Cell boundary analysis using radial search for dual staining techniques

Abstract

In medical image analysis and segmentation, many conventional methods work very well on good quality tissue section images, but often fail when the images are not of good quality. Active contours or snakes are widely used in medical image processing applications especially for boundary detection. However, the problems with initialization and poor performance of snakes on noisy images limit their efficacy. As an alternative, this research presents an efficient and robust method to segment cell nuclei and their respective boundaries for low contrast cell images using a combination of a radial search and interpolation methods. This radial search method can be used in medical image analysis and segmentation applications for images which are very noisy or whose structural regions are not very clear. The processes in this method consists of (1) extracting the location of the cell nuclei (2) finding the edge information of the given image (3) applying radial search on the edge image patch for finding the radial initialization and finally (4) using an interpolation method to find the desired boundary points, which describe the potential boundary points to best fit to that candidate shape or cell. The results shown on the images of branch aorta of rabbit are suggesting that the proposed radial search method correctly finds the boundaries even on very low contrast images, which can be used for further medical image analysis.