@article{(Open Science Index):https://publications.waset.org/pdf/10002999,
	  title     = {3D Liver Segmentation from CT Images Using a Level Set Method Based on a Shape and Intensity Distribution Prior},
	  author    = {Nuseiba M. Altarawneh and  Suhuai Luo and  Brian Regan and  Guijin Tang},
	  country	= {},
	  institution	= {},
	  abstract     = {Liver segmentation from medical images poses more
challenges than analogous segmentations of other organs. This
contribution introduces a liver segmentation method from a series of
computer tomography images. Overall, we present a novel method for
segmenting liver by coupling density matching with shape priors.
Density matching signifies a tracking method which operates via
maximizing the Bhattacharyya similarity measure between the
photometric distribution from an estimated image region and a model
photometric distribution. Density matching controls the direction of
the evolution process and slows down the evolving contour in regions
with weak edges. The shape prior improves the robustness of density
matching and discourages the evolving contour from exceeding liver’s
boundaries at regions with weak boundaries. The model is
implemented using a modified distance regularized level set (DRLS)
model. The experimental results show that the method achieves a
satisfactory result. By comparing with the original DRLS model, it is
evident that the proposed model herein is more effective in addressing
the over segmentation problem. Finally, we gauge our performance of
our model against matrices comprising of accuracy, sensitivity, and
specificity.
},
	    journal   = {International Journal of Computer and Information Engineering},
	  volume    = {9},
	  number    = {12},
	  year      = {2015},
	  pages     = {2435 - 2441},
	  ee        = {https://publications.waset.org/pdf/10002999},
	  url   	= {https://publications.waset.org/vol/108},
	  bibsource = {https://publications.waset.org/},
	  issn  	= {eISSN: 1307-6892},
	  publisher = {World Academy of Science, Engineering and Technology},
	  index 	= {Open Science Index 108, 2015},
	}