Extraction of Haralick features from segmented texture multispectral bio-images for detection of colon cancer cells

The automatic recognition and classification of biomedical objects can enhance work efficiency while identifying new inter-relationships among biological features, in this paper Haralick's features based GLCM are applied for classification of cancer cell of textured bio-images. The objective of this work is the selection of the most discriminating parameters for cancer cells. A new approach aiming to detect and classify colon cancer cells is presented. Our detection approach was derived from the "Snake" method but using a progressive division of the dimensions of the image to achieve faster segmentation. The time consumed during segmentation decrease to more than 50%. The efficiency of this method resides in its ability to segment Carcinoma (Ca) type cells that was difficult through other segmentation procedures. Classification of three cell types was based on five Haralicks features, only three Haralicks features were used to assess the efficiency classifications models, including Benign Hyperplasia (BH), Intraepithelial Neoplasia (IN) that is a precursor state for cancer, and Ca that corresponds to abnormal tissue proliferation (cancer). The analysis results show that three parameters (correlation, entropy and contrast) were found to be effective to discriminate between the three types of cells. The results obtained show the efficacy of the method.