MAARTA:Multi-Agentic Adaptive Radiology Teaching Assistant
This addresses a gap in AI-driven radiology education by focusing on perceptual error explanation rather than just diagnostic accuracy, though it is incremental as it builds on multi-agent and gaze analysis methods.
The paper tackles the problem of radiology students' perceptual errors in visual search and diagnosis due to limited expert mentorship by introducing MAARTA, a multi-agent framework that analyzes gaze patterns and reports to provide personalized feedback, helping students understand and improve their errors.
Radiology students often struggle to develop perceptual expertise due to limited expert mentorship time, leading to errors in visual search and diagnostic interpretation. These perceptual errors, such as missed fixations, short dwell times, or misinterpretations, are not adequately addressed by current AI systems, which focus on diagnostic accuracy but fail to explain how and why errors occur. To address this gap, we introduce MAARTA (Multi-Agentic Adaptive Radiology Teaching Assistant), a multi-agent framework that analyzes gaze patterns and radiology reports to provide personalized feedback. Unlike single-agent models, MAARTA dynamically selects agents based on error complexity, enabling adaptive and efficient reasoning. By comparing expert and student gaze behavior through structured graphs, the system identifies missed findings and assigns Perceptual Error Teacher agents to analyze discrepancies. MAARTA then uses step-by-step prompting to help students understand their errors and improve diagnostic reasoning, advancing AI-driven radiology education.