The Application of the Snake Model in Carcinoma Cell Image Segment
Accurate cell nucleus segmentation is crucial for the development of automated cytological cancer recognition and diagnosis system. The paper proposes an improved Snake model for esophageal cell image based on the study of several main methods for esophageal cell image and analysis of their advantages and disadvantages. The novel cell nucleus segmentation method has been tested on a number of cell images obtained from esophageal smear slide and the results are encouraging. Experimental results show that the presented method performs well on both well-separated nuclei and some overlapped nuclei.
Keywordssnake model image segmentation cell Image cell boundary esophageal cancer
Unable to display preview. Download preview PDF.
- 1.Kass, M., Witkin, A.P., Terzopoulo, S.D.: Snake: Active Contour Models. In: Process. First Int. Conf. Compute. Vision, London, pp. 259–268 (1987)Google Scholar
- 5.Dwi, A.: Cell Segmentation with Median Filter and Mathematical Morphology Operation. In: Proc. Of The IEEE 10th International Conference On Image Analysis And Processing, pp. 1034–1046 (1999)Google Scholar
- 7.Yi, Y.: The New Image Segmentation Based on the Snake Model. First Military Medical University. 32–67 (2005)Google Scholar
- 8.Xue, D.J., Ping, X.J.: The New Image Segmentation Based on Geomatics Morphology. Journal of Information Engineering University 4(4), 88–92 (2003)Google Scholar
- 9.Hang, D., Yu, R.: The Snake Model Uses in Edge Detection. Journal of Shanghai Jiaotong University 34, 848–850 (2000)Google Scholar
- 10.Zhang, Y.J.: Image Segmentation Appraisal Classification and Comparison. Journal of Image and Graphics 5A(1), 39–43 (2000)Google Scholar
- 11.Zhao, B.J., Li, D.: The Improvement Snake Model for Complex Edge Detection. Journal of Beijing Institute of Technology 24(2), 162–165 (2004)Google Scholar