Segmentation of Breast Thermal Images Using Kapur's Entropy and Hidden Markov Random Field

摘要

Breast cancer is one of the common cancers in women community and the early diagnosis of breast cancer will improve the survival rate. Thermography is one of the non-invasive and most efficient screening modality for the breast cancer detection. Extracting the cancerous region/ tumor from breast thermal image is widely preferred to have a clear idea about the disease and the infected section. The success of disease prediction and analysis depends mainly on the segmented tool considered to analyse thermograms. In this work, a two stage approach combining the Firefly Algorithm (FA) assisted Kapur's thresholding and Hidden Markov Random Field (HMRF) based segmentation is proposed for the extraction of the region of interest from breast thermal images. The results obtained from the HMRF are then validated with the results of Distance Regularized Level Set (DRLS). From the result, it is observed that, HMRF provides better tumor mass compared to the DRLS with better values of image similarity index.