从而获得有指导意义的斑块特征。有研究发现,无症状患者中的斑块负荷(包括其数量、大小、形态等)是未来心血管不良事件的预测因子[28]。斑块分析通常在CT后处理系统中由人工手动完成,其时间成本及人工成本十分昂贵,且具有一定的人为主观性。ML基于数据进行的分析在很大程度上可提高效率,弥补这一缺点。
由于斑块分析仅在管腔内进行,部分斑块自动检测方法更关注管腔及血管壁的分割,以此作为斑块搜索的基础。Zhou等[29]提出了一种冠脉多尺度响应-滚动球囊区域生长法(MSCAR-RBG)用于提取冠状动脉树。Wei等[30]在此基础上,通过学习血管壁径向梯度的二维拓扑特征来检测非钙化斑块。Ghanem等[31]则将血管滤过器、区域生长与水平集算法相结合,分割血管壁来进行斑块检测,是首个通过3D CCTA图像数据输入进行管壁分割的框架。这些分割方法虽然有效地提取了管腔区域,使斑块检测更具有针对性,但其算法较为复杂,仅有少量研究开展。
另外一种常见的思路是在沿冠脉中心线的管腔截面中提取形状、强度及纹理特征,训练ML模型识别斑块。Zuluaga等[32]提出基于强度特征识别血管异常值以检测有无斑块;Zhao等[33]引入随机半径对称特征向量进行不同斑块类型的识别;Jawaid等[34]以平均径向轮廓为特征检测非钙化斑块。这几种检测方式均基于SVM模型进行。Zreik等[35]则提出了一种组合算法框架,应用CNN提取特征,通过递归神经网络(recurrent neural network,RNN)聚集特征,实现对斑块类型及狭窄程度的检测。
目前大多数研究仅可实现对斑块的粗略区分,即有无斑块、斑块类型(钙化、非钙化、混合斑块)及有无狭窄等,仅有少量研究对特定斑块类型进行了检测。如Yamak等[36]及Masuda等[37]对纤维斑块及脂质斑块的检测,Shi等[38]对易损斑块的识别。Kolossváry等[39]提出了一种识别组织学定义的晚期粥样硬化斑块的方法,该方法通过将组织学图像与体外CCTA扫描配准,确定CCTA上的参考标准,提取冠脉横断面特征,使用线性分类器将病变分为晚期或早期动脉粥样硬化。不同斑块类型对患者预后的影响不一,对高危斑块进行识别更有意义,但由于学习样本有限,模型难以达到广泛适用性。Kolossváry等[39]研究中的斑块类型由组织学切片定义,仅纳入7例患者的21根血管进行建模及验证,Masuda等[37]研究则以血管内超声(intravascular ultrasound,IVUS)的结果作为斑块分类标准,均难以获得大量样本,这大大限制了同类型研究的进一步开展。
目前,国内外均有使用基于ML的冠脉病变智能辅助诊断系统,如以色列斑马医疗研发的HealthCCS系统可针对钙化斑块进行分析,于2018年经美国FDA批准上市;我国CoronaryDoc冠心病辅助诊断系统可对易损斑块进行分析,进行冠脉血流动力学评估并给出血运重建术前规划,现已进入AI三类证绿色通道审批阶段。此外,随着更多的诸如“阿里AI”等人工智能平台的迅速发展,预计未来将有更多的人工智能辅助诊疗产品应用于临床实践。
风险模型多采用ML分类算法,已在临床各领域得到广泛应用。常见的分类器包括RF、SVM、k-NN、决策树、逻辑回归及朴素贝叶斯。在心脏CT方面,ML主要使用回顾性数据建立预后模型,多用于预测疑似CAD患者的心血管不良事件,如Motwani等[40]及Ambale-Venkatesh等[41]的模型将临床特征与CT影像特征相结合,van Rosendael等[42]及Johnson等[43]的模型则仅纳入CT影像特征。其中,Johnson等[43]的研究基于16节段冠脉的4个特征,包括斑块体积、钙化程度、直径狭窄率及有无正性重构,对DF、逻辑回归、k-NN及分类神经网络4种模型进行比较,结果显示k-NN对结局的预测性能最佳,预测全因死亡的曲线下面积(area under curve,AUC)达0.77,预测冠心病死亡或非致死性心肌梗死的AUC达0.85。该研究还将k-NN评分与现有的非ML评分相比较,包括CAD-RADS、SSS、SIS、CT-Leaman及SPS,除SPS在冠心病死亡或非致死性心肌梗死事件中与k-NN无明显差异外(AUC:0.84 vs. 0.85, P=0.37),其余评分的AUC均明显低于k-NN(全因死亡:0.77 vs. 0.72~0.26,P<0.001;冠心病死亡或非致死性心肌梗死:0.85 vs. 0.80~0.83,P<0.001)。
