Research on Aided Diagnosis of Breast Tumors Based on Deep Belief Networks
XU Kaibo
LUO Guangxiang
SUN Zhenhui
Abstract：Aiming at the problem that the accuracy of breast tumor is low when applied the traditional shallow machine learn?ing recognition algorithm,a new breast tumor recognition model which based on deep belief network(DBN)is proposed. Firstly, preprocessing of the original breast tumor feature data is carried out. Then a deep belief network model is constructed to train and recognize the breast tumor feature data. Finally,the recognition accuracy of deep belief network model is compared with several tra?ditional shallow machine learning models. The simulation experiments results show that the new proposed model reached the highest average recognition accuracy(98.45%),which performance are better than traditional shallow machine learning algorithm such as BP neural network,LVQ neural network ,decision tree and support vector machine algorithm.
Keywords：shallow machine learning algorithmdeep belief networkbreast tumorsaided diagnosis
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 582-586 )