Abstract
We explored whether radiomic features from T1 maps by cardiac magnetic resonance (CMR) could enhance the diagnostic value of T1 mapping in distinguishing health from disease and classifying cardiac disease phenotypes. A total of 149 patients (n = 30 with no heart disease, n = 30 with LVH, n = 61 with hypertrophic cardiomyopathy (HCM) and n = 28 with cardiac amyloidosis) undergoing a CMR scan were included in this study. We extracted a total of 850 radiomic features and explored their value in disease classification. We applied principal component analysis and unsupervised clustering in exploratory analysis, and then machine learning for feature selection of the best radiomic features that maximized the diagnostic value for cardiac disease classification. The first three principal components of the T1 radiomics were distinctively correlated with cardiac disease type. Unsupervised hierarchical clustering of the population by myocardial T1 radiomics was significantly associated with myocardial disease type (chi2 = 55.98, p < 0.0001). After feature selection, internal validation and external testing, a model of T1 radiomics had good diagnostic performance (AUC 0.753) for multinomial classification of disease phenotype (normal vs. LVH vs. HCM vs. cardiac amyloid). A subset of six radiomic features outperformed mean native T1 values for classification between myocardial health vs. disease and HCM phenocopies (AUC of T1 vs. radiomics model, for normal: 0.549 vs. 0.888; for LVH: 0.645 vs. 0.790; for HCM 0.541 vs. 0.638; and for cardiac amyloid 0.769 vs. 0.840). We show that myocardial texture assessed by native T1 maps is linked to features of cardiac disease. Myocardial radiomic phenotyping could enhance the diagnostic yield of T1 mapping for myocardial disease detection and classification.
Highlights
Cardiac magnetic resonance (CMR) is considered the state-of-the-art imaging approach for assessing myocardial disease[1], allowing tissue characterization and fibrosis detection by late gadolinium enhancement (LGE)[2]
We calculated a total of 850 radiomic features by segmentation of left ventricular (LV) myocardium, which included 15 shape-related features, 18 first order statistics, 15 Gray Level Co-occurrence Matrix (GLCM), 18 Gray Level Dependence Matrix (GLDM), 16 Gray Level Run-Length Matrix (GLRLM), 16 Gray Level Size Zone Matrix (GLSZM), and 5 Neighboring Gray Tone Difference Matrix (NGTDM) features as well as eight wavelet transformations for each one of them
The first three components were variably associated with the underlying cardiac phenotype (Fig. 2D), suggesting that native T1 maps of LV myocardium contain rich extractable information associated with distinct phenotypes of human heart, which could be used to distinguish healthy myocardium from myocardial disease (Fig. 2E)
Summary
Cardiac magnetic resonance (CMR) is considered the state-of-the-art imaging approach for assessing myocardial disease[1], allowing tissue characterization and fibrosis detection by late gadolinium enhancement (LGE)[2]. Since T1 mapping is a standardized CMR acquisition, extraction of radiomic features by myocardial T1 maps is feasible[9] and recent evidence supports their value for classification between hypertensive heart disease and hypertrophic cardiomyopathy (HCM)[10]. More evidence is needed to fully establish the clinical value of T1 radiomics in reliably discriminating between various cardiac phenotypes. The aim of this proof-of-concept study was to extract and validate radiomic features from T1 maps using machine learning in a wide spectrum of conditions ranging from normal to various myocardial diseases with particular emphasis on distinguishing healthy from diseased myocardium and classifying LVH phenotypes
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