最近一项研究利用25个临床特征建立验前概率模型,预测CCTA上阻塞型CAD的出现,该模型在多国、多中心CONFIRM研究人群中应用,结果显示,与ML模型(AUC=0.773)、CAD联盟评分(AUC=0.734)、CACS(AUC=0.866)、更新的Diamond-Forrester评分(UDF,AUC=0.682)相比,ML与CACS组合的预测性能最佳(AUC=0.881,P<0.05)[43]
ML用于风险模型的优点在于:不基于先验假设,即纳入模型的特征不具有主观偏向性,而是运用算法对所有能获得的信息进行筛选,得到对结局有益的特征。如Motwani等[40]的研究中展示的信息增益排名、Al'Aref等[44]的研究中的特征重要性排名等。这有助于获得更全面的信息,建立更精准的模型。虽然ML算法的优越性已被证实,但不同算法的计算策略、效率及精准度有所区别,目前尚缺乏大型研究对不同算法的性能进行比较[44]。另外,风险模型的建立完全是由数据驱动的,这需要有相对完整临床信息的大样本人群,同时要求有准确的随访或诊断结果作为模型分类标准。由于我国目前临床数据的收集及随访程序并不十分完善,因此在我国开展此类研究还存在一定困难。
CTP是最近几年发展起来的一种新型功能学检查,通过观测对比剂在心肌中的灌注及流出情况评价心肌缺血程度,可分为静态及动态两种模式,前者在首次灌注期间的单个时间点进行图像捕获,而后者在灌注期间进行多次扫描,可获得完整的信号强度-时间曲线。检测心肌在负荷状态下的灌注情况,通常在动态CTP中完成,多以药物形式进行负荷。
ML在CTP中的应用尚不多见。Xiong等[45]采用训练好的Adaboost分类器在静息CCTA扫描图集中执行左室自动分割,并以标准化灌注强度、跨壁灌注比及心肌壁厚度3个特征训练ML模型,预测定量冠脉造影(quantitative coronary angiography,QCA)上>50%的狭窄病变。该研究将ML方法同时用于图像分割及预测模型中,展示了ML模型组合应用的可能性,然而其局限性在于,基于CTP的预测模型是以QCA结果为分类标准的,但QCA并不能反映狭窄的功能学意义。该团队的一项后续研究使用相似的分析及建模方法预测FFR上的显著缺血,结果显示,该方法的诊断准确率达63.5%,与CT显示的冠脉狭窄(AUC=0.68)相比,静息CTP可明显提高对缺血病变的识别能力(AUC=0.75,P=0.001)[46]。近期van Hamersvelt等[47]对冠脉中度狭窄的患者进行研究,使用深度学习算法对患者的左室心肌形状、纹理及对比度等图像信息进行提取,预测FFR定义的功能性狭窄,结果显示与仅基于狭窄等级的分类相比,该方法提高了对缺血病变的识别能力(AUC:0.76 vs. 0.68)。
在心肌灌注方面,ML更多应用于SPECT中,而CTP在检测小面积心内膜下缺血及多血管病变等方面较SPECT心肌灌注更具优势。即便如此,一些问题仍亟待解决,如动态CTP辐射暴露更大、对扫描硬件要求高、易受伪影影响(特别是线束硬化伪影),而静态CTP对扫描时间的要求更为严格等,这些缺陷可能会成为未来ML改进的立足点。另外,动态CTP已被证明与未来不良心脏事件的发生相关,可预测冠状动脉狭窄的预后[3],但目前尚缺少相关研究,将CTP特征引入预后模型可能会提高对相关患者的风险分层能力。
CT-FFR是另一项很有前景的新兴技术,它以流体动力学为计算基础,通过纳维-斯托克斯方程(Navier-Stokes equations)将血液模拟为牛顿流体,在静息CCTA图像上,对心室、冠脉树及主动脉进行三维重建,模拟冠脉最大充血状态,与冠脉血流量、管壁弹性等参数结合,计算狭窄远端冠脉内的平均压力与冠脉开口处主动脉平均压力的比值,获得血流储备分数。
最早提出的Heartflow模型于2014年经FDA批准用于临床。该模型主要是基于计算流体力学(computational fluid dynamics,CFD),其临床适用性已得到大量研究支持,最近Patel等[48]使用ADVANCE(Assessing Diagnostic Value of Non-invasive FFRCT in Coronary Care)注册研究中接受CCTA患者的1年随访结果,评估基于Heartflow的CT-FFR对下游护理及临床结局的影响,结果显示,患者发生主要心血管不良事件(MACE)的比例较低,与CT-FFR>0.8的患者相比,CT-FFR≤0.8的患者发生心血管死亡或非致死性心肌梗死的风险明显升高(RR=4.22,P=0.01)。然而,这种基于计算流体力学的方法对计算机硬件要求高,运算耗时长,计算成本巨大,且其依赖于经验模型,难以完成复杂病变的计算。我国基于深度学习的CT-FFR软件DEEPVESSEL-FFR已于去年投产上市,这是国内首个获得AI智能医疗器械三类证的AI医学影像产品,也是全球范围内第二款获批上市的CT-FFR产品。