Scholarlink

<p>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 <i>Δ</i> = 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&#xa0;GB → 32B:95&#xa0;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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Personalized CT Protocol Recommendation via Large Language Model: Enabling Fully Automated CT Scanning Workflows

  • 期刊论文

  • 发表日期：

    2025年10月16日

查看全文
  • Xiaolin Meng,
  • Yefen Wu,
  • Xin Dou,
  • Kaiyi Liang,
  • Peng Ji,
  • Yang Wang,
  • Manhua Liu

摘要

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.