This research introduces a hybrid intelligence framework for medical imaging quality control that combines AI capabilities with human expertise.

• Establishes a standardized dataset of chest X-rays and CT reports for quality assessment
• Leverages large language models to assist in image quality evaluation
• Creates an adaptive dataset curation system with closed-loop feedback
• Demonstrates how human-AI collaboration can reduce subjectivity in quality control

This approach matters for healthcare by reducing diagnostic errors, improving standardization, and optimizing radiologist workflow while maintaining human oversight in critical diagnostic processes.

Multimodal Human-AI Synergy for Medical Imaging Quality Control: A Hybrid Intelligence Framework with Adaptive Dataset Curation and Closed-Loop Evaluation