不同于Heartflow模型依靠传统的流场仿真技术,DEEPVESSEL-FFR采用自主研发的深度学习技术,将血流动力学模型与深度神经网络结合,能够高效、精准地对全冠脉树上任意一点的FFR值进行计算,可以对复杂病变进行评估,与压力导丝测量的有创FFR具有良好的一致性(r=0.686,95%CI 0.567~0.799,P<0.001)[49]。此外,国内外多家企业也一直致力于研发基于不同深度学习算法的CT-FFR模型,并相继进入临床试验及医疗审查阶段,如早期由Itu等[50]提出的cFFR模型,基于12 000多个具有不同狭窄程度的冠脉模型,构建ML模型以学习解剖特征与使用CFD模型计算的FFR值之间的映射关系。该方法最大的优点是使FFR计算时间明显缩短,可达近乎实时的结果,且其对缺血性病变的诊断能力已得到证实[51-53],包括基于不同金标准[54-55]及对特定病变[56-57]的研究。近期Lossnitzer等[58]的一项研究表明,在CT-FFR>0.8的患者中,94%经侵入性冠状动脉造影(invasive coronary angiography,ICA)证实为无阻塞型病变,cFFR的应用可能会减少55%潜在的ICA转诊,有助于改善临床下游管理。最近提出的uCT-FFR模型以侵入性FFR为金标准,在9个中心的338例患者中进行验证,诊断准确率达91%,高于CCTA及ICA(P<0.001)[59]
传统的有创FFR基于冠脉造影,其耗材昂贵,且需药物扩张血管,有一定风险,而CT-FFR依赖于无创影像学检查CCTA,在降低医疗成本的同时,可精准、快速、安全地进行FFR分析,而ML算法的应用为此提供了保障。与CCTA图像分析类似,CT-FFR分析产生的误差主要来源于图像质量干扰,包括CCTA图像噪声及重度弥漫钙化伪影。目前有学者提出可应用减影冠状动脉计算机断层扫描(subtraction coronary computed tomography angiography,S-CCTA)来克服钙化伪影的影响,或可提高CT-FFR在弥漫钙化病变中的诊断性能[60]。另外,随着仿真技术水平的提高,CT-FFR在提供病变功能学评估的同时,还可进行虚拟支架植入及虚拟搭桥仿真,为下游诊疗提供精准预案。目前的研究多围绕CT-FFR诊断性能进行,少有预后研究评估不同模型的临床应用价值,我国正在开展一项CT-FFR影响稳定型胸痛患者临床决策的多中心随机对照临床研究(TARGET研究,ClinicalTrial.gov注册号:NCT03901326)[61],这将为该技术在我国的开展提供更多循证医学依据。
ML是计算机科学高速发展的产物,它基于大数据计算,对潜在的事物规律进行自主学习,优化了传统计算模型,大幅提高了工作效率及质量。目前,ML在实际应用中面临的挑战主要源于算法及数据质量两个方面。其中在算法方面,尚缺少对不同模型的横向比较研究,不同算法采取的建模思路与计算方式各异,需要考虑针对不同类型的临床问题采取何种算法以取得最优解,特别是对于目前尚在探索中的应用领域,如重度钙化、支架影的识别及CT-FFR诊断灰区等问题。在数据质量方面,受限于临床成本问题,高质量、大样本训练数据较难获得,影响了以此为基础建立的ML模型的泛化能力及稳定性。对某些复杂问题,当ML模型不具备解决能力时,尚需人为干预及校正。
近年来,随着深度学习及卷积神经网络等AI技术的不断涌现,影像组学的概念被提出,以概述从医疗影像中自动提取高通量特征参数,建立模型以进行风险分层、辅助诊疗决策这一完整过程,其可视为AI在医疗影像评估中多个环节的组合应用,并已逐渐成为目前临床研究的大趋势。在心脏CT领域,已有许多AI产品落地应用,未来如何借助AI实现临床患者诊疗路径的优化管理值得进一步关注研究。
  • 国家重点研发计划(2016YFC1300304)
  • 北京市科技新星计划(Z181100006218055)
  • 解放军总医院医疗大数据与人工智能研发项目(2019MBD035)
参考文献 引证文献
排序方式:
[1]
Knuuti J, Wijns W, Saraste A, et al. 2019 ESC Guidelines for the diagnosis and management of chronic coronary syndromes[J]. Eur Heart J, 2020, 41(3): 407-477.
[2]
