MonteRET: AI Agent Enhancing Multimodal LLMs with Multi-granularity Knowledge Retrieval for Chest CT Report Generation
For radiologists and clinicians, MonteRET addresses the challenge of generating clinically faithful chest CT reports by reducing omitted findings, as shown by improved recall and human expert preference.
MonteRET is a region-aware retrieval-enhanced framework for chest CT report generation that integrates global and region-level features with knowledge retrieval and a rewriting agent. On 24,128 training scans and evaluation on 1,564 public and 82 external scans, it improved report quality, semantic similarity, and clinical efficacy over baselines, with gains most pronounced in recall.
Automated chest CT report generation remains challenging because clinically faithful reporting requires both whole-volume understanding and accurate description of localized anatomical findings. Here we developed and retrospectively evaluated MonteRET, a region-aware retrieval-enhanced framework for generating chest CT findings sections. MonteRET integrates global CT features with region-level anatomical representations, retrieves clinically relevant knowledge using predicted medical conditions and region-level vision-language alignment, and refines initial reports through a knowledge-guided report rewriting agent. We trained our model on a public cohort with 24,128 CT scans from RadGenome-ChestCT. We evaluated MonteRET on the public RadGenome-ChestCT test set of 1,564 CT scans and an external cohort of 82 CT scans from NewYork-Presbyterian/Weill Cornell Medical Center. MonteRET improved report quality, semantic similarity, and clinical efficacy compared with a matched baseline and several state-of-the-art methods. Gains were most pronounced for recall, suggesting fewer omitted findings. Human expert evaluation by radiology residents also favored MonteRET.