Breast Cancer Detection Using Hybrid Model Of Quantum Coupled Neural Network
Abstract
The detection of breast cancer faced a problem of feature selection and optimization. The process of feature selection and optimization improves the accuracy of detection and classification. The modelling of the neural network is an excellent contribution to the diagnosing of medical diseases. The process of modelling designs the model of the hybrid classifier using a quantum neural network and pulse coupled neural network. The hybrid neural network is efficient for the detection of breast cancer. The processing of quantum improves the selection of features and mapping of feature space of data. In this paper proposed a model for cancer detection: the proposed model based on the fashion of feature optimization. The process of feature extraction applied discrete wavelet transform, wavelet transform is a rich dominated function of texture feature extraction. The texture feature is the most common features of breast cancer image captured by the mammogram. The proposed algorithm of breast cancer detection tested on reputed public dataset MIAS. For the validate of proposed algorithm measured standard empirical parameters. The proposed algorithm compares with existing methods such as SVM and ensemble of KNN.