Budoff MJ, Dowe D, Jollis JG, et al. Diagnostic performance of 64-multidetector row coronary computed tomographic angiography for evaluation of coronary artery stenosis in individuals without known coronary artery disease: results from the prospective multicenter ACCURACY (Assessment by Coronary Computed Tomographic Angiography of Individuals Undergoing Invasive Coronary Angiography) trial[J]. J Am Coll Cardiol, 2008, 52(21): 1724-1732.
[3]
Nakamura S, Kitagawa K, Goto Y, et al. Incremental prognostic value of myocardial blood flow quantified with stress dynamic computed tomography perfusion imaging[J]. JACC Cardiovasc Imaging, 2019, 12(7 Pt 2): 1379-1387.
[4]
Sørgaard MH, Linde JJ, Kühl JT, et al. Value of myocardial perfusion assessment with coronary computed tomography angiography in patients with recent acute-onset chest pain[J]. JACC Cardiovasc Imaging, 2018, 11(11): 1611-1621.
[5]
van Assen M, De Cecco CN, Eid M, et al. Prognostic value of CT myocardial perfusion imaging and CT-derived fractional flow reserve for major adverse cardiac events in patients with coronary artery disease[J]. J Cardiovasc Comput Tomogr, 2019, 13(3): 26-33.
[6]
Gong J, Du C, Zhong XG, et al. Researches on the illness risk of essential hypertension complicated with coronary heart disease based on machine learning algorithm[J]. Med J Chin PLA, 2020, 45(7): 735-741.
[龚军, 杜超, 钟小钢, 等. 基于机器学习算法的原发性高血压并发冠心病的患病风险研究[J]. 解放军医学杂志, 2020, 45(7): 735-741.]
[7]
Tatsugami F, Higaki T, Nakamura Y, et al. Deep learning-based image restoration algorithm for coronary CT angiography[J]. Eur Radiol, 2019, 29(10): 5322-5329.
[8]
Kang E, Koo HJ, Yang DH, et al. Cycle-consistent adversarial denoising network for multiphase coronary CT angiography[J]. Med Phys, 2019, 46(2): 550-562.
[9]
Huang L, Jiang H, Li S, et al. Two stage residual CNN for texture denoising and structure enhancement on low dose CT image[J]. Comput Methods Programs Biomed, 2020, 184: 105115.
[10]
Chen H, Zhang Y, Zhang W, et al. Low-dose CT via convolutional neural network[J]. Biomed Opt Express, 2017, 8(2): 679-694.
