Multi-Stage Clustering of Different Heart Tissues in Patients Using Composite Strain Encoding (C-Senc) Mri Images

Abstract

The combination of myocardial functional and viability images is important for therapeutic decision making in patients with myocardial infarction. Composite strain encoding (C-SENC) imaging provides both functional and viability images at the same cardiac phase. This allows for applying automatic clustering techniques without suffering from misregistration problems. In this work, a multi-stage unsupervised clustering technique was applied to the resulting C-SENC images of seven patients. The technique used both fuzzy c-means (FCM) and ISODATA clustering methods. Normal myocardium, infarction, and blood were successfully identified using the proposed technique. In addition, different degrees of contractility were assigned to the non-infarcted myocardium.