Research on Pneumothorax Classification Model of DenseNet Based on Multilayer Network Optimization

Abstract

This article establishes the DenseNet based on multilayer network optimization (DenseNet-MNO) using a binary dataset of pneumothorax. This method optimizes multiple network layers and ensures the convergence of the neural network by reducing the learning rate with each iteration. Then, the binary cross-entropy loss function and accuracy evaluation function iteratively evaluated the effectiveness of the deep learning model and conducted multiple experiments. The experimental results show that during the iteration process, the loss is reduced, and the accuracy is improved. The DenseNet-MNO classification model has a strong generalization ability and will not overfit. The classification accuracy is between 80% and 85%. The DenseNet-MNO classification model can accurately detect the condition of pneumothorax, providing technical support for detection technology.