用多粒度知识检索提升肺部CT报告生成准确性
MonteRET: AI Agent Enhancing Multimodal LLMs with Multi-granularity Knowledge Retrieval for Chest CT Report Generation
- 融合全局与局部解剖特征，实现精准定位与描述
- 在1564例公开数据和82例外部数据上显著提升报告召回率
- 适合医学影像生成、临床辅助诊断场景
自动化肺部CT报告生成仍具挑战，因临床可信报告需兼顾整体体积理解与局部解剖发现的精确描述。本文提出MonteRET，一种区域感知的知识增强框架，用于生成胸部CT病灶描述部分。该框架整合全量CT特征与区域级解剖表示，通过预测的医学状况与区域级视觉-语言对齐检索临床相关知识，并利用知识引导的报告重写代理优化初稿。模型在包含24,128例CT扫描的RadGenome-ChestCT公开队列上训练，在1,564例公开测试集及82例来自纽约长老会/威尔康奈尔医学院的外部队列上评估。相比匹配基线与多个先进方法，MonteRET在报告质量、语义相似性与临床有效性上均有提升，尤其在召回率方面改善显著，表明遗漏发现更少。放射科住院医师的人工评估也更青睐MonteRET。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。