Early Detection of Breast Cancer from Mammogram Images Using Fuzzy and Non Sub Sampled Contourlet Transform Techniques

Abstract

One of the most significant causes of increased women death rate in the world is due to Breast cancer. Mammography is the most effective method for early detection of breast diseases. The main aim of mammography is to detect tiny, non-palpable cancers during its premature stage. Conversely, mammograms are extremely complex to deduce as the pathological transformations of the breast are slight and their visibility is very poor with low contrast and noise. Mammograms have the significant information likemicrocalcifications and masses, which are complicated to detect because mammograms are of blur and fuzzy. newline Breast Cancer detection using mammography mainly concentrates on features of tiny microcalcifications, together with the number, size and spatial arrangement of microcalcification clusters and morphological features of individual microcalcifications. It is necessary to enhance the mammogram images for accurate identification and early diagnosis of breast cancer. Since, Radiologists can miss the detection of a significant proportion of abnormalities it results in high rate of false positives. So, it would be valuable to develop a computer aided method for mass/tumor classification based on the extracted features from the Region of Interest (ROI) in mammograms. The Region of Interest has to be segmented from the digital mammogram using the segmentation techniques. newline