Cardiac magnetic resonance-based layer-specific strain in immune checkpoint inhibitor-associated myocarditis

Aims To assess the different imaging characteristics between corticosteroid-sensitive (CS) and corticosteroid-refractory (CR) immune checkpoint inhibitor-associated myocarditis (ICIaM) with cardiac magnetic resonance (CMR) and the potential CMR parameters in the early detection of CR ICIaM.Methods and results Thirty-five patients diagnosed with ICIaM and 30 age and gender-matched cancer patients without a history of ICI treatment were enrolled. CMR with contrast was performed within 2 days of clinical suspicion. Left ventricular ejection fraction (LVEF) and late gadolinium enhancement (LGE) were assessed by CMR. LV sub-endocardial (GLSendo) and sub-epicardial (GLSepi) global longitudinal strains were quantified by offline feature tracking analysis. CS and CR ICIaM were defined based on the trend of Troponin I and clinical course during corticosteroid treatment. All 35 patients presented with non-fulminant symptoms upon initial assessment. Twenty patients (57.14%) were sensitive, and 15 (42.86%) were refractory to corticosteroids. Compared with controls, 22 patients (62.86%) with ICIaM developed LGE. LVEF decreased in CR ICIaM compared with the CS group and controls. GLSendo (-14.61 +/- 2.67 vs. -18.50 +/- 2.53, P < 0.001) and GLSepi (-14.75 +/- 2.53 vs. -16.68 +/- 2.05, P < 0.001) significantly increased in patients with CR ICIaM compared with the CS ICIaM. In patients with CS ICIaM, although GLSepi (-16.68 +/- 2.05 vs. -19.31 +/- 1.80, P < 0.001) was impaired compared with the controls, GLSendo was preserved. There was no difference in CMR parameters between LGE-positive and negative groups. LVEF, GLSendo, and GLSepi were predictors of CR ICIaM. When LVEF, GLSendo, and GLSepi were included in multivariate analysis, only GLSendo remained an independent predictor of CR ICIaM (OR: 2.170, 95% CI: 1.189-3.962, P = 0.012). A GLSendo of >=-17.10% (sensitivity, 86.7%; specificity, 80.0%; AUC, 0.860; P < 0.001) could predict CR ICIaM in the ICIaM cohort. Kaplan-Meier analysis showed that in patients with impaired GLSendo of >=-17.10%, cardiovascular adverse events (CAEs) occurred much earlier than in patients with preserved GLSendo of <-17.10% (Log-rank test P = 0.017).Conclusions CR and CS ICIaM demonstrated different functional and morphological characteristics in different myocardial layers. An impaired GLSendo could be a helpful parameter in early identifying corticosteroid-refractory individuals in the ICIaM population.