Classification of pneumonia using pre-trained convolutional networks on chest X-Ray images

Abstract

Pneumonia is an infection that is caused to the people of all ages with mild to severe inflammation of the lung disease. The most common and best method for the diagnosis of pneumonia is chest radiography. But diagnosing pneumonia from chest radiographs is a difficult task, even for radiologists. To overcome, Pre-Trained Convolutional Neural Networks namely Inceptionv3 and Resnet50 are used as a feature extractor. The exacted features are fed into 1D CNN which is classifies into Normal, Bacterial Pneumonia and Viral Pneumonia. When comparing Inceptionv3 with 1D CNN and resnet50 with 1D CNN, it is analyzed that Inceptionv3 with 1D CNN gives the satisfactory results of 96.04%.