Prediction of Thorax Diseases Using Deep and Transfer Learning

Abstract

A chest X-ray is often among the principal method that the patients experience when their specialists suspect a lung disease. Sometimes, striking insights about the malady in the x-beams go unnoticed by the radiologists or restorative inspectors and just when these x-beams are reexamined, the sicknesses appearances are found, therefore a great deal of time is squandered. This paper includes deep learning and transfer learning procedures connected for modernized forecast of fourteen thoracic infections to be specific Atelectasis, Consolidation, Infiltration, Pneumothorax, Edema, Emphysema, Fibrosis, Effusion, Pneumonia, Pleural thickening, Cardiomegaly, Nodule Mass, Hernia utilizing the data-set given by NIH clinic center. Keywords-Machine Learning, Deep Learning, Transfer learning, Thoracic diseases, Convolutional Neural Networks(CNN), Medical Imaging