| Abstrakt: |
A bacterial, viral, or fungal infection can cause pneumonia, a dangerous respiratory illness. It is a serious global health issue that primarily affects vulnerable populations, such as young children, the elderly, and those with weakened immune systems. This paper explores the diagnosis of pneumonia from chest X-ray images using Convolutional Neural Networks (CNNs), a type of deep learning. on increase the efficiency and accuracy of diagnosis, we use state-of-the-art CNN architectures on a dataset of 5,863 X-ray images classified as pneumonia or normal. The design suggested includes a seven-layer CNN with convolutional neural networks, normalization in batches, the maxpooling dropout, and layers that are dense. To guarantee strong performance, the model has been extensively trained and verified using multiple datasets. The outcomes show just how much better CNN is to more conventional diagnostic techniques at quickly and accurately analyzing X-ray images. Despite multiple limitations such as variations in the quality of images and comprehension of the approach, our study shows the possibility of using deep learning to improve pneumonia diagnosis. This work improves the field of medical imaging with the aim of improving the results for patients while making the best use of the resources available in healthcare, especially in environments with limited resources. [ABSTRACT FROM AUTHOR] |
