Object classification to analyze medical imaging data using deep learning

Over 300 million diagnostic radiology images are taken every year in the United States ^[1]. The pressure on healthcare providers will increase considerably to operate more efficiently and accurately with growing demand for diagnostic services. The National Institute of Medicine estimates that 12 million Americans are misdiagnosed every year ^[2]. More accurate and efficient decision support tools for doctors could greatly reduce that number. Deep learning is a technology inspired by the workings of the human brain. Networks of artificial neurons analyze large datasets to automatically discover underlying patterns, without human intervention. Deep learning excels at identifying patterns in unstructured data, which most people know as media such as medical images, sound, video, and text. This paper talks about using deep learning networks to analyze medical imaging data such as X-rays and Magnetic Resonance Imaging (MRI) to increase diagnostic accuracy in less time and at reduced cost compared to traditional diagnostic methods.