Histogram statistics and GLCM features of breast thermograms for early cancer detection

Breast cancer is one of the diseases with the highest mortality rate among women. Early detection is the key to decreasing the rate. Cancerous cell increases the blood circulation, thus temperature around skin surface. Thermography is a potential screening method for early detection of breast cancer because it is non-invasive, radiation-free and can identify cell metabolism activity, i.e., the heat around the cancerous area. This paper presents an analysis of healthy and cancerous breast based on intensity value of grayscale thermograms. We use histogram statistics features, and gray level co-occurrence matrix (GLCM) features. We inspect 18 healthy and 21 cancerous breast images from Database for Mastology Research (DMR) dataset. Experiment results showed that mean, entropy and skewness values are the statistical features that can indicate whether the thermograms contains cancerous cell. Furthermore, the energy, homogeneity and contrast of healthy and malignant cells of the GLCM features are significantly distinctive, thus can also be used as discriminative features.