Multiple Lung Diseases Classification from Chest X- Ray Images using Deep Learning approach

Lung diseases are disorders in the lung that affects proper functioning of the breathing system. Chronic Obstructive Pulmonary Disease, lung Cancer, pneumonia, tuberculosis, and pneumothorax are prevalent in most developing countries. Diagnosis of lung diseases is usually performed through visual inspection of chest X- ray images, especially in low resource settings. This procedure is time consuming, tedious, and subjected to inter- and intra-observer variability leading to misdiagnosis. The purpose of this research was to develop a method for automatic classification of multiple lung disease from chest X-ray images using Xception deep learning method. The data required for training, validation and testing the system was collected from Jimma University Medical Center Radiology Department and National Institute of Health (NIH) chest X-ray dataset repository. All the images have been pre- processed prior to training. An accuracy, sensitivity, and specificity of 97.3%, 97.2%, and 99.4%, respectively have been achieved for multi-class classification. The developed system can be used as a decision support system for physicians, especially those in low resource settings where both the expertise and the means is in scarce. The system also allows capturing of images from radiographic films extending its implementation in areas where only the conventional X-ray machines are available.