Radiomic Analysis of Native T₁ Mapping Images Discriminates Between MYH7 and MYBPC3‐Related Hypertrophic Cardiomyopathy

Abstract

Background: The phenotype via conventional cardiac MRI analysis of MYH7 (β-myosin heavy chain)-and MYBPC3 (β-myosin-binding protein C)-associated hypertrophic cardiomyopathy (HCM) groups is similar. Few studies exist on the genotypic-phenotypic association as assessed by machine learning in HCM patients. Purpose: To explore the phenotypic differences based on radiomics analysis of T 1 mapping images between MYH7 and MYBPC3-associated HCM subgroups. Study Type: Prospective observational study. Subjects: In all, 102 HCM patients with pathogenic, or likely pathogenic mutation, in MYH7 (n = 68) or MYBPC3 (n = 34) genes. Field Strength/Sequence: Cardiac MRI was performed at 3.0T with balanced steady-state free precession (bSSFP), phasesensitive inversion recovery (PSIR) late gadolinium enhancement (LGE), and modified Look-Locker inversion recovery (MOLLI) T 1 mapping sequences. Assessment: All patients underwent next-generation sequencing and Sanger genetic sequencing. Left ventricular native T 1 and LGE were analyzed. One hundred and fifty-seven radiomic features were extracted and modeled using a support vector machine (SVM) combined with principal component analysis (PCA). Each subgroup was randomly split 4:1 (feature selection / test validation). Statistical Tests: Mann-Whitney U-tests and Student's t-tests were performed to assess differences between subgroups. A receiver operating characteristic (ROC) curve was used to assess the model's ability to stratify patients based on radiomic features. Results: There were no significant differences between MYH7and MYBPC3-associated HCM subgroups based on traditional native T 1 values (global, basal, and middle short-axis slice native T 1 ; P = 0.760, 0.914, and 0.178, respectively). However, the SVM model combined with PCA achieved an accuracy and area under the curve (AUC) of 92.0% and 0.968 (95% confidence interval [CI]: 0.968-0.971), respectively. For the test validation dataset, the accuracy and AUC were 85.5% and 0.886 (95% CI: 0.881-0.901), respectively. Data Conclusion: Radiomic analysis of native T 1 mapping images may be able to discriminate between MYH7and MYBPC3-associated HCM patients, exceeding the performance of conventional native T 1 values. Level of Evidence: 3 Technical Efficacy Stage: 2

Myocardial Deformation Analysis in MYBPC3 and MYH7 Related Sarcomeric Hypertrophic Cardiomyopathy—The Graz Hypertrophic Cardiomyopathy Registry

“…Pathogenic or likely pathogenic variants in sarcomere protein encoding genes can be identified in 40-60% of adolescents and adults affected by HCM. MYBPC3 (encoding cardiac myosin binding protein-C, cMyBPC) and MYH7 (encoding β cardiac myosin heavy chain) account for the majority of cases [2][3][4].…”

“…Previous studies failed in the majority to demonstrate phenotypic differences between MYBPC3 and MYH7 mutation carriers. Some imaging studies were suggestive of a more severe phenotype in individuals carrying a pathogenic genetic variant in MYH7 mutations compared to MYBPC3, although differences were often marginal and non-significant [3,8,12]. Other studies found no significant differences with regard to parameters of left ventricular (LV) function and structure, and myocardial scar formation [13,14].…”

The Predictive Value of Myocardial Native T1 Mapping Radiomics in Dilated Cardiomyopathy: A Study in a Chinese Population

“…The myocardium was initially manually delineated with the endocardial and epicardial contours and the radiomic features were subsequently extracted from the myocardium ROI. A total of 157 features was extracted from the T1 mapping for each participant and the process of image filtering and feature extraction was performed with MATLAB 2014 (MathWorks, Natick, MA, USA), which is consistent with previous study 24 . PyRadiomics of Python (https://github.com/Radiomics/pyradiomics) was used to extract features from the annotated regions, including Gray Level Cooccurence Matrix (GLCM), Gray Level Run Length Matrix (GLRLM), Gray Level Size Zone Matrix (GLSZM), Gray Level Dependence Matrix (GLDM) and Neighborhood Gray Tone Difference Matrix (NGTDM), as well as filtered features (Laplacian of Gaussian, Wavelet, Square, Square Root, Logarithm Exponential, Gradient, and Local Binary Pattern).…”

CMR-Verified Myocardial Fibrosis Is Associated With Subclinical Diastolic Dysfunction in Primary Aldosteronism Patients

“…Our research center used 0.15 mmol/kg to detect T1 mapping for many years. Some researches have been reported (25)(26)(27). Figure 1 shows the contrast-enhanced T1 maps of two PA patients and two EH patients.…”