Segmentation of Histopathological Section Using Snakes
This paper presents a semi-automatic method for segmentation of digital images. The segmentation method is based on snakes and a novel implementation of the snake evolution algorithm is presented. Analytical expressions describing the snake evolution are derived using the Fourier transform. These expressions can be sampled and used in a fast algorithm for snake propagation. Experiments are carried out on images of histopathological tissue sections and the results are very promising. In particular the method is able to cope with overlapping nuclei.
- 1.Jarkrans, T.: Algorithms for cell images analysis in cytology and pathology. PhD thesis, Faculty of Science and Technology, Uppsala University (1996)Google Scholar
- 6.Xu, C, Prince, J.L.: Gradient vector flow: A new external force for snakes. In: IEEE Proc. on Computer Vision and Pattern Recognition. (1997) 66–71Google Scholar
- 10.Xu, C.: Deformable models with applications to human cerebral cortex reconstruction from magnetic resonance images. PhD thesis, Johns Hopkins University (2000)Google Scholar
- 11.Xu, C., Prince, J.L.: Global optimality of gradient vector flow. In: Proc. Conference on Information Sciences and Systems. (2000)Google Scholar