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.
Background Myocardial T1 mapping by cardiac magnetic resonance (CMR) is a useful technique to detect diffuse myocardial fibrosis, but a major limitation of T1 mapping is the significant overlap in native T1 values between health and disease. Purpose We explored whether radiomic features from T1 maps could enhance the diagnostic value of T1 mapping in distinguishing health from disease and classifying cardiac disease phenotypes. Methods In a total of 149 patients (n=30 with no evidence of heart disease, n=30 with LVH of various etiologies, n=61 with hypertrophic cardiomyopathy (HCM) and n=28 with cardiac amyloidosis) undergoing a CMR scan for various indications were included in this study. In addition to measuring native myocardial T1 values from T1 maps, we extracted a total of 843 radiomic features of myocardial texture and explored their value in disease classification. Results We first demonstrated that T1 mapping images are a rich source of extractable, quantifiable data. The first three principal components of the T1 radiomics were significantly and 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 machine learning for feature selection, training with 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. amyloid). A subset of seven radiomic features outperformed mean native T1 values for classification between myocardial health vs. disease and HCM phenocopies (for normal: T1 AUC 0.549 vs. radiomics AUC 0.888, for LVH: T1 AUC 0.645 vs. radiomics AUC 0.790, for HCM T1 AUC 0.541 vs. radiomics AUC 0.638 and for amyloid T1 AUC 0.769 vs. radiomics AUC 0.840). Conclusions We have shown that specific imaging patterns in myocardial native T1 maps are linked to features of cardiac disease and we have provided for the first-time evidence that radiomic phenotyping can be used to enhance the diagnostic yield of native T1 mapping for myocardial disease detection and classification. FUNDunding Acknowledgement Type of funding sources: None.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.