An Introductory Guide to Artificial Intelligence in Interventional Radiology: Part 1 Foundational Knowledge

Area of Science:

• Radiology
• Medical Imaging
• Artificial Intelligence

Background:

• Artificial intelligence (AI) is rapidly advancing, with substantial implications for interventional radiology (IR).
• Limited formal training in AI presents a barrier for clinicians, impacting the adoption and trust of AI technologies in clinical settings.
• Familiarity with AI concepts is crucial for interventional radiologists to engage in its development and deployment.

Purpose of the Study:

• To provide interventional radiologists with foundational knowledge of AI.
• To introduce a pragmatic classification system for AI models based on complexity.
• To explore the current applications and implementation patterns of AI in interventional radiology.

Main Methods:

• Review of AI concepts relevant to clinical practice.
• Development of a classification system for AI models.
• Analysis of AI implementation in IR across pre-procedural, intra-procedural, and post-procedural phases.

Main Results:

• Foundational AI knowledge can enhance clinician understanding and participation.
• A complexity-based classification system can guide AI assessment.
• AI is being implemented across all stages of IR procedures.

Conclusions:

• Education in AI fundamentals is key for interventional radiologists.
• A structured approach to AI classification can facilitate its clinical integration.
• AI holds transformative potential for enhancing interventional radiology practice.