New Roadmap Outlines AI Research Priorities for Medical Imaging

A second report on translational research in AI focusing on real-world AI problems will be published in the Journal of the American College of Radiology (JACR) in early summer.

Both the reports are the outcome of a workshop convened last August by the National Institute of Biomedical Imaging and Bioengineering at the NIH to explore the future of AI in medical imaging. The workshop brought together government, industry, academia and radiology specialty societies to create a roadmap that sets a path forward for both foundational research in AI and the translational research necessary to deliver AI to clinical practice. The workshop organizers hope to carry on with their work together to continue identifying knowledge gaps and prioritize research needs to promote AI development for medical imaging.

“We all appreciate NIBIB hosting this important event. The workshop was a great opportunity for the radiology community to come together to discuss the needs and challenges for AI research facing our specialty and develop a roadmap for future research in medical imaging,” said Bibb Allen, MD, workshop co-chair and chief medical officer of the ACR Data Science Institute. “We look forward to publishing the roadmap for translational research, including approaches for solving some of these real-world AI problems.”

“This collaborative workshop between the NIH and major radiology organizations was instrumental in bringing together the key stakeholders to define the compelling opportunities for AI research in medical imaging,” said Curtis P. Langlotz, MD, PhD, workshop co-chair, professor of radiology and biomedical informatics, director of the Center for Artificial Intelligence in Medicine and Imaging at Stanford University, and RSNA board liaison for information technology and the annual meeting. “The published outcomes from the event help set the stage for our colleagues and other constituencies working to bring these innovations to patients.”

“The workshop expanded our collective knowledge about the potential utility for Artificial Intelligence to improve the efficiency and accuracy of diagnostic systems,” said Steven E. Seltzer, MD, FACR, health and science policy fellow of the Academy of Radiology and Biomedical Imaging Research “If the need for precision diagnosis in the future requires collation of images from Radiology, Pathology and ‘Omics’ systems into a Diagnostic “Cockpit”, the human observer will need considerable help from computers to extract optimum information from multiple, disparate sources. AI can be a key ingredient in this process.”