[11]
Shan H, Zhang Y, Yang Q, et al. 3-D convolutional encoder-decoder network for low-dose CT via transfer learning from a 2-D trained network[J]. IEEE Trans Med Imaging, 2018, 37(6): 1522-1534.
[12]
Zheng X, Ravishankar S, Long Y, et al. PWLS-ULTRA: an efficient clustering and learning-based approach for low-dose 3D CT image reconstruction[J]. IEEE Trans Med Imaging, 2018, 37(6): 1498-1510.
[13]
Lossau T, Nickisch H, Wissel T, et al. Motion artifact recognition and quantification in coronary CT angiography using convolutional neural networks[J]. Med Image Anal, 2019, 52: 68-79.
[14]
Lossau Née Elss T, Nickisch H, Wissel T, et al. Motion estimation and correction in cardiac CT angiography images using convolutional neural networks[J]. Comput Med Imaging Graph, 2019, 76: 101640.
[15]
Lossau Née Elss T, Nickisch H, Wissel T, et al. Learning metal artifact reduction in cardiac CT images with moving pacemakers[J]. Med Image Anal, 2020, 61: 101655.
[15]
Park HS, Lee SM, Kim HP, et al. CT sinogram-consistency learning for metal-induced beam hardening correction[J]. Med Phys, 2018, 45(12): 5376-5384.
[17]
Callister TQ, Cooil B, Raya SP, et al. Coronary artery disease:improved reproducibility of calcium scoring with an electron-beam CT volumetric method[J]. Radiology, 1998, 208(3): 807-814.
[18]
Hong C, Becker CR, Schoepf UJ, et al. Coronary artery calcium:absolute quantification in nonenhanced and contrast-enhanced multi-detector row CT studies[J]. Radiology, 2002, 223(2): 474-480.
[19]
Agatston AS, Janowitz WR, Hildner FJ, et al. Quantification of coronary artery calcium using ultrafast computed tomography[J]. J Am Coll Cardiol, 1990, 15(4): 827-832.
[20]
Wolterink JM, Leiner T, Takx RA, et al. Automatic coronary calcium scoring in non-contrast-enhanced ECG-triggered cardiac CT with ambiguity detection[J]. IEEE Trans Med Imaging, 2015, 34(9): 1867-1878.
[21]
Yang G, Chen Y, Ning X, et al. Automatic coronary calcium scoring using noncontrast and contrast CT images[J]. Med Phys, 2016, 43(5): 2174.
[22]
Isgum I, Prokop M, Niemeijer M, et al. Automatic coronary calcium scoring in low-dose chest computed tomography[J]. IEEE Trans Med Imaging, 2012, 31(12): 2322-2334.
[23]
Shahzad R, van Walsum T, Schaap M, et al. Vessel specific coronary artery calcium scoring: an automatic system[J]. Acad Radiol, 2013, 20(1): 1-9.
[24]
Wolterink JM, Leiner T, de Vos BD, et al. Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks[J]. Med Image Anal, 2016, 34: 123-136.
[25]
Lessmann N, van Ginneken B, Zreik M, et al. Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions[J]. IEEE Trans Med Imaging, 2018, 37(2): 615-625.
[26]
de Vos BD, Wolterink JM, Leiner T, et al. Direct automatic coronary calcium scoring in cardiac and chest CT[J]. IEEE Trans Med Imaging, 2019, 38(9): 2127-2138.
[27]
van Velzen SGM, Lessmann N, Velthuis BK, et al. Deep learning for automatic calcium scoring in CT: validation using multiple cardiac CT and chest CT protocols[J]. Radiology, 2020, 295(1): 66-79.
[28]
Lee JM, Choi KH, Koo BK, et al. Prognostic implications of plaque characteristics and Stenosis severity in patients with coronary artery disease[J]. J Am Coll Cardiol, 2019, 73(19): 2413-2424.
[29]
Zhou C, Chan HP, Chughtai A, et al. Computerized analysis of coronary artery disease: performance evaluation of segmentation and tracking of coronary arteries in CT angiograms[J]. Med Phys, 2014, 41(8): 081912.
[30]
Wei J, Zhou C, Chan HP, et al. Computerized detection of noncalcified plaques in coronary CT angiography: evaluation of topological soft gradient prescreening method and luminal analysis[J]. Med Phys, 2014, 41(8): 081901.
