An Efficient System for Cancer Detection using Digital Mammograms
Ashraf Anwar · IOSR Journal of Computer Engineering · 2017
Breast cancer can be considered one of the most dangerous types of cancer among women.Early detection of breast cancer leads to significant improvements in treatment.Digital mammograms are one of the most effective means for detecting breast cancer in early stages.In this paper, an efficient system based on performing professional pre-processing phase and on applying Discrete Cosine Transform (DCT) for features extraction, and support vector machine has been used for classification into benign and malignant.We have used Mias data set for experimentation purpose.We tune the coefficients of DCT to get the best sensitivity, specificity, positive predicitivity, and accuracy results.We reach 100% performance rate in some cases.