A novel algorithm based on Adaptive Thresholding for Classification and Detection of Suspicious Lesions in Mammograms

Mammography is the most effective procedure for the early detection of breast cancer. The segmentation of mammograms plays a major role in isolating areas which can be subject to tumors. The identification of these zones is generally done in three stages: pectoral muscle segmentation, hard density zone detection and texture analysis of regions of interest. In this paper, a novel algorithm for detection of suspicious masses from mammographic images is presented. The algorithm utilizes the combination of Classification of mammograms and Detection of suspicious lesions in mammograms using image processing tool. The objective of this work is to contribute to improved diagnosis, prognosis, and prediction of breast cancer