[31]
Ghanem AM, Hamimi AH, Matta JR, et al. Automatic coronary wall and atherosclerotic plaque segmentation from 3D coronary CT angiography[J]. Sci Rep, 2019, 9(1): 47.
[32]
Zuluaga MA, Magnin IE, Hernández Hoyos M, et al. Automatic detection of abnormal vascular cross-sections based on density level detection and support vector machines[J]. Int J Comput Assist Radiol Surg, 2011, 6(2): 163-174.
[33]
Zhao F, Wu B, Chen F, et al. An automatic multi-class coronary atherosclerosis plaque detection and classification framework[J]. Med Biol Eng Comput, 2019, 57(1): 245-257.
[34]
Jawaid MM, Riaz A, Rajani R, et al. Framework for detection and localization of coronary non-calcified plaques in cardiac CTA using mean radial profiles[J]. Comput Biol Med, 2017, 89: 84-95.
[35]
Zreik M, van Hamersvelt RW, Wolterink JM, et al. A recurrent CNN for automatic detection and classification of coronary artery plaque and Stenosis in coronary CT angiography[J]. IEEE Trans Med Imaging, 2019, 38(7): 1588-1598.
[36]
Yamak D, Panse P, Pavlicek W, et al. Non-calcified coronary atherosclerotic plaque characterization by dual energy computed tomography[J]. IEEE J Biomed Health Inform, 2014, 18(3): 939-945.
[37]
Masuda T, Nakaura T, Funama Y, et al. Machine-learning integration of CT histogram analysis to evaluate the composition of atherosclerotic plaques: Validation with IB-IVUS[J]. J Cardiovasc Comput Tomogr, 2019, 13(2): 163-169.
[38]
Shi P, Xin J, Liu S, et al. Vulnerable plaque recognition based on attention model with deep convolutional neural network[J]. Annu Int Conf IEEE Eng Med Biol Soc, 2018, 2018: 834-837.
[39]
Kolossváry M, Karády J, Kikuchi Y, et al. Radiomics versus visual and histogram-based assessment to identify atheromatous lesions at coronary CT angiography: an ex vivo study[J]. Radiology, 2019, 293(1): 89-96.
[40]
Motwani M, Dey D, Berman DS, et al. Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis[J]. Eur Heart J, 2017, 38(7): 500-507.
[41]
Ambale-Venkatesh B, Yang XY, Wu CO, et al. Cardiovascular event prediction by machine learning: the multi-ethnic study of atherosclerosis[J]. Circ Res, 2017, 121(9): 1092-1101.
[42]
van Rosendael AR, Maliakal G, Kolli KK, et al. Maximization of the usage of coronary CTA derived plaque information using a machine learning based algorithm to improve risk stratification;insights from the CONFIRM registry[J]. J Cardiovasc Comput Tomogr, 2018, 12(3): 204-209.
[43]
Johnson KM, Johnson HE, Zhao Y, et al. Scoring of coronary artery disease characteristics on coronary CT angiograms by using machine learning[J]. Radiology, 2019, 292(2): 354-362.
[44]
Al'Aref SJ, Maliakal G, Singh G, et al. Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry[J]. Eur Heart J, 2020, 41(3): 359-367.
[45]
Xiong G, Kola D, Heo R, et al. Myocardial perfusion analysis in cardiac computed tomography angiographic images at rest[J]. Med Image Anal, 2015, 24(1): 77-89.
[46]
Han D, Lee JH, Rizvi A, et al. Incremental role of resting myocardial computed tomography perfusion for predicting physiologically significant coronary artery disease: A machine learning approach[J]. J Nucl Cardiol, 2018, 25(1): 223-233.
[47]
van Hamersvelt RW, Zreik M, Voskuil M, et al. Deep learning analysis of left ventricular myocardium in CT angiographic intermediate-degree coronary stenosis improves the diagnostic accuracy for identification of functionally significant stenosis[J]. Eur Radiol, 2019, 29(5): 2350-2359.
[48]
Patel MR, Nørgaard BL, Fairbairn TA, et al. 1-year impact on medical practice and clinical outcomes of FFRCT: the ADVANCE registry[J]. JACC Cardiovasc Imaging, 2020, 13(1 Pt 1): 97-105.
