Radiomic Cardiac MRI Signatures for Predicting Ventricular Arrhythmias in Patients With Nonischemic Dilated Cardiomyopathy.

Background: Risk stratification in patients with nonischemic dilated cardiomyopathy (DCM) remains challenging. Although late gadolinium enhancement (LGE) cardiovascular magnetic resonance is recognized as a major risk factor for ventricular tachycardia/ventricular fibrillation (VT/VF), the prognostic value of LGE radiomics is unknown.

Objectives: The purpose of this study was to investigate if radiomic analysis of LGE images can improve arrhythmia risk stratification in patients with DCM beyond current clinical and imaging markers.

Methods: In a 2-center retrospective study, patients with DCM were identified among those who received primary prevention implantable cardioverter-defibrillators (ICDs) according to the clinical guidelines and had a cardiovascular magnetic resonance before ICD implantation. The study included patients with DCM from the Cleveland Clinic Foundation for model development and patients with DCM from Beth Israel Deaconess Medical Center for external validation. Left ventricular myocardial radiomic features were extracted from LGE images. The primary outcome was appropriate ICD intervention defined as shock or antitachycardia pacing for VT/VF. Consensus clustering and pairwise correlation were used to identify the radiomic signature. To assess the prognostic value of LGE radiomics, we built 2 logistic regression models using the development data: 1) model 1, including clinical risk factors and scar presence and 2) model 2, which combines model 1 and LGE radiomics.

Results: In total, 270 patients with DCM (61% male, age 58 ± 13 years) in development data and 113 patients with DCM (71% male, age 55 ± 14 years) in external validation were included. VT/VF occurred in 40 (15%) patients in development and 16 (15%) in external validation cohorts over a median follow-up period of 4.0 (IQR: 2.5-6.1) and 2.6 (IQR: 1.2-4.1) years, respectively. Consensus clustering and pairwise correlation revealed 3 distinct radiomic features. Model 2 showed a higher C-statistic than model 1 (0.71 [95% CI: 0.62-0.80] vs 0.61 [95% CI: 0.53-0.71]; P = 0.028 in development and 0.70 [95% CI: 0.59-0.85] vs 0.61 [95% CI: 0.46-0.77]; P = 0.025 in external validation). This also significantly improved risk stratification with a continuous net reclassification index of 0.60 [95% CI: 0.29-0.91; P < 0.001] in development and of 0.29 [95% CI: 0.26-0.56; P = 0.03] in external validation. Additionally, 1 radiomic feature, namely the gray level co-occurrence matrix autocorrelation, was an independent predictor of VT/VF in both development (HR: 1.45 [95% CI: 1.10-1.91]; P = 0.01) and in external validation (HR: 2.38 [95% CI: 1.28-4.42]; P = 0.01).

Conclusions: In this proof-of-concept study, radiomic analysis of LGE images provides additional prognostic value beyond LGE presence in predicting arrhythmia in patients with DCM.