A Fast Level Set Algorithm for Liver Tumor Segmentation
Sajith A.G1, Hariharan.S2
1Sajith A.G, Electrical & Electronics, Sarabhai Institute of Science and Technology, Kerala, India.
2Hariharan S, Electrical & Electronics, College of Engineering, Kerala, India.
Manuscript received on May 27, 2013. | Revised Manuscript received on June 10, 2013. | Manuscript published on June 30, 2013. | PP: 400-404 | Volume-2, Issue-5, June 2013. | Retrieval Number: E1877062513/2013©BEIESP

Open Access | Ethics and Policies | Cite
© 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: Accurate and fast image segmentation algorithm is of paramount importance for a wide range of medical imaging applications. The most widely used image segmentation algorithms are region based and typically rely on the homogeneity of the image intensities in the regions of interest, which often fail to provide accurate segmentation results due to the gradient function gives very small values at the boundary and makes the speed of the moving contour low and the gradient based term can never stop the level set evolution completely even for ideal edges, making leakage often inevitable. In this paper a fast narrow band distance preserving level set evolution algorithm is used for liver tumor segmentation. Experimental result for CT images shows desirable performances of the method.
Keywords: Level set, FCM.