By Topic

The analysis of biological cell behaviors using Bayesian bidirectional network model

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Keming Zhang ; Dept. of EE, Shanghai Jiaotong Univ., Shanghai, China ; Hua Yang ; Chongyang Zhang

As the increasing demand on medical and biological research, automatic behavior analysis for large scale biological cells faces a big challenge. A novel Bayesian bidirectional network model is proposed in this paper for detection and statistic of the cells behaviors such as birth, vanishing, split, merging and so on. First the cells in every frame are distinguished from background by mean shift filter and level set segmentation. Then we build a bidirectional Bayesian network by modeling the cell regions as vertices and the similarity of cell regions in successive frames as directed edges. By applying weights on the directed edges, the graph model represents the relation between cell regions. Finally, in order to remove fake edges, a iterative algorithm is adopted for analyzing the graph model and obtaining the optimal path of each cell. Experiment result shows that the proposed method is effective and accurate to detect most cells behaviors.

Published in:

Biomedical Engineering and Informatics (BMEI), 2010 3rd International Conference on  (Volume:6 )

Date of Conference:

16-18 Oct. 2010