3D level set model for medical image segmentation

Three-dimensional segmentation of medical volumetric image data as a basis of 3D reconstruction has important significance in biomedicine engineering. However, noises or intensity inhomogeneity in practical application often make 3D medical images segmentation become formidable. To effectively alleviate these problems, this paper presents a novel variational level set framework using neighbors statistical analysis. Firstly, a basic 3D level set model is constructed based on Bayesian inference for the segmentation of objects from 3D volumetric image data. Then neighbors statistical analysis is introduced into above model in order to overcome disturbances caused by noise and intensity inhomogeneity. Experiments have demonstrated that the proposed method performs well in 3D volumetric data segmentation in intensity inhomogeneity and noises scene.

[1]  S. Osher,et al.  Regular Article: A PDE-Based Fast Local Level Set Method , 1999 .

[2]  Tony F. Chan,et al.  A Multiphase Level Set Framework for Image Segmentation Using the Mumford and Shah Model , 2002, International Journal of Computer Vision.

[3]  Serge Miguet,et al.  Weighted Adaptive Neighborhood Hypergraph Partitioning for Image Segmentation , 2005, ICAPR.

[4]  Guido Gerig,et al.  Level-set evolution with region competition: automatic 3-D segmentation of brain tumors , 2002, Object recognition supported by user interaction for service robots.

[5]  Bostjan Likar,et al.  A Review of Methods for Correction of Intensity Inhomogeneity in MRI , 2007, IEEE Transactions on Medical Imaging.

[6]  Ronald Fedkiw,et al.  Level set methods and dynamic implicit surfaces , 2002, Applied mathematical sciences.

[7]  Chunming Li,et al.  Brain MR Image Segmentation Using Local and Global Intensity Fitting Active Contours/Surfaces , 2008, MICCAI.

[8]  Daniel Cremers,et al.  On the Statistical Interpretation of the Piecewise Smooth Mumford-Shah Functional , 2007, SSVM.

[10]  S. Osher,et al.  A PDE-Based Fast Local Level Set Method 1 , 1998 .

[11]  Chunming Li,et al.  Level set evolution without re-initialization: a new variational formulation , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[12]  Patrick Bouthemy,et al.  Robust Adaptive Segmentation of 3D Medical Images with Level Sets , 1999 .

[13]  Chunming Li,et al.  Implicit Active Contours Driven by Local Binary Fitting Energy , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.