MAARTA:Multi-Agentic Adaptive Radiology Teaching Assistant

TL;DR

MAARTA is a multi-agent system that analyzes radiology students' gaze and report data to provide personalized, adaptive feedback, aiming to improve perceptual expertise and reduce diagnostic errors.

Contribution

This work introduces MAARTA, a novel multi-agent framework that dynamically adapts to error complexity to enhance radiology education through personalized feedback.

Findings

Effectively identifies missed findings in radiology images.

Provides step-by-step explanations to improve student reasoning.

Outperforms baseline models in error detection accuracy.

Abstract

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.