Graph Cut-based Automatic Segmentation of Lung Nodules using Shape, Intensity, and Spatial Features


This paper presents a new, fully automatic method of accurately extracting lesions from CT data. It first determines, at each voxel, a fivedimensional feature vector that contains intensity, shape index, and 3D spatial location. Then, non-parametric mean shift clustering is applied to produce intensity and shape mode maps. Finally, a graph cut algorithm… (More)


1 Figure or Table