Design & Development of Deep Learning Algorithm with Convolutional Neural Networks for Breast Cancer Classification

This paper presents a method for classification of normal and abnormal tissues in mammograms using a deep learning approach. Breast biopsies based on the results of mammography and ultrasound have been diagnosed as benign at a rate of approximately 40 to 60 percent. Breast cancer is one of the primary causes of cancer death among the women world population. For early detection of breast cancer in women Mammography and ultrasound methods are used. This is a holistic methodology which can help classify a whole mammography exam, containing the MLO views along with CC and the segmentation maps, as compared to the classification of individual lesions, which is the dominant approach in the field. We are also demonstrating that the system discussed in this paper is capable of using the segmentation maps that are generated by micro-calcification detection systems and automated mass detection systems, and still produces highly accurate results.