Knee osteoarthritis classification algorithm based on improved DenseNet network
Aiming at the problem of low classification accuracy of knee osteoarthritis,an improved DenseNet algorithm is proposed.On the basis of the Dense201 model,a shallow convolution block is added,and the shallow features are spliced with the deep features to enrich the discriminant information of the classification layer.Use data enhancement methods such as horizontal flipping and image rotation to expand the data set,and use transfer learning to train the model to reduce overfitting.The results of comparative experiments show that the classification accuracy of the improved DenseNet model reaches 91.0%,which improves the classification accuracy compared with the original DenseNet network.
万方数据
