Artificial intelligence (AI), including machine learning technologies, has the potential to transform healthcare by deriving new and important insights from the vast amount of data generated during the delivery of health care every day. Radiological applications of AI-based technologies are numerous and expanding. These applications aim to automate and streamline tasks to improve efficiency, accuracy, and consistency. Early applications of AI in radiological imaging include computer aided-detection and diagnosis software (CADe and CADx). CADe and CADx software analyze radiological images to suggest clinically relevant findings and aid diagnostic decisions. Similarly, computer aided triage (CADt) software analyzes images to prioritize the review of images for patients with potentially time sensitive findings.

Large sets of widely available imaging data across imaging modalities have supported the development of AI based algorithms 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 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.

Another area of growth is the use of AI to provide prescriptive guidance for the operator to acquire optimal images. The image quality of ultrasound imaging can be greatly influenced by how the operator uses a handheld probe. Clinical AI applications may assist the acquisition of standardized images independent of the operator, guiding both sonographers and non-experts in sonography, potentially including lay users, to acquire images with equivalent diagnostic quality. The addition of such clinical AI applications and the potential for new users of these devices, similarly affect the benefit risk profiles for these devices and the expectations for the safety and effectiveness of these devices.

Through this workshop, FDA is seeking to engage with stakeholders to explore benefits and risks of these evolving applications of AI in radiology. As the benefit-risk profile changes, it is critical to adapt the methods used to evaluate and characterize their performance. In this workshop, FDA is also seeking innovative and consistent ways to leverage existing methods and to develop new methods for validation of these AI-based algorithms and explore opportunities for stakeholder collaboration in these efforts.

During the workshop, we will be discussing specific topics outlined in the Agenda below.

Date, Time, and Location

Webcast

Transcripts

Agenda

Registration

Requests for Oral Presentations

Submit Comments

Contact

Workshop on Artificial Intelligence

Event Information

Venue

Learn More

About

Organize Events