G. Annapoorani*, G. Lathaselvi and Javid Ali Pages 1 - 15 ( 15 )
The Deep Neural Networks have gained prominence in the biomedical domain becoming the most sought after machine learning technology. Mammograms can be used to detect breast cancers with high precision with the help of Convolutional Neural Network (CNN) which is a deep learning technology. An exhaustive labeled data is required to train the CNN from the scratch. This can be overcome by deploying Generative Adversarial Network (GAN) which comparatively needs lesser training data during mammogram screening. In the proposed study that is carried out, application of GANs in estimating the breast density, high-resolution mammogram synthesis in clustered microcalcification analysis, effective segmentation of breast tumor, analyzing the shape of breast tumor, extraction of features and augmenting the image during mammogram classification have been extensively reviewed.
General adversarial networks, breast density estimation, microcalcification, breast tumour segmentation and shape analysis, feature extraction, mammogram augmentation and classification
Department of Information Technology, University College of Engineering, Anna University, Tiruchirappalli, Department of Information Technology, St. Joseph’s College of Engineering, Chennai, Department of Information Technology, St. Joseph's Institute of Technology, Chennai