Radiology AI Reality Check: Automated Reports, Implementation Failures and Agentic Future
In this episode of Frame by Frame: Rethink Imaging, host Chris St John sits down with Dr. Woojin Kim, Chief Strategy Officer at HOPPR and Chief Medical Officer at the ACR Data Science Institute, to explore the evolving role of generative AI in radiology. From automated reporting to intelligent assistants, Dr. Kim offers a pragmatic look at how AI can streamline workflows without replacing human expertise.
Whether you're a radiologist, technologist, or healthcare innovator, this episode delivers a practical roadmap for integrating AI while maintaining patient-centered care.
In this episode of Frame by Frame: Rethink Imaging, host Chris St John welcomes Dr. Woojin Kim, an expert at the intersection of radiology and AI innovation, to discuss the future of generative AI in medical imaging. As Chief Strategy Officer at HOPPR and Chief Medical Officer at the ACR Data Science Institute, Dr. Kim draws from deep experience in both clinical practice and healthcare entrepreneurship.
Together, they explore the growing capabilities of AI in radiology, from automated draft reporting for chest X-rays and CT scans to the emerging potential of Agentic AI as a true assistant within clinical workflows. Dr. Kim emphasizes that while AI holds the promise of boosting efficiency, with some studies reporting 15.5% gains, it must be grounded in personalization and supported by human oversight to avoid risks like hallucinated results.
The conversation dives into practical mechanisms for safe integration, including Model Context Protocols (MCPs) that embed clinical nuance into AI outputs, and the need for hands-on experience over purely theoretical exposure. Dr. Kim also addresses the regulatory and liability gaps that could hinder responsible adoption, advocating for frameworks that can keep pace with innovation.
For professionals navigating the AI landscape in healthcare, this discussion offers a forward-looking yet grounded perspective on building meaningful human-AI partnerships, where technology enhances rather than replaces clinical judgment.
If you enjoyed this episode, don’t forget to subscribe and leave a review. It helps us reach more imaging professionals and healthcare leaders around the world.
What You'll Learn:
- How automated draft reporting for chest X-rays and CT scans is becoming a reality, with early studies showing 15.5% efficiency gains
- Why personalization in AI-generated radiology reports is crucial for widespread adoption and clinical effectiveness
- The critical importance of preventing AI hallucinations in medical reporting through human-in-the-loop workflows
- How Model Context Protocols (MCPs) are enabling more sophisticated AI integration in radiology workflows
- Why Agentic AI could transform radiology by functioning as an intelligent assistant rather than a replacement
- How to balance AI implementation with clinical expertise while maintaining focus on patient care and safety
- The importance of hands-on experience with AI tools rather than just theoretical knowledge
- Why regulatory and liability frameworks need to catch up with AI advancement in medical imaging
Chapters:
00:00 Intro: Meet Dr. Woojin Kim, Pioneer in Medical AI
00:07:25 The Reality of AI-Generated Radiology Reports
00:14:27 Why Personalization Matters in AI Reports
00:21:12 Managing AI Hallucination Risks in Medical Imaging
00:27:47 Current Barriers to GenAI Implementation
00:30:31 Understanding Agentic AI in Radiology
00:36:27 Model Context Protocols: The Future of Integration
00:43:48 Key Takeaways: Learning to Work With AI in Healthcare