Appearance based Spatiotemporal Constraint for LV Segmentation in 4D Cardiac SPECTRonghua Yang, Majid Mirmehdi, Xianghua Xie, David Hall, Appearance based Spatiotemporal Constraint for LV Segmentation in 4D Cardiac SPECT. MICCAI Workshop on Cardiovascular Intervetional Imaging and Biophysical Modelling, pp. 84–93. September 2009. PDF, 995 Kbytes.
We propose a novel appearance based spatiotemporal constraint and combine it with a level set based deformable model, which can be used for Left Ventricle segmentation in 4D gated cardiac SPECT, particularly in the presence of perfusion defects. Unlike current shape based constraint works, ours incorporates texture in addition to shape information into a probabilistic constraint, and utilizes spatiotemporal regularization via a Maximum A Posteriori framework. We present comparative results to illustrate the improvement gain.