Local and Global Thresholding-Based Breast Cancer Detection Using Thermograms

In a recent study, to detect breast cancer abnormalities, thermography has been observed to be a qualitative modality. Due to an increase in blood vessel activity, the cancer cells and the tissues become hotter. Thus, by using thermography, the thermograms of the image are captured which depict the surface temperature of the breast, where the hot spot is indicated by the higher temperature. This modality has increased the non-invasiveness in detecting breast abnormalities. The different channels of the RGB (Red, Green, and Blue) image gives information of the different intensity of the color with respect to the image. In this work, the breast thermograms corresponding to the red channel are extracted for analysis. Further, three different thresholding methods viz., Otsu thresholding, Adaptive Mean Thresholding, and Adaptive Gaussian Thresholding methods are applied which depict the local image characteristics of the image. The image enhancement methods improve the quality of the image. Further, the statistical features are extracted from the obtained thresholded images, and two different classifiers Random Forest and Decision Tree are applied for classifying the normal and abnormal breasts.