Classification of Benign/Malignant Digital Mammogram Images using Deep Learning Scheme

Breast cancer (BC) is one of the harsh diseases in women and causes a large diagnostic burden globally. Early diagnosis and treatment of the BC is necessary to plan and execute the treatment. Clinical level detection of the BC is commonly performed using the medical imaging approaches and digital mammogram is one of the common procedures in early screening of the BC. This work aims to develop a deep-learning (DL) based approach to detect the benign/malignant BC from the mammogram. The different phases of the proposed scheme includes; (i) image collection and resizing, (ii) feature extraction with DL-model and best model selection using SoftMax classification, (iii) implementing feature reduction with 50% dropout and serial features integration to get the fused-feature-vector (FFV), and (iv) binary classification and 3-fold cross validation to confirm the performance. In this work, DenseNet (DN) scheme is considered for the evaluation and the achieved result of this study confirms that the Support Vector Machine (SVM) based classification offered >98% result on the MIAS-mammogram database.