Cardiacmagnetic resonance radiomics: basic principles and clinical perspectives

被引:62
作者
Raisi-Estabragh, Zahra [1 ,2 ]
Izquierdo, Cristian [3 ]
Campello, Victor M. [3 ]
Martin-Isla, Carlos [3 ]
Jaggi, Akshay [3 ]
Harvey, Nicholas C. [4 ,5 ,6 ]
Lekadir, Karim [3 ]
Petersen, Steffen E. [1 ,2 ]
机构
[1] Queen Mary Univ London, Dept Adv Cardiovasc Imaging, William Harvey Res Inst, NIHR Barts Biomed Res Ctr, Charterhouse Sq, London EC1M 6BQ, England
[2] Barts Hlth NHS Trust, Barts Heart Ctr, St Bartholomews Hosp, West Smithfield EC1A 7BE, England
[3] Univ Barcelona, Dept Matemat & Informat, Gran Via Corts Catalanes 585, Barcelona 08007, Spain
[4] Univ Southampton, MRC Lifecourse Epidemiol Unit, Tremona Rd, Southampton SO16 6YD, Hants, England
[5] Univ Southampton, NIHR Southampton Biomed Res Ctr, Tremona Rd, Southampton SO16 6YD, Hants, England
[6] Univ Hosp Southampton NHS Fdn Trust, Tremona Rd, Southampton SO16 6YD, Hants, England
基金
英国工程与自然科学研究理事会; 欧盟地平线“2020”;
关键词
radiomics; texture analysis; cardiac magnetic resonance; image-based diagnosis; machine learning; QUANTITATIVE TEXTURE ANALYSIS; MYOCARDIAL-INFARCTION; ECHOCARDIOGRAPHY; INFORMATION; PREDICTION; DIAGNOSIS; IMAGES;
D O I
10.1093/ehjci/jeaa028
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Radiomics is a novel image analysis technique, whereby voxel-level information is extracted from digital images and used to derive multiple numerical quantifiers of shape and tissue character. Cardiac magnetic resonance (CMR) is the reference imaging modality for assessment of cardiac structure and function. Conventional analysis of CMR scans is mostly reliant on qualitative image analysis and basic geometric quantifiers. Small proof-of-concept studies have demonstrated the feasibility and superior diagnostic accuracy of CMR radiomics analysis over conventional reporting. CMR radiomics has the potential to transform our approach to defining image phenotypes and, through this, improve diagnostic accuracy, treatment selection, and prognostication. The purpose of this article is to provide an overview of radiomics concepts for clinicians, with particular consideration of application to CMR. We will also review existing literature on CMR radiomics, discuss challenges, and consider directions for future work.
引用
收藏
页码:349 / 356
页数:8
相关论文
共 37 条
[1]   Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach [J].
Aerts, Hugo J. W. L. ;
Velazquez, Emmanuel Rios ;
Leijenaar, Ralph T. H. ;
Parmar, Chintan ;
Grossmann, Patrick ;
Cavalho, Sara ;
Bussink, Johan ;
Monshouwer, Rene ;
Haibe-Kains, Benjamin ;
Rietveld, Derek ;
Hoebers, Frank ;
Rietbergen, Michelle M. ;
Leemans, C. Rene ;
Dekker, Andre ;
Quackenbush, John ;
Gillies, Robert J. ;
Lambin, Philippe .
NATURE COMMUNICATIONS, 2014, 5
[2]   Texture analysis in assessment and prediction of chemotherapy response in breast cancer [J].
Ahmed, Arfan ;
Gibbs, Peter ;
Pickles, Martin ;
Turnbull, Lindsay .
JOURNAL OF MAGNETIC RESONANCE IMAGING, 2013, 38 (01) :89-101
[3]   Relationship between Extension or Texture Features of Late Gadolinium Enhancement and Ventricular Tachyarrhythmias in Hypertrophic Cardiomyopathy [J].
Amano, Yasuo ;
Suzuki, Yasuyuki ;
Yanagisawa, Fumi ;
Omori, Yuko ;
Matsumoto, Naoya .
BIOMED RESEARCH INTERNATIONAL, 2018, 2018
[4]   Cardiac MRI Texture Analysis of T1 and T2 Maps in Patients with Infarctlike Acute Myocarditis [J].
Baessler, Bettina ;
Luecke, Christian ;
Lorz, Julia ;
Klingel, Karin ;
von Roeder, Maximilian ;
de Waha, Suzanne ;
Besler, Christian ;
Maintz, David ;
Gutberlet, Matthias ;
Thiele, Holger ;
Lurz, Philipp .
RADIOLOGY, 2018, 289 (02) :357-365
[5]   Texture analysis and machine learning of non-contrast T1-weighted MR images in patients with hypertrophic cardiomyopathy-Preliminary results [J].
Baessler, Bettina ;
Mannil, Manoj ;
Maintz, David ;
Alkadhi, Hatem ;
Manka, Robert .
EUROPEAN JOURNAL OF RADIOLOGY, 2018, 102 :61-67
[6]   Subacute and Chronic Left Ventricular Myocardial Scar: Accuracy of Texture Analysis on Nonenhanced Cine MR Images [J].
Baessler, Bettina ;
Mannil, Manoj ;
Oebel, Sabrina ;
Maintz, David ;
Alkadhi, Hatem ;
Manka, Robert .
RADIOLOGY, 2018, 286 (01) :103-112
[7]  
Cetin I, 2019, I S BIOMED IMAGING, P640, DOI [10.1109/isbi.2019.8759440, 10.1109/ISBI.2019.8759440]
[8]   LGE-CMR-derived texture features reflect poor prognosis in hypertrophic cardiomyopathy patients with systolic dysfunction: preliminary results [J].
Cheng, Sainan ;
Fang, Mengjie ;
Cui, Chen ;
Chen, Xiuyu ;
Yin, Gang ;
Prasad, Sanjay K. ;
Dong, Di ;
Tian, Jie ;
Zhao, Shihua .
EUROPEAN RADIOLOGY, 2018, 28 (11) :4615-4624
[9]   USE OF GRAY VALUE DISTRIBUTION OF RUN LENGTHS FOR TEXTURE ANALYSIS [J].
CHU, A ;
SEHGAL, CM ;
GREENLEAF, JF .
PATTERN RECOGNITION LETTERS, 1990, 11 (06) :415-419
[10]   Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD statement [J].
Collins, G. S. ;
Reitsma, J. B. ;
Altman, D. G. ;
Moons, K. G. M. .
BRITISH JOURNAL OF CANCER, 2015, 112 (02) :251-259