Combining trace transform and SVD for classification of micro-calcifications in digital mammograms

Abstract

Breast cancer has been most frequent form of common cancer in women. It is also the leading cause of mortality in women each year. Breast cancer is much less common in younger women and is most often diagnosed when women are over 60. Breast cancer is the second-most common and leading cause of cancer death among women. It has turn into a major health issue in the world over the past 50 years, and its occurrence has increased in recent years. One of the leading methods for diagnosing breast cancer is screening mammography. The appearance of micro-calcification in mammograms is an early sign of breast cancer. To overcome the issue automated micro-calcification detection 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 Support vector machine (SVM) based classifier for to detect the microcalcification at each location in the mammogram images. The proposed method has been implemented in three stages (a) preprocessing (b) feature extraction (c) SVM classification. The proposed method has been evaluated using Mammogram Image Analysis Society (MIAS) database. Experimental results show that, when compared to several other methods SVM shows 94.94% micro calcification detection in mammograms.