Segmentation of Brain Tumors in CT Images Using Level Sets
This paper proposes an approach based on level sets to segment brain tumors from CT images. Combining edge information with region information dynamically, the novel method introduces a new energy function model, which will make the initial contour evolve towards the desirable boundary while not leak at weak edge positions. In addition, re-initialization of the evolving level set function is avoided by introducing a new simple regularization term, which can eliminate radical changes of level set function(LSF) far away from the contour, and make the LSF prone to be a signed distance function around the contour as well. Experimental results demonstrate that the proposed method performs well on CT images, and can segment brain tumors exactly.
KeywordsBrain Tumor Active Contour Regularization Term Initial Contour Signed Distance Function
Unable to display preview. Download preview PDF.
- 1.Osher, S., Fedkiw, R.: Level Set Methods and Dynamic Implicit Surfaces. Springer (2002)Google Scholar
- 3.Li, C., Xu, C., Gui, C., Fox, M.: Level set evolution without re-initialization: a new variational formulation. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 430–436 (2005)Google Scholar
- 7.Chen, S., Radke, R.: Level set segmentation with both shape and intensity priors. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 763–770 (2009)Google Scholar