Forecasting the lung diseases from Radiography scans with hybrid Transfer Learning Techniques

Lung related issues are rapidly increasing day by day as it is very important to identify the disease and get treated earliest possible as lungs are part of very complex system, expanding and relaxing thousands of times each day allow us to breathe by bringing oxygen into our bodies and sending carbon dioxide out. Lung related issues are directly preoperational to breathing problems. X-rays are one of the important ways of identifying the status of lungs. As there are many communicable diseases like Covid-19, the person should be identified early and should be treated to control the spread of virus. Lung Opacity is one of the major problem faced by many people and also a very serious problem if not treated early it will spread entire lungs and which leads to cancer similarly Pneumonia is another disease which is an infection to one's lungs caused by spread of virus. All these diseases directly affect Respiratory system of human. The paper aims to lung diseases classification among Pneumonia, Lung opacity, Normal and Covid-19 using the proposed hybrid model. The Deep Transfer Learning model helps to extract good features which helps for better learning and greater results. The Ensembled model of Deep Transfer Learning is used in this paper, which is a combination of VGG, EfficientNet and DenseNet. Considering the output of image augmentation as input for Ensembled model and classification of lung disease. The accuracy of the proposed hybrid model is very much accurate when compared to individual base models.