Podcast Summary
Becker’s Healthcare Podcast
Episode: AI at the Heart of Radiology Informatics Innovation
Release Date: December 3, 2025
Host: Lucas Voss, Becker’s Healthcare
Guests:
- Dr. Paul Yee, Associate Professor of Radiology and Chief of the Intelligent Imaging Informatics Section at St. Jude Children's Research Hospital
- Dr. Sanjay Gandhi, Chief Medical Officer for Philips Enterprise Informatics
1. Episode Overview
This episode investigates how artificial intelligence (AI) is transforming radiology informatics, improving patient care, and reshaping the working environment for clinicians. Dr. Paul Yee and Dr. Sanjay Gandhi discuss the challenges in radiology, real-world applications of AI, risks and mitigations, and their vision for the future of AI in healthcare.
2. Key Discussion Points and Insights
Guest Introductions
- Dr. Paul Yee works at the intersection of clinical care, imaging, informatics, and AI research, focusing on creating an AI-driven radiology ecosystem to improve diagnostic accuracy, reduce clinical burden, and accelerate care, especially for pediatric cancer patients.
- "Our mission is to build an AI driven radiology ecosystem that improves diagnostic accuracy, reduces clinical burden and accelerates how quickly we can get answers for children with cancer." (01:18–01:32)
- Dr. Sanjay Gandhi is an interventional cardiologist and plays a key role in integrating technology and data at Philips to enhance care delivery across large systems.
Challenges in Radiology and the Role of AI
Staffing Shortages, Increased Demand, and Quality Maintenance
- Even in St. Jude's unique environment—where patient numbers are capped, and care is highly specialized—radiology faces the same nationwide challenges of staffing shortages, growing imaging demand, and the pressure to maintain exceptional quality (03:03–04:08).
- AI is being used to:
- Improve efficiency and safety (e.g., AI-driven image reconstruction cuts PET/CT scan times from 15–20 minutes to about 5 minutes, benefiting both children and radiologists).
- Enhance diagnostic workflows and eventually enable more precise tumor measurements.
- “What we're using right now is AI driven image reconstruction. That's allowed us to cut certain scan times dramatically...we're actually get better image quality related to the AI and then overall smoother experience for families.” – Dr. Yee (04:25–05:29)
The Vision: AI in Tumor Boards
- Dr. Yee envisions a future with “AI agent” councils mimicking multidisciplinary Tumor Boards, where specialized AI agents for each discipline collaborate asynchronously to provide advanced diagnostic and care recommendations.
- "What I envision is...a council of so-called AI agents where each agent specializes in a particular field. So you've got an AI agent that's an oncologist, an AI agent that's a radiologist..." – Dr. Yee (06:46–07:27)
- This system could democratize access to expert-level interdisciplinary guidance for all patients, not just those at top-tier centers (07:52–08:22).
Risks and Responsible AI
- Dr. Gandhi: Emphasizes transparency, explainability, and workflow integration as key risks. Philips’ approach centers on “human oversight”—AI should support, not replace, clinicians.
- "We want solutions that are integrated into the workflow of clinicians so they can support them, they can augment them, but not replace them." (09:42–10:19)
- Dr. Yee: Every AI use case warrants a fresh review; St. Jude uses a three-pillar approach: awareness of risks, context-aware measurement, and interdisciplinary governance.
- "Every new AI model or use case really requires a fresh look and frankly, a fresh sense of humility. We don't assume that what worked last time is going to teach us everything we need to know about the next one." (11:01–11:18)
3. Notable Quotes & Memorable Moments
- On workflow transformation:
"AI will move from isolated tools...to deeply integrated systems that can automate workflows, enhance decision making and personalize care." – Dr. Gandhi (14:53–15:24) - On clinician empowerment:
"AI can help clinicians do more than what we could do before...It just gives me more brain space and bandwidth, the focus on the things I enjoy and the things that honestly are going to make a difference in a patient." – Dr. Yee (16:40–17:06) - Collaboration theme:
"The future of AI to be successful needs to be collaborative...if we do it well, we can truly democratize access, we can reduce disparities and truly empower physicians." – Dr. Gandhi (18:41–18:58) "Collaboration is how we turn AI from exciting prototypes into tools that genuinely improve care." – Dr. Yee (19:15–19:30)
4. Timestamps for Important Segments
| Timestamp | Segment/Topic | |-----------|------------------------------------------------------| | 01:14 | Dr. Yee introduces his work and research priorities | | 02:05 | Dr. Gandhi gives background and role at Philips | | 03:03 | Radiology challenges: staffing, demand, quality | | 04:25 | Practical AI benefits at St. Jude (scan times, quality) | | 06:07 | How AI could reshape the Tumor Board | | 08:46 | Risks in adopting AI—transparency, explainability | | 11:01 | Guardrails for safe AI deployment (St. Jude approach)| | 14:39 | The next 3 years for AI in radiology—future vision | | 18:26 | Collaboration, data, and patient-centered design emphasized |
5. Forward-Looking Perspectives
- Dr. Gandhi: Predicts AI will soon fully integrate and automate entire radiology workflows, reducing administrative burden and enabling more proactive, personalized care.
- Excitement centers on “AI’s ability to enable proactive personalized care while keeping clinicians and patients firmly in them.” (15:44–15:50)
- Dr. Yee: Envisions true augmentation—AI as a tool that orchestrates data, automates routine tasks, and allows clinicians to focus on critical thinking and patient interaction.
- He welcomes collaboration for successful implementation: “...Now it's about people, process and collaboration and making it work in this amazing healthcare ecosystem that we're blessed to be a part of.” (19:34–19:37)
6. Final Thoughts
Both experts stress that thriving AI innovation in healthcare requires cross-disciplinary, cross-sector collaboration and humility, not just technical advancement.
For Listeners
This episode provides a nuanced look at both the promise and complexity of AI in radiology, balancing optimism with the need for wise implementation, strong governance, explainability, and teamwork. It’s essential listening for anyone interested in the real-world transformation of medical imaging by artificial intelligence.
