<![CDATA[The global COVID-19 pandemic has posed significant challenges in the early detection and management of pneumonia caused by the virus. One effective way to detect COVID-19 pneumonia is through chest X-ray imaging, which offers advantages in terms of accessibility and cost. However, the manual diagnostic process requires time and high accuracy. This study aims to develop a hybrid convolutional neural network (CNN) model capable of automatically and accurately detecting COVID-19 pneumonia from chest X-ray images. The methodology used in this research involves meticulous data processing, including data augmentation and image quality enhancement, as well as the application of a hybrid CNN architecture combining VGG-16 and ResNet-50 models for feature extraction and complex pattern processing. Experimental evaluation results show that this model achieves 96.5% accuracy, 97.2% precision, 96.5% recall, and 96.8% F1-score in detecting COVID-19 pneumonia. The model also demonstrates good performance in distinguishing non-COVID pneumonia and healthy conditions, with accuracy ranging from 96.5% to 96.6%. These findings highlight the potential of artificial intelligence in enhancing diagnostic efficiency and accuracy, particularly in public health emergencies. This research is expected to contribute to the development of reliable AI-based diagnostic solutions to assist healthcare professionals in the early detection of COVID-19 pneumonia and other pulmonary infections.]]>
Copyrights © 2024
