指南与共识技术与安全CT

基于大语言模型的个性化CT协议推荐:实现全自动CT扫描工作流

Personalized CT Protocol Recommendation via Large Language Model: Enabling Fully Automated CT Scanning Workflows.
指南 / 共识 · J Imaging Inform Med · 2025-10-16

研究开发了基于大语言模型检索增强生成(LLM-RAG)的框架,从历史检查记录构建协议知识库,用于个性化CT协议推荐。系统最低精确率88.60%、召回率89.34%、F1值88.08%、准确率96.09%,Qwen与DeepSeek同规模任务表现相当(32B最大差异1.41%),模型增大准确率提升(DeepSeek 7B至32B提高1.55%),GPU内存随模型线性增长(7B为25 GB至32B为95 GB)。

要点

  • LLM-RAG框架最低精确率88.60%、召回率89.34%、F1值88.08%、准确率96.09%。
  • Qwen与DeepSeek同规模任务表现相当,32B最大差异1.41%。
  • 模型增大准确率提升,DeepSeek 7B至32B提高1.55%。

核心结论

  • LLM-RAG框架无需模型再训练即可达到临床可行的准确率,有助于简化扫描操作并加速影像工作流自动化。

研究设计与样本

  • 研究开发LLM-RAG框架,从历史检查记录构建协议知识库,进行个性化CT协议推荐;错误分析纳入225例不一致病例。

诊断标准与关键数值

  • 系统最低精确率88.60%、召回率89.34%、F1值88.08%、准确率96.09%。
  • Qwen与DeepSeek同规模任务表现相当,32B最大差异1.41%。
  • 模型增大准确率提升,DeepSeek 7B至32B提高1.55%。
  • GPU内存随模型线性增长,7B为25 GB至32B为95 GB。

局限性

  • 原文未报告局限性

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

Manual CT protocol selection persists as a time-intensive and error-prone bottleneck in radiology workflows, impeding the realization of fully automated scanning pipelines. To overcome this limitation, we developed a Large Language Model Retrieval-Augmented Generation (LLM-RAG) framework for personalized CT protocol recommendation. This system constructs a protocol knowledge base from historical examination records to deliver institutionally tailored, precision recommendations aligned with clinical preferences. Our system demonstrated compelling performance (min: 88.60% precision, 89.34% recall, 88.08% F1, 96.09% accuracy), with key findings revealing: (1) task-specific parity between Qwen and DeepSeek models at equivalent scales (max Δ = 1.41% at 32B); (2) positive scaling laws where larger models boost accuracy (e.g., DeepSeek 7B → 32B: + 1.55%); and (3) linear GPU memory-cost scaling (7B:25 GB → 32B:95 GB), defining clinical deployment constraints. Error analysis of 225 discordant cases identified three primary patterns: over-recommendation (52.44%), unsuitable recommendation (27.56%), and clinically equivalent choices (20%). Critically, the framework achieves clinically viable accuracy without model retraining requirements-a pivotal advantage enabling significant utility in streamlining scanning operations and accelerating imaging workflow automation.

来源:J Imaging Inform Med,查看原文。版权归原作者所有。

引用

  1. Meng X, Wu Y, Dou X, et al. Personalized CT Protocol Recommendation via Large Language Model: Enabling Fully Automated CT Scanning Workflows. J Imaging Inform Med. 2025. PMID: 41102426. doi:10.1007/s10278-025-01720-2

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。