Radiomic Analysis Of Nativet(1)Mapping Images Discriminates Betweenmyh7andmybpc3-Related Hypertrophic Cardiomyopathy

Background The phenotype via conventional cardiac MRI analysis ofMYH7(beta-myosin heavy chain)- andMYBPC3(beta-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 betweenMYH7andMYBPC3-associated HCM subgroups. Study Type Prospective observational study. Subjects In all, 102 HCM patients with pathogenic, or likely pathogenic mutation, inMYH7(n =68) orMYBPC3(n =34) genes. Field Strength/Sequence Cardiac MRI was performed at 3.0T with balanced steady-state free precession (bSSFP), phase-sensitive 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-WhitneyU-tests and Student'st-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 betweenMYH7- andMYBPC3-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 betweenMYH7- andMYBPC3-associated HCM patients, exceeding the performance of conventional native T(1)values. Level of Evidence 3 Technical Efficacy Stage 2