Micro calcification detection in digital mammograms using deep learning approaches

Abstract

Breast Cancer is one of the normal and causing passing among ladies and least essential in men; Micro calcification, an abnormality that leads to breast cancer and is detected by various imaging such as X-ray, Computerized tomography (C.T.), etc. Detection of breast carcinoma is a challenging task since the micro calcifications are buried under the background of mammography. Numbers of studies have shown the early diagnosis is a more effective method to cure breast carcinoma. In this paper, Micro calcification was distinguished by the techniques for profound learning and by numerical figuring. The capabilities of deep learning futures and mathematically calculated features are combined on the characteristic of a deep learning filter. The filtered deep learning feature provides better experimental results compare with the mathematically calculated feature. We obtained 86.6% of overall precision level and sensitivity level by applying the deep learning features filtered and providing better performance with all the features.