Classification of chest pneumonia from x-ray images using new architecture based on ResNet

Abstract

Pneumonia is a potentially fatal bacterial or viral lung infection. The detection of pneumonia anomalies in the early lungs, can save the life of a child or an old lady, especially, in the early moments;These divergences have a very minimal size.In this paper we propose a new architecture based on ResNet 50, we project the adjusted Resnet50 model, based on medical images of the chest to bring out the infected examples with pneumonia. The result predicted are very interesting (97, 65 %) by comparing them with several prior scientific researches and radiologists hope.