Analysis and Design of Artificial Intelligence System for the Prediction of Pulmonary Diseases

Abstract: Report generated by radiologists using chest X-rays has significant potential to improve clinical patient care. Diagnosing chest X-rays can be challenging and sometimes more difficult than diagnosis via chest CT imaging. Lack of availability of well- trained radiologists and delayed report generation results in long waiting time which indeed leads to delayed medical assistance. As the interpretation of chest X-rays is time consuming, we propose a system that assist the medical professionals in doing the same job within minimum time. In this work, the proposed system can detect heart and pulmonary diseases such as pneumonia and enlargement of heart from chest radiographs at a level equal to the knowledge and skill set of practicing radiologist. The system employs artificial intelligence techniques. Using such techniques improves a patient's overall treatment with less hospital time and can also be used to deliver high-quality and cost-effective care. Its focus is to produce accurate disease profiles to power downstream tasks such as diagnosis and care providing.

Keywords: Machine Learning, Deep Learning, Recurrent Neural Network, Image augmentation, Reinforcement Learning.