Comparative Analysis of Pneumonia Detection from Chest X-Ray Images Using CNN And Transfer Learning

Abstract

A widespread bacterial or viral infection of the respiratory tract, pneumonia affects many people. particularly in developing and impoverished countries where pollution, unsanitary living conditions, and overcrowding are all too common, as well as a lack of medical infrastructure. Pneumonia produces pleural effusion, which is a condition in which fluids fill the lungs and create breathing problems. Early detection of pneumonia is critical for ensuring a cure and improving survival rates. The most common method for detecting pneumonia is chest X-ray imaging. As opposed to that, examining chest X-rays can be challenging and vulnerable to subjective fluctuation. A computer-aided diagnosis method for automatic pneumonia detection utilizing This research includes the creation of chest Images from X-rays. To evaluate which model is superior, an experiment was conducted utilizing a publicly accessible database on all three models. A Convolutional Neural Network (CNN) model was developed to address the lack of readily available data. together using transfer learning strategies like Mobile Net and VCG. On a dataset of accessible pneumonia X-rays, the method was tested. This research shows which neural network algorithm is optimal for detecting pneumonia, and how medical practitioners might use it in the actual world. Keywords: Pneumonia, Chest X-ray, Deep Learning, Convolutional Neural Network (CNN), Mobile Net, VCG, ReLU, Max pooling.