Mammogram Based Automatic Computer Aided Detection Of Masses In Medical Images

Abstract

Breast cancer was a treacherous disease, which leads to large scale of death for women. Substantial numbers of patients are reaching to a progressive breast cancer stage due to increase in the false negatives coming out of cumbersome and tedious job of continuously observing the mammograms in fatigue. Mammogram is a scanning image of breast, used to aid in the early detection as well as diagnosis of breast diseases. Because of high sensitivity, mammogram will lose precision of an image. To overcome this issue, the Automatic Mass Detection of Mammogram was developed based on the Computer Aided Detection (CAD) techniques for the correct identification of cancer in the breast and it gives 80-90% of high detection rate. This technique will guide radiologist to determine the presence of cancer accurately. The proposed Independent Component Analysis will involve local and texture feature for mass detection. The two complex features are extracted, based upon the co-occurrence matrix and optical density transformation to describe local texture characteristic. The proposed method uses Independent Component Analysis for selecting normal and abnormal area of individual region, which will give more accuracy. Finally, compared to LDA the obtained successive rate of accuracy in ICA method is  93.82%