MLO and CC View of Feature Fusion and Mammogram Classification Using a Deep Convolution Neural Network
V. Sridevi, J. Abdul Samath · Apple Academic Press eBooks · 2024
Breast cancer is a frequent type of cancer in women all over the world. The improvement of computer-aided system helps the radiologist with the effective analysis and diagnosis of breast cancer. It presents a computational methodology for classifying mammogram cancer as normal, benign, and malignant from the CC and MLO views of mammogram images. The proposed strategy consists of feature extraction, multiple-view feature fusion, and classification. The input images are fed into feature extraction where convolution neural network (CNN) is applied. The CNN is well suited for feature extraction, feature fusion, and mammogram classification. In this framework, the convolution layer, pooling, and activation function are used as feature extraction techniques. After the process of feature extraction, feature fusion is employed by the average pooling of CNN. The feature fusion will increase or maximize the relevant information of the breast image. Finally, obtained features from the fusion are fed into the CNN classifier, in which 230 softmax and fully connected layers are employed as classifier techniques. The proposed work achieves 96.4% accuracy in classifying breast cancer from MLO and CC views using a hybrid feature with the CNN classifier.