On the detection of intra-ventricular dyssynchrony in the left ventricle from routine cardiac MRI

Intra-ventricular dyssynchrony (IVD) in the left ventricle (LV), the asynchronous activation of the LV walls, has been identified as a novel target for therapy in heart failure patients. Current guidelines for resynchronization therapy rely on measures that do not reliably predict successful patient response to treatment, in part due to poor characterization of IVD. We present a two-class statistical pattern recognition approach for the detection of IVD in the LV from routinely acquired short-axis MRI sequences depicting complete cardiac cycles. First, the LV endocardial and epicardial boundaries were extracted from 33 studies, including dyssynchronous and non-dyssynchronous LVs. A pose normalization procedure was then applied to align the resulting spatio-temporal characterizations of LV wall motion, before training a classifier using principal component analysis plus linear discriminant analysis. Classification results provided a correct detection ratio of 90.9%, compared to just 62.5% provided by current determinants of patient eligibility for therapy