a new reportwith contributions from the National Institute of Biomedical Imaging and Bioengineering (NIBIB), part of the National Institutes of Health, provides a roadmap for translational research on artificial intelligence (AI) in medical imaging. The report, published May 28, 2019, in the Journal of the American College of Radiology, identifies research priorities that leverage big data, cloud, and machine learning to increase clinicians’ planning and use of images to make diagnoses or evaluate patients’ responses to therapy.
This report and a companion report published last month summarize the findings of an August 2018 workshop co-hosted by the NIH, the Radiologic American College of Radiology (ACR), the Radiological Society of North America (RSNA), and the Academy of Radiology and Biomedical Imaging Research (The Academy). The first report, published on April 16, 2019, charts a path forward for fundamental research in AI and this second report focuses on the translational research needed to bring AI to clinical practice.
“Radiology has transformed the practice of medicine over the past century, and AI has the potential to radically impact radiology in a positive way,” said Krishna Kandarpa, M.D., Ph.D., co-author of the report and director of research sciences and strategic directions at NIBIB. “This roadmap is a timely survey and analysis by experts from federal agencies and from our industry and professional societies that will help us make the most of artificial intelligence technologies in their impact on the field of medical imaging.”
Companion reports, co-authored by government, industry, academic, and radiology society leaders, have identified and prioritized initiatives to accelerate fundamental and translational research in AI for medical imaging.
“This new roadmap document provides guidance for the clinical translation of AI innovation,” said Curtis P. Langlotz, M.D., Ph.D., co-author of the report and RSNA Board of Directors Liaison for Information Technology and Annual Meeting. “Together, these two connected roadmaps show us how AI will not only transform the work of radiologists and other medical imaging specialists, but also improve the delivery of care across the clinical environment.”
The authors suggest that the application of AI can impact the entire radiology process, from the clinical decision to perform diagnostic imaging, to preparing patients for procedures, performing the scan, interpreting imaging results, and finally managing workflow in radiology departments. While most of the focus is on the power of computers to aid in image interpretation, according to the report, research is being done on artificial intelligence applications that address all aspects of the imaging process. The AI tools considered in this roadmap are algorithms for disease detection and classification, image optimization, radiation reduction, and workflow improvement. The authors suggest that radiologists should take the lead in identifying the most important areas for AI development.
The authors identified key priorities:
- Structured AI use cases. In software development, use cases define who will use a system and for what specific purpose. AI use cases should define and highlight the clinical challenges that AI can solve.
- Data exchange. Researchers should establish methods to encourage data sharing to train and test AI algorithms to promote generalization into widespread clinical practice and minimize unwanted biases.
- AI algorithm performance monitoring and validation tools to facilitate regulatory approval.
- Common data elements and standards for seamless integration of AI tools into existing clinical workflows.
“Although advances in fundamental research are occurring rapidly, translation into routine clinical practice has been slower because we must ensure that AI in medical imaging is useful, safe, effective, and easily integrated into existing radiology workflows before they can be used in routine patient care,” said Bibb Allen, MD, co-author of the report and medical director of the ACR Data Science Institute. The report states that an important goal of the resulting roadmap is to grow an ecosystem, facilitated by professional societies, industry and government agencies, that will enable robust collaborations between practicing clinicians and AI researchers to advance fundamental and translational research relevant to medical imaging.
“This NIBIB-sponsored workshop was an important step in coordinating private and government efforts related to the implementation of AI in medical imaging,” said Mitchell Schnall, MD PhD, Eugene P. Pendergrass Professor and Chair of Radiology at the University of Pennsylvania; Vice President and Chair of the DxCP Task Force, Academy of Radiology and Biomedical Imaging Research. “A true public-private partnership will be needed to realize the enormous potential contribution of AI to transform medical imaging, and this roadmap is the first step in that direction.”
###
About the National Institute of Biomedical Imaging and Bioengineering: NIBIB’s mission is to improve health by leading the development and accelerating the application of biomedical technologies. The Institute is committed to integrating the physical and engineering sciences with the biological sciences to advance basic research and healthcare. NIBIB supports research and development of emerging technologies within its internal laboratories and through grants, collaborations and training. More information is available on the NIBIB website: http://www.nibib.nih.gov.
About the National Institutes of Health (NIH): NIH, the nation’s medical research agency, includes 27 institutes and centers and is a component of the U.S. Department of Health and Human Services. NIH is the primary federal agency that conducts and supports basic, clinical, and translational medical research, and is investigating the causes, treatments, and cures of common and rare diseases. For more information about NIH and its programs, visit www.nih.gov.
