The U.S. National Institutes of Health (NIH) has published a dataset of over 100,000 chest x-ray images and corresponding medical data to enable researchers to train AI systems to better diagnose patients. NIH compiled the anonymized dataset from 30,000 patient volunteers at the NIH Clinical Center, a research hospital in Bethesda, Maryland, many of whom suffer from advanced lung diseases. NIH hopes the data will spur the development of AI diagnostic systems that can confirm radiologists’ findings and spot details in x-rays that radiologists might have missed.
Teaching Computers to Study X-Rays
Joshua New is a policy analyst at the Center for Data Innovation. He has a background in government affairs, policy, and communication. Prior to joining the Center for Data Innovation, Joshua graduated from American University with degrees in C.L.E.G. (Communication, Legal Institutions, Economics, and Government) and Public Communication. His research focuses on methods of promoting innovative and emerging technologies as a means of improving the economy and quality of life. Follow Joshua on Twitter @Josh_A_New.