Paper Title
Deep Learning System to Diagnose Plumonary Tuberclosis Using Chest X-Ray

Tuberculosis is a deadly infectious disease that has affected numerous countries in the world. The existing processes of diagnosis like blood tests or sputum tests are inadequate. Due to the lack of proper technology in place, the early detection of this disease is unattainable. The existing methods to detect Tuberculosis are not up to a commendable standard due to their dependency on unnecessaryfeatures. This makes such technology obsolete and challenging for Physicians to diagnose accurately. There is a huge need to findnew prompt methods for TB detection. Deep learning is one of the most important and advanced methodused widely in diagnosing and evaluating medical images in today’s world. This paper aims to develop a deep learning system that diagnoses tuberculosis based on the important features along with original chest X-rays. This paper uses three deep learning technique based on Image classification, Object detection, and Image segmentation to overcome the false detection and to reduce duration. Also, to find a better performance of the module to diagnose Tuberculosis accurately. The simulation results indicate that this deep learning system can be useful for Prior case finding in high TB-burden regions. In our work, we use the real pulmonary chest X-ray dataset to train our system from a hospital in India. Our approach will help the deep neural network focus its training on tuberculosis-affected regions, making it more robust and accurate than other methods. Keywords - Deep Learning, Chest X-Ray, TB Diagnosis