In August of 2018, the National Institutes of Health (NIH), the Radiological Society of North America (RSNA), and The Academy for Radiology and Biomedical Imaging Research participated in a two-day discussion of the steps necessary to advance the use of AI in medical imaging.
A new report published in the Journal of the American College of Radiology describes the top priorities the groups identified for bringing AI into the mainstream of everyday care, including potential uses in imaging.
For starters, the group noted the need to recognize the challenges that are unique to bringing AI into clinical situations.
“Understanding the nature of these new challenges, potential mitigation strategies, and a well-conceived research road map that ensure that advances in AI algorithm development are efficiently translated to clinical practice are of paramount importance.”
One problem the group identified is that, to date, use cases for AI in medical imaging have lacked standard inputs and outputs among comparable algorithms.
Another problem needing correction is the lack of established data sharing methods to ensure the existence of quality datasets containing the appropriate annotations or rich metadata necessary to develop high-performing AI algorithms.
“Accelerating the release of publicly available data sets and AI techniques such as transfer learning that allow patient data to remain behind an institution’s firewall while exposing algorithm training to more diverse data may be able to help accelerate translation of AI into clinical practice,” the report said.
Similarly, the report pointed to a lack of user interfaces for bringing the results of AI algorithms into clinical workflows, which limits the deployment of AI models for widespread clinical use. IT developers will need to create an efficient user interface and user experience to integrate with existing clinical workflow tools to accelerate AI use.
“Understanding the infrastructure needs, including both qualitative and quantitative analyses for AI deployment in clinical practice—either local or cloud-based—will be critical in allowing use of thousands of AI algorithms in actual clinical practice,” the report said. “The medical imaging community must be involved in assessing the clinical and infrastructure needs and work with existing standards bodies such as the National Science Foundation and the NIH Connected Health Initiative to find solutions that facilitate adoption of AI in clinical practice.”
Finally, medical stakeholders must ensure that the technology is safe and accurate by working with IT developers, government agencies, and the public to make sure AI algorithms are accurate, free of bias, and safe for patients. To do this, stakeholders will need to validate AI algorithms using datasets that contain demographic and technical diversity. Federal agencies such as the FDA have played a critical role in validating AI models to ensure patient safety.”
“The FDA regulates a broad array of medical imaging devices as well as computer-aided diagnosis software and other algorithms that provide decision-making support to medical practitioners,” the report said. “The agency recognizes the rapid increase in digitization across the health care continuum and the importance of regulating computer software that is able to detect and classify disease processes and has been issuing regulatory guidance for software computer-aided detection and computer-aided diagnosis since 2012.”
Clinicians in the medical imaging field, the report concluded, will be crucial to moving cross-industry partnerships forward.