Time resolved three-dimensional automated segmentation of the left ventricle

This paper describes a robust approach for multimodality segmentation of the cardiac left ventricle. The method is based on the concept of deformable models, but extended with an enhanced and fast edge detection scheme that includes temporal information, and anatomical a priori information. The algorithm is implemented with a fast numeric scheme for solving energy minimization, and efficient filter nets for fast edge detection. This allows clinically applicable time for a whole time resolved 3D cardiac data set to be achieved on a standard desktop computer. The algorithm is validated on images acquired using MRI gradient echo, MRI (SSFP) images, and Cardiac CT The complete algorithm is implemented into a software package freely available for non commercial research at http://segment.heiberg.se