Paper: | FR-PM-PS4.3 |
Session: | Cellular and Molecular Image Analysis |
Time: | Friday, April 7, 13:30 - 14:50 |
Presentation: |
Poster
|
Title: |
Shape-Constrained Repulsive Snake Method to Segment and Track Neurons in 3D Microscopy Images |
Authors: |
Hongmin Cai; University of Hong Kong | | |
| Xiaoyin Xu; Harvard Center for Neurodegeneration and Repair | | |
| Ju Lu; Harvard University | | |
| Jeff Lichtman; Harvard University | | |
| S. P. Yung; University of Hong Kong | | |
| Stephen T. C. Wong; Harvard Center for Neurodegeneration and Repair | | |
Abstract: |
To study the structure and branch pattern of neurons, it is important to segment neurons at first. We develop a snake model based on repulsive force to segment neurons in 3D microscopy image stacks. To overcome the difficulty that the boundary between two adjacent neurons is weak and snakes tend to make mistakes, we introduce a shape constraint on the snake deformation and use repulsive force to keep snakes corresponding to adjacent snakes from merging into one. After obtaining the contours on the first image slice, we project them to the next slice as initialization for snakes and repeat the process for all the slices in a 3D image stacks. Individual neuron can then be segmented by connecting the corresponding snake through all slices. Results obtained from processing real data show that the method can successfully segment two or more neurons that are close to each other by alternating repulsive force generated from the neighboring objects. |