[49]
Wang ZQ, Zhou YJ, Zhao YX, et al. Diagnostic accuracy of a deep learning approach to calculate FFR from coronary CT angiography[J]. J Geriatr Cardiol, 2019, 16(1): 42-48.
[50]
Itu L, Rapaka S, Passerini T, et al. A machine-learning approach for computation of fractional flow reserve from coronary computed tomography[J]. J Appl Physiol (1985), 2016, 121(1): 42-52.
[51]
Coenen A, Kim YH, Kruk M, et al. Diagnostic accuracy of a machine-learning approach to coronary computed tomographic angiography-based fractional flow reserve: result from the MACHINE consortium[J]. Circ Cardiovasc Imaging, 2018, 11(6): e007217.
[52]
Tesche C, De Cecco CN, Baumann S, et al. Coronary CT angiography-derived fractional flow reserve: machine learning algorithm versus computational fluid dynamics modeling[J]. Radiology, 2018, 288(1): 64-72.
[53]
Li Y, Yu M, Dai X, et al. Detection of hemodynamically significant coronary stenosis: CT myocardial perfusion versus machine learning CT fractional flow reserve[J]. Radiology, 2019, 293(2): 305-314.
[54]
Baumann S, Hirt M, Rott C, et al. Comparison of machine learning computed tomography-based fractional flow reserve and coronary CT angiography-derived plaque characteristics with invasive resting full-cycle ratio[J]. J Clin Med, 2020, 9(3): 714.
[55]
Baumann S, Hirt M, Schoepf UJ, et al. Correlation of machine learning computed tomography-based fractional flow reserve with instantaneous wave free ratio to detect hemodynamically significant coronary stenosis[J]. Clin Res Cardiol, 2020, 109(6): 735-745.
[56]
Zhou F, Wang YN, Schoepf UJ, et al. Diagnostic performance of machine learning based CT-FFR in detecting ischemia in myocardial bridging and concomitant proximal atherosclerotic disease[J]. Can J Cardiol, 2019, 35(11): 1523-1533.
[57]
Tesche C, Otani K, De Cecco CN, et al. Influence of coronary calcium on diagnostic performance of machine learning CTFFR: results from MACHINE registry[J]. JACC Cardiovasc Imaging, 2020, 13(3): 760-770.
[58]
Lossnitzer D, Chandra L, Rutsch M, et al. Additional value of machine-learning computed tomographic angiography-based fractional flow reserve compared to standard computed tomographic angiography[J]. J Clin Med, 2020, 9(3): 676.
[59]
Tang CX, Liu CY, Lu MJ, et al. CT FFR for ischemia-specific CAD with a new computational fluid dynamics algorithm: a Chinese multicenter study[J]. JACC Cardiovasc Imaging, 2020, 13(4): 980-990.
[60]
Takamura K, Fujimoto S, Kawaguchi Y, et al. The usefulness of low radiation dose subtraction coronary computed tomography angiography for patients with calcification using 320-row area detector CT[J]. J Cardiol, 2019, 73(1): 58-64.
[61]
Yang J, Shan D, Dong M, et al. The effect of on-site CT-derived fractional flow reserve on the management of decision making for patients with stable chest pain (TARGET trial): objective, rationale, and design[J]. Trials, 2020, 21(1): 728.
2021年第46卷第3期
PDF下载
188
80
引用本文
BibTeX
文章信息
doi: 10.11855/j.issn.0577-7402.2021.03.12
  • 接收时间:2020-07-16
  • 首发时间:2025-12-26
  • 出版时间:2021-03-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2020-07-16
  • 修回日期:2020-10-26
基金
National Key Research and Development Program of China(2016YFC1300304)
国家重点研发计划(2016YFC1300304)
Beijing NOVA Program(Z181100006218055)
北京市科技新星计划(Z181100006218055)
Medical Big Data Program of PLAGH(2019MBD035)
解放军总医院医疗大数据与人工智能研发项目(2019MBD035)
作者信息
    1解放军总医院第一医学中心心血管内科,北京 100853
    2南开大学医学院,天津 300071

通讯作者:

杨俊杰,E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/jfjyxzz/CN/10.11855/j.issn.0577-7402.2021.03.12
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