Segmentation and Morphometry of Histological Sections Using Deformable Models: A New Tool for Evaluating Testicular Histopathology
This paper presents a tool that uses image segmentation and morphometric methods to evaluate testicular toxicity through the analysis of histological sections of mice testis. The tool is based on deformable models (Snakes) and includes several adaptations to solve important difficulties of histological sections imaging, mainly the low contrast edges between the boundary tissue of seminiferous tubules and the interstitial tissue. The method is designed to produce accurate segmentation and to keep track of tubular identities on images under study. The extracted data can be used straightforwardly to compute quantitative parameters characterizing tubular morphology. The method was validated on a realistic data set and the results were compared with those obtained with traditional techniques. The application of this new technique facilitates measurements allowing assessing a higher number of tubules in a fastest and accurate way.
KeywordsActive Contour Seminiferous Tubule Edge Point Deformable Model Gradient Vector Flow
- 2.Hess, R.A., Nakai, M.: Histopathology of the male reproductive system induced by the fungicide benomyl. Histology and Histopathology 15, 207–224 (2000)Google Scholar
- 4.Xu, C., Prince, J.L.: Gradient Vector Flow. A New External Force for Snakes. In: Proc. IEEE Conf. on Comp. Vis. Patt. Recog (CVPR), pp. 66–71. Comp. Soc. Press, Los Alamitos (1997)Google Scholar
- 7.Guevara, M.A., Rodríguez, R.: Knowledge-based vision techniques to classify sugarcane somatic embryos. In: Proceedings 13th ISPE/IEEE International Conference on CAD/CAM, Robotic and Factories of the Future (CARS & FOF 1997), pp. 388–396 (1997)Google Scholar
- 8.Canny, J.F.: A computational approach to edge detection. IEEE Tra ns. Pattern Anal.Machine Intell. PAMI-8, 678–679 (1986)Google Scholar
- 14.Rodenacker, K., Bengtsson, E.: A feature set for cytometry on digitized microscopic images. Analytical Cellular Pathology 25, 1–36 (2003)Google Scholar