SIR 2024
General IR
Ekramul Gofur, MD (he/him/his)
Radiology Resident
Westchester Medical Center
Financial relationships: Full list of relationships is listed on the CME information page.
Shane Lee, MD
Interventional Radiology Attending
Temple University Health System
Disclosure information not submitted.
Emily Cuthbertson, MD
Clinical Associate Professor, Interventional Radiology
Temple University Hospital
Disclosure information not submitted.
Gary Cohen, MD
Chair, Department of Radiology
Temple University Hospital
Disclosure information not submitted.
Joseph Panaro, MD
Clinical Associate Professor, Interventional Radiology
Temple University Hospital
Disclosure information not submitted.
Perry Gerard, MD, FACR, MBA
Professor of Radiology
New York Medical College- Westchester Medical Center
Disclosure information not submitted.
Jared Meshekow, MD MPH
Clinical Assistant Professor, Vascular and Interventional Radiology
Temple University Hospital
Disclosure information not submitted.
Interventional radiology (IR) plays a key role in diagnosing and treating a wide range of medical conditions with minimally invasive alternatives to surgery. The use of artificial intelligence is beginning to transform the field of IR through improvements in procedural efficiency, patient outcomes, and safety. In this abstract, we discuss the methods and outcomes associated with AI orchestration in interventional radiology.
Clinical Findings/Procedure Details:
AI-Enhanced Image Guidance: AI-driven image analysis and real-time guidance have been integrated into IR procedures. In addition to reducing procedure time and radiation exposure, these technologies assist with precise needle placement, catheter navigation, and tumor localization. AI can also help approximate the region of treatment in oncology cases with treatment zone and dose mapping in real-time. This can help augment decision-making in terms of further treatment before the end of the procedure.
Predictive Modeling in IR: AI algorithms can predict patient outcomes and procedural success rates based on clinical data. For example, predictive models have been used to anticipate complications during vascular interventions, enabling early intervention and improved patient safety.
Automated Lesion Detection: AI-based software detects and characterizes lesions via medical images, such as CT scans and MRIs. This aids in early disease detection, staging, and treatment planning, particularly in cancer management.
Enhanced Workflow Efficiency: AI solutions optimize IR workflow by automating administrative tasks, such as scheduling, documentation, and reporting. This allows radiologists to focus on clinical decision-making and patient care. AI can also compile appropriate test results and other pertinent clinical data when a consult comes in. This improves turnaround time for consults in a more streamlined fashion.
Conclusion and/or Teaching Points:
AI orchestration in interventional radiology holds immense promise for streamlining procedures and enhancing patient care. However, successful integration requires radiologists to be well-versed in AI technologies and clinical applications.