Performance analysis and detection of micro calcification in digital mammograms using wavelet features

Abstract

Breast cancer has been most persistent form of common cancer in women. It is also the leading cause of fatality in women each year. Breast cancer is much less common in younger women and is most often analyzed when women are over 60. One of the leading methods for interpretation of breast cancer is screening mammography. The appearance of micro-calcification in mammograms is an initial sign of breast cancer. To overcome the issue automated micro-calcification exposure techniques play a vital role in cancer diagnosis and treatment. This paper aims to develop an automatic system to classify the digital mammogram images into Benign or Malignant images. We have proposed artificial neural network based classifier to detect the micro calcification at each location in the mammogram images. The proposed method has been evaluated using Mammogram Image Analysis Society (MIAS) database. Experimental results show that, when compared to several other methods RBF shows 93% micro calcification detection in mammograms.