AI fundamentals for imaging and healthcare

AI fundamentals for imaging and healthcare is organized by The Royal College of Radiologists (RCR) and will be held on Sep 15, 2026.

Event Description:
Build your foundation for confident, safe use of AI in clinical practice

We've updated the course pricing to make this event more accessible, while maintaining the same high-quality, expert-led learning experience. Secure your place at the reduced rate while spaces remain.

AI is embedded in imaging and wider healthcare workflows. From automated image analysis to supporting complex diagnostic decisions, hospitals are already deploying AI tools that directly influence your workflow. Foundational AI knowledge is no longer optional – it’s essential. Our AI Fundamentals in Imaging and Healthcare course equips you with the practical understanding to navigate this fast-moving landscape: how AI works, where it's delivering impact, the risks, limitations and biases you need to look out for. 

• AI is here now: know what’s behind the AI tools you encounter everyday.  
• Protect patient safety: learn how to spot model issues and bias before they impact patient care. 
• Lead the conversation: gain confidence to discuss AI trends, applications and governance with colleagues and stakeholders. 

What you’ll Gain:
By the end of our course, you’ll possess the foundational knowledge to immediately and confidently engage with AI tools in your daily work. 

• Risk management: understand the core steps in AI model creation, with emphasis on data gathering, annotation, and security, ensuring you know the origin and limitations of the tools you use. 
• Bias awareness: recognise challenges of open-source datasets, the concept of "grand challenges," and evaluate how bias and unintended outcomes can compromise AI models and patient safety. 
• Practical application: explain the fundamental principles of AI and compare various techniques, justifying their use (or non-use) for specific radiology and healthcare applications.

Learn AI confidently with visual tools and continuous assessment
The course contextualises AI concepts using diagrams and other visual aids to bring complex concepts to life. Formative assessments are embedded throughout to reinforce understanding and help you track your progress. 

A complete learning experience: flexible, practical and expert-led

The programme blends self-paced e-learning with an expert led live online learning day for maximum impact.

Starting with two interactive e-learning modules (2-3 hours each), designed to simplify difficult concepts through visual aids, and offering optional formative assessment to test your understanding, you'll then join a focused live learning day led by experts, where you'll move seamlessly from foundational principles to real-world appraisal, engage in peer discussions, and leave with actionable steps you can apply in your own setting.

Learning Outcomes:

1. Describe the fundamental principles of AI?and how these technologies are applied in healthcare settings 
2. Identify and compare various AI techniques, outlining their advantages and disadvantages, and justify the use of these methods?for specific applications 
3. Describe the core steps involved in AI model creation, including data gathering, annotation, and the significance of data management and security 
4. Recognise the challenges associated with open-source datasets, the concept of AI grand challenges, and evaluate how bias and unintended outcomes can potentially influence AI models. 

e-learning Objectives:

• Explain key AI terminology (machine learning, deep learning and neural networks) and apply these concepts to interpret how different AI approaches are used in radiology.
• Compare and differentiate the main forms of learning in AI and justify which approach is most appropriate for specific radiology use cases.
• Analyse the role of "ground truth" in AI model development and justify how the bias-variance trade-off influences model performance and clinical applicability in radiology.
• Analyse the structure and function of neural networks and evaluate how their characteristics influence AI performance and clinical applicability in radiology.
• Critically appraise the current state of AI in radiology and evaluate its potential future applications within your subspecialty, identifying at least two opportunities and two limitations that could impact clinical practice.