3D shape decomposition for gallbladder anomaly analysis

This paper presents an approach to the gallbladder anomaly analysis using 3D shape modeling and 2D image segmentation. The 3D shape of gallbladder is represented as a surface mesh model, which is constructed from the contours segmented in CT data by a scheme of propagation based voxel classification. To better extract the shape feature, the surface mesh is further down-sampled by a decimation filter and smoothed by a Taubin algorithm. The curvatures are computed on the regularized mesh for the salience region localization on the surface. With a given tolerance the 3D shape can be decomposed and represented as 3D ellipsoids, which reveal the shape topology and anomaly of a gallbladder. Preliminary experiments on 10 sets of gallbladder CT data have shown the promising results in the shape structure extraction and shape anomaly detection.