Automatic assessment of myocardial viability based on PET-MRI data fusion

In this paper, a fusion system which combines data generated by tagged magnetic resonance imaging (MRI) and F18-FDG positron emission tomography (PET) is presented. MRI and PET complementarity leads to a very accurate assessment of the myocardial viability in patients with coronary heart disease. An accurate viability analysis allows a better prediction of the successes of the revascularization procedure. The fusion system is based on soft computing techniques. It is a modular network which consists of four adaptive network-based fuzzy inference systems (ANFIS) organized in a hierarchical way. The network is able to learn and adapt itself and integrates expert knowledge. It is considered a valuable tool for clinical and research applications