Locating Liver Lesion with Local C-V Level Set and Image Registration

Zhaohui Luo (Hunan University of Science and Technology)
Xi Zaifang (Hunan University of Science and Technology)
Wang Junnian (Hunan University of Science and Technology)

Indonesian Journal of Electrical Engineering and Computer Science
Vol 12, No 6: June 2014

In this paper, we proposed comprehensive methods to locate the liver lesion in multi-phase CT images. It first construct a local liver lesion image from the image in which liver lesion differs from liver tissue most markedly, then pre-segment the lesion with OTSU method to get the initial contour, and evolve the active contour with local C-V level set method to get the final contour of lesion in the CT image. Finally locate the liver lesion in CT images of other phases by image registration. Experiments showed this method can extract liver tumor efficiently.A well-prepared abstract enables the reader to identify the basic content of a document quickly and accurately, to determine its relevance to their interests, and thus to decide whether to read the document in its entirety. DOI : http://dx.doi.org/10.11591/telkomnika.v12i6.5393