PneumonXNet - A deep learning model for pneumonia detection

Standard chest X-rays are used to diagnose pneumonia, an infection of the lungs that can be highly contagious due to being caused by viruses and bacteria. Nevertheless, this method is more time-consuming and routine-dependent with a bias in outcome. So to overcome these problem we developed PneumonXNet, a bespoke CNN model for the detection of pneumonia. We evaluated the performance of our method with respect to pre-trained models such as VGG16, EfficientNetB3 and ResNet50 on a X-ray image dataset comprising 5,856 images. The best result we have reached is a test accuracy of 97% with dropout value of 0.4 which is better than the pretrained models. The pre-trained model EfficientNetB3 showed the highest accuracy, which points on possible applications of transfer learning. This research signifies the capabilities of CNN models to streamline and improve detection on pneumonia, which in turn paves way for technological sophistication in health care sectors. The findings of this study carry significant impact on pneumonia detection, emphasizing the importance of deep learning model in pneumonia detection and how it can help in saving a lot of time for doctors and patients from the traditional X rays collecting systems. This can also reduce the overall treatment cost for patients. This research therefore offers new avenues for developing strong techniques for pneumonia identification, which hold promise for improving healthcare technology and patient outcomes in general.