A Region based Active Contour Approach for Liver CT Image Analysis Driven by Local likelihood Image Fitting Energy
Sajith A.G1, Hariharan S2
1Sajith A.G, Research Scholar, Department of Electrical Engineering, College of Engineering, Trivandrum (Kerala), India.
2Dr. Hariharan S, Professor, Department of Electrical Engineering, College of Engineering, Trivandrum (Kerala), India.
Manuscript received on 13 June 2017 | Revised Manuscript received on 20 June 2017 | Manuscript Published on 30 June 2017 | PP: 15-23 | Volume-6 Issue-5, June 2017 | Retrieval Number: E4986066517/17©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Computer tomography images are widely used in the diagnosis of liver tumor analysis because of its faster acquisition and compatibility with most life support devices. Accurate image segmentation is very sensitive in the field of medical image analysis. Active contours plays an important role in the area of medical image analysis. It constitute a powerful energy minimization criteria for image segmentation. This paper presents a region based active contour model for liver CT image segmentation based on variational level set formulation driven by local likelihood image fitting energy. The neigh bouring intensities of image pixels are described in terms of Gaussian distribution. The mean and variances of intensities in the energy functional can be estimated during the energy minimization process. The updation of mean and variance guide the contour evolving toward tumor boundaries. Also this model has been compared with different active active contour models. Our results shows that the presented model achieves superior performance in CT liver image segmentation.
Keywords: Active Contours, Chan-Vese Model, Level Sets
Scope of the Article: Image Processing