Automated Cell Nuclei Segmentation and Classification of Squamous Cell Carcinoma from Microscopic Images of Esophagus Tissue

The task of segmenting cell nuclei in microscopic images is a classical image analysis problem. The accurate nuclei segmentation may contribute to development of successful system which automates the analysis of microscope images for pathology detection. The major features of malignancy are related with the nuclei of the cells. It is therefore essential to operate a segmentation of the image, to isolate the nuclei from the rest of the image that is from the cytoplasm, and from some other undesirable elements coming from the image preparation. In this paper, we have proposed an automated cell nuclei segmentation and classification of Squamous Cell Carcinoma (SCC) from microscopic images of esophagus tissue using moment based textural features. The morphological operations are used to remove the squaring effect on the boundary of nuclei. The proposed method is applied on color microscopic images in RGB color space. The experimental results show that the proposed method can efficiently segment cell nuclei and classify squamous cell carcinoma from the microscopic images. Also the results obtained are in good agreement with the manual segmentation done by the medical expert.