Radiology Reimagined: Interoperability and Lessons Learned from the Imaging AI in Practice Demonstration

Area of Science:

• Medical Imaging
• Artificial Intelligence in Healthcare
• Radiology Informatics

Background:

• The Radiology Reimagined demonstration at the RSNA Annual Meeting addresses the integration of artificial intelligence (AI) into clinical radiology.
• It emphasizes the critical role of interoperability and semantic standards in streamlining AI adoption across the entire radiology workflow.
• Since 2020, this event has evolved, showcasing increasingly complex AI applications in medical imaging.

Purpose of the Study:

• To demonstrate the practical integration of AI tools into point-of-care radiology systems.
• To foster collaboration between radiology professionals and industry vendors to promote AI adoption.
• To highlight the importance and application of standards like DICOM, HL7 FHIR, and IHE profiles in AI integration.

Main Methods:

• Presentation of realistic clinical scenarios at the RSNA Annual Meeting.
• Collaboration with over 20 unique industry vendor partners annually.
• Progressive incorporation of new standards, including Integrated Multimedia Reporting and FHIRcast.

Main Results:

• Demonstrated successful integration of AI for tasks ranging from nodule detection to prostate MRI interpretation.
• Showcased the utility and challenges of integrating AI into existing healthcare IT infrastructure.
• Facilitated learning on practical integration strategies and key considerations for AI implementation in radiology.

Conclusions:

• Interoperability and semantic standards are essential for seamless AI integration in radiology.
• The Radiology Reimagined demonstration serves as a vital platform for advancing AI in clinical practice.
• Future efforts will focus on enhancing attendee engagement, quantitative feedback, and adopting emerging standards.