Artificial intelligence (AI) is helping to automate and streamline work processes in the field of radiology, an early adopter of this emerging technology. With radiology AI applications growing at a brisk clip, there is an urgency to explore benefits and risks of such wide-ranging applications.
It is precisely for this reason that the U.S. Food and Drug Administration (FDA) has scheduled a public workshop aptly titled "Evolving Role of Artificial Intelligence in Radiological Imaging."
You might also like: Multisociety AI Radiology Ethics Framework Announced
In a statement, the FDA said the workshop will enable the agency "to work with interested stakeholders to identify the benefits and risks associated with use of AI in radiological imaging."
In addition, the public workshop – set for 25-26 February 2020 – will provide a venue to discuss best practices for the validation of AI-automated radiological imaging software and image acquisition devices.
Massive volumes/sets of imaging data generated from imaging modalities have supported the development of AI algorithms intended to optimise quality of images or make innovative uses for these devices.
"While historically the information provided by these algorithms has augmented the tasks performed by radiologists, software developments now can enable the devices to perform certain tasks autonomously," the FDA noted. "The potential for independent action by these devices to bypass human clinical review is an important factor in their benefit-risk profile, and it heightens expectations for the safety and effectiveness of these devices."
Validation of AI tool performance with respect to the intended use is critical to assess safety and effectiveness, according to the FDA.
Another area of growth is the use of AI to provide guidance for the operator to acquire optimal images and signals. Clinical AI applications may assist the acquisition of standardised images independent of the operator, guiding both sonographers and non-experts in sonography, potentially including lay users, to acquire images with equivalent diagnostic quality. These trends, the FDA said, also affect the benefit-risk profiles for these devices.
The planned workshop will provide the FDA an avenue to seek innovative and consistent ways to leverage existing methods and to develop new methods for validation of AI-based algorithms and explore opportunities for stakeholder collaboration in these efforts.
This public workshop will be held at the Ruth Kirschstein Auditorium, inside the National Institutes of Health (NIH) Main Campus, Bethesda MD. The general sessions of the workshop will be webcasted and the link will be posted on the FDA website after the workshop.
Those interested to attend must register by 4 pm on 12 February 2020. There is no fee to register for the workshop and registration will be on a first-come, first-served basis. Early registration is recommended because seating is limited.
Source: FDA - Food and Drug Administration
Image credit: iStock