A snake for CT image segmentation integrating region and edge information

The 3D representation and solid modeling of knee bone structures taken from computed tomography (CT) scans are necessary processes in many medical app lications. The construction of the 3D model is generally carried out by sta cking the contours obtained from a 2D segmentation of each CT slice, so the quality of the 3D model strongly depends on the precision of this segmenta tion process. In this work we present a deformable contour method for the p roblem of automatically delineating the external bone (tibia and fibula) co ntours from a set of CT scan images. We have introduced a new region potent ial term and an edge focusing strategy that diminish the problems that the classical snake method presents when it is applied to the segmentation of C T images. We introduce knowledge about the location of the object of intere st and knowledge about the behavior of edges in scale space, in order to en hance edge information. We also introduce a region information aimed at com plementing edge information. The novelty in that is that the new region pot ential does not rely on prior knowledge about image statistics; the desired features are derived from the segmentation in the previous slice of the 3D sequence. Finally, we show examples of 3D reconstruction demonstrating the validity of our model. The performance of our method was visually and quan titatively validated by experts. (C) 2001 Elsevier Science B.V. All rights reserved.