Font Size: a A A

Active Contour Models In Medical Image Segmentation

Posted on:2007-02-24Degree:MasterType:Thesis
Country:ChinaCandidate:X F ZhangFull Text:PDF
GTID:2208360182993403Subject:Computer software and theory
Abstract/Summary:PDF Full Text Request
The increasingly important role of medical imaging in the diagnosis and treatment of disease has opened an array of challenging problems centered on the computation of accurate geometric models of anatomic structures from medical images. A promising approach to tackle such problems is the use of active contour models. These powerful models have proven to be effective in segmenting, visualizing, matching and tracking anatomic structures by exploiting constraints derived from the image data together with a priori knowledge about the location, size and shape of these structures. Furthermore, active contour models support highly intuitive interaction mechanisms that allow medical scientists and practitioners to bring their expertise to bear on the image interpretation task.The focus of this dissertation is to investigate active contour models. An energy minimizing formulation is applied to get mathematical representation of an object boundary. The finite difference method is applied to do numerical implementations of the deformable model.GVF model is a kind of representative active contour model. It derives from generalized force balance equations, a vector diffusion equation is employed to diffuse the gradient of an edge map in regions distant from the boundary, yielding a general type of force field which can be decomposed in to an irrotational component and a solenoidal component. The excellence of GVF model is analyzed in this thesis.2D GVF computations are implemented using MATLAB code.In the practice of application, the present models often subject to the influence of noises and fake edges, Based on the multi-scale image analysis, the improved gradient vector flow(GVF) including gradient direction information in the external image force introduced to present a new active contour model. Experiments prove that the new model limits the influence of false edge and noise disturbance and obtains desired segmentation results.
Keywords/Search Tags:Image Segmentation, Active Contour Model, Gradient Vector Flow
PDF Full Text Request
Related items