New algorithm for 3D automatic detection and tracking of cardiac wall motion

We present a new algorithm for surface tracking of volumetric cardiac data with a Gradient-Vector-Flow-(GVF)-based deformable parametric model applied to non linear anisotropic diffusion filtered images. The system allows automated quantitative image analysis of sequences of volumetric medical data in order to track endocardium and epicardium in anatomical studies with Magnetic Resonance. In order to test the developed algorithm on real data, dynamic sequences of multislice magnetic resonance image have been processed.