Ventricular tachycardia (VT) is a major cause of sudden cardiac death (SCD) in patients with heart failure (HF). Left ventricular ejection fraction (LVEF) and heart failure class according to the New York Heart association (NYHA) are in most common use to identify patients that may benefit from implantable cardioverter defibrillator (ICD) therapy. But during 3 years of follow up only 35% of patients receive appropriate ICD action. Therefore, there is a continued need for refinement of selection criteria for ICD implantation. In this regard, molecular imaging of the autonomic nervous system, which plays a central role in HF progression and cardiac electro-mechanical regulation, can make a substantial contribution. This article reviews the currently available literature concerning the value of molecular neuronal cardiac imaging for prediction of ventricular arrhythmias in HF patients.