Mammogram density classification using deep convolutional neural network

Artificial intelligence plays an important role in the classification of medical images for computerized diagnosis of the disease. The computer-aided medical imaging analysis system is developed for breast tissue density classification in mammogram images. Mammogram density is considered as significant predictive markers for breast cancer detection, treatment and management. Recently, deep learning techniques achieved impressive results in computer-assisted disease diagnosis. The deep learning technique such as the convolution neural network (CNN) is used for automated classification of mammogram density as fatty, dense and glandular. This study investigates how computer-aided medical imaging analysis system provides a reliable classification of mammogram density. The proposed methodology is evaluated using a mini-MIAS (Mammogram Image Analysis Society) database. We obtained an average accuracy of 98.5%. So, the proposed CAD system aids the clinicians in the classification of mammogram density.