Cell segmentation and NC ratio analysis for biopsy images using marker controlled watershed algorithm

Segmentation of cell nuclei and cytoplasm is an important task in most of the medical images. Microscopic cell image analysis is the fundamental tool for biological research. Visual inspection of cellular images is often insufficient to detect and describe the important changes in cellular morphology. In this paper, the cell segmentation approach uses the marker controlled watershed based approach, which is used to avoid over segmentation. The main goal of watershed transform is to distinguish the regional minima of original images, which are the nuclei´s region and it integrates the convergence index filter to segment the region of cell´s cytoplasm. This cell segmentation approach contributes the way for the analysis of nuclear-to cytoplasm ratio (NC ratio), which is significant to distinguish or detecting the prior symptoms of diseases like cancer based on normal and abnormal NC ratios.