Texture analysis to assess risk of serious arrhythmias after myocardial infarction

Implantable cardioverter-defibrillator (ICD) prevents sudden cardiac death in patients with healed myocardial infarction (MI) at high risk of serious arrhythmias. This study was designed to identify if texture analysis of cardiac magnetic rensonance (CMR) images can be used to identify high-risk patients likely to benefit from ICD implantation. Two groups of patients with MI were compared: 24 patients with indication for ICD and 37 patients with healed MI and no ICD indication corresponding to high and low risk of arrhythmia respectively. Statistical and texture descriptors were calculated in segmented late gadolinium enhancement images. ICD- and non-ICD patients were compared using pattern classification methods. The specificity to discriminate ICD- and non-ICD-patients was calculated at a sensitivity of ≥ 90% by combining one, two or three features. LVEF alone was able to discriminate the two groups with a specificity of 70% (CI:57-81%). Combining LVEF with one texture descriptor of the non-scarred myocardium increased specificity to 81% (CI:69-89%) and with two texture descriptors of non-scarred myocardium and infarct further increased specificity to 84% (CI: 72-91%).