Pneumonia Image Recognition Based On Deep Learning

This article introduces a comprehensive method for diagnosing pneumonia using chest X-ray (CXR) images. By using deep learning models for feature extraction and machine learning methods for classification, the effectiveness of feature extraction has been evaluated using CNN, ResNet.50, and ViT models. The performance of random forest and logistic regression classifiers based on these models were compared, conducting a comprehensive evaluation of accuracy and F1 score to determine the most effective model. This study addresses the challenges of diagnosing artificial pneumonia and emphasizes the urgency of automated solutions. In the end, the combination of ResNet.50 and logistic regression achieved higher accuracy (78.68%), higher precision (99.99%), and more ideal F1 score (0.6239). These results demonstrate that the application of deep learning in clinical diagnosis can improve the clinical efficiency and accuracy of pneumonia detection, which is beneficial for the subsequent treatment of patients.