MAARTA:Multi-Agentic Adaptive Radiology Teaching Assistant

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Awasthi, Akash, Chang, Brandon V., Vu, Anh M., Le, Ngan, Agrawal, Rishi, Deng, Zhigang, Wu, Carol, Van Nguyen, Hien
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911016331247616
author Awasthi, Akash
Chang, Brandon V.
Vu, Anh M.
Le, Ngan
Agrawal, Rishi
Deng, Zhigang
Wu, Carol
Van Nguyen, Hien
author_facet Awasthi, Akash
Chang, Brandon V.
Vu, Anh M.
Le, Ngan
Agrawal, Rishi
Deng, Zhigang
Wu, Carol
Van Nguyen, Hien
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17320
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MAARTA:Multi-Agentic Adaptive Radiology Teaching Assistant
Awasthi, Akash
Chang, Brandon V.
Vu, Anh M.
Le, Ngan
Agrawal, Rishi
Deng, Zhigang
Wu, Carol
Van Nguyen, Hien
Computers and Society
Computer Vision and Pattern Recognition
Machine Learning
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.
title MAARTA:Multi-Agentic Adaptive Radiology Teaching Assistant
topic Computers and Society
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2506.17320