Construction of Left Ventricle 3D Shape Atlas from Cardiac MRI

摘要

In this paper, we present an effective algorithm to construct a 3D shape atlas for the left ventricle of heart from cardiac Magnetic Resonance Image data. We derive a framework that creates a 3D object mesh from a 2D stack of contours, based on geometry processing algorithms and a semi-constrained deformation method. The geometry processing methods include decimation, detail preserved smoothing and isotropic remeshing, and they ensure high-quality meshes. The deformation method generates subject-specific 3D models, but with global point correspondences. Once we extract 3D meshes from the sample data, generalized Procrustes analysis and Principal Component Analysis are then applied to align them together and model the shape variations. We demonstrate the algorithm via a set of experiments on a population of cardiac MRI scans. We also present modes of variation from the computed atlas for the control population, to show the shape and motion variability.