Fast Constrained Surface Extraction by Minimal Paths

A new approach performing surface extraction from 3D images under user defined geometrical constraints is presented. The constraints are introduced through boundary curves given by the user or by preprocessing. Our approach is based on minimal paths that integrate the information coming from the constraint curves and from the image through a potential representing the features to extract. The minimal paths build a network of curves that represent a first approximation of the desired surface. An interpolation method is then used to build a mesh or an implicit representation based on the information retrieved from the network of paths. Our paper describes a fast construction obtained by exploiting the Fast Marching algorithm and a fast analytical interpolation method. Moreover, a model extension as well as a Level set method can be used to refine the segmentation when higher accuracy is required. The algorithm has been successfully applied to 3D ultrasound heart images and synthetic imag...

• Type: Journal
• Year: 2006
• Where: IJCV
• Authors: Roberto Ardon, Laurent D. Cohen
• Keywords: IJCV 2006, Images, Interpolation Method, Minimal Paths