文献速递乳腺技术与安全乳腺X线

在隐私约束下使用本地部署的大语言模型实现符合BI-RADS的结构化乳腺X线摄影报告

BI-RADS-compliant structured mammography reporting using locally deployed large language models under privacy constraints.
PubMed 文献 · Eur Radiol · 2025-11-19

该多中心研究收集3家机构7161份自由文本乳腺X线摄影报告,用商业Qwen-Max模型生成的伪标签对开源Llama-3模型进行低秩适配监督微调,输出符合BI-RADS的嵌套JSON结构化数据。微调模型在第10轮达到精确率0.942、召回率0.929、F1分数0.932,JSON格式准确率0.964、字段完整性准确率1.000,显著优于基座模型,但略低于Qwen-Max,尤其在「特殊征象」类别(F1=0.737 vs 0.947)。作者认为该方法可在本地部署,在隐私保护与结构化报告之间取得平衡。

要点

  • 微调Llama-3模型将乳腺X线摄影自由文本报告转为BI-RADS结构化JSON,F1分数0.932。
  • 字段完整性准确率1.000,JSON格式准确率0.964,结构输出完整可靠。
  • 「特殊征象」类别F1为0.737,低于Qwen-Max的0.947,为相对薄弱环节。

核心结论

  • 本地微调的开源大语言模型可有效将乳腺X线摄影报告转换为结构化数据,虽较商业模型有轻微性能损失,但提升了隐私保护并支持本地部署;作者认为其准确性、临床相关性和合规性使其成为医疗机构的实用方案。

研究设计与样本

  • 多中心研究,回顾性收集3家机构共7161份非结构化乳腺X线摄影报告,使用商业Qwen-Max模型生成的伪标签对开源Llama-3模型进行低秩适配监督微调,输出遵循BI-RADS导向的嵌套JSON模式,在23个特征上以精确率、召回率和F1分数评估性能。

诊断标准与关键数值

  • 微调模型第10轮精确率0.942、召回率0.929、F1分数0.932,JSON格式准确率0.964,字段完整性准确率1.000,显著优于基座模型(p < 0.05,Cohen's d > 0.8)。

局限性

  • 所有标签均为商业Qwen-Max模型生成的伪标签,而非人工标注。
  • 微调模型整体略低于Qwen-Max,差异有统计学意义(p < 0.05;0.5 < Cohen's d < 0.8)。
  • 「特殊征象」类别F1为0.737,低于Qwen-Max的0.947。
  • 作者结论称存在轻微性能折衷(slight performance trade-off)。

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

OBJECTIVE: To develop a privacy-preserving method for structuring free-text mammography reports using a locally fine-tuned, open-source large language model (LLM).

MATERIALS AND METHODS: In this multicenter study, 7161 unstructured mammography reports were collected from three institutions. The open-source Llama-3 model was fine-tuned via supervised learning using pseudo-labels from the commercial Qwen-Max model with low-rank adaptation. All labels were pseudo-labels generated by the commercial Qwen-Max model rather than human annotations. Structured outputs followed a BI-RADS-oriented nested JSON schema. Performance was evaluated across 23 features using Precision, Recall, and F1-score. Structural integrity was assessed using the JSON format accuracy (JFA) and field integrity accuracy (FIA) metrics. Statistical comparisons were performed using the paired Wilcoxon signed-rank test and Cohen's d effect size.

RESULTS: A total of 7161 reports were retrospectively obtained from three institutions and analyzed. The fine-tuned model achieved strong performance at epoch 10 (Precision 0.942, Recall 0.929, F1-score 0.932), with JFA and FIA reaching 0.964 and 1.000, respectively, showing significant gains over the base model (p < 0.05, Cohen's d > 0.8). While slightly below Qwen-Max overall, the model exhibited moderate yet statistically significant differences (p < 0.05; 0.5 < Cohen's d < 0.8), particularly in the "special signs" category (F1 = 0.737 vs 0.947).

CONCLUSION: This method effectively converts mammography reports into structured data using a locally fine-tuned, open-source LLM. Although there is a slight performance trade-off, it improves privacy and can be deployed locally. Its accuracy, clinical relevance, and compliance make it a practical solution for medical institutions.

KEY POINTS: Question Free-text mammography reports lack standardization, making structured extraction difficult, while existing solutions often compromise privacy, adaptability, or require costly commercial tools. Findings Our fine-tuned LLaMA-3 model achieved high extraction accuracy (F1-score: 0.932) and complete structural integrity (FIA: 1.000) within a fully local deployment pipeline. Clinical relevance This method enables standardized and privacy-preserving mammography reporting without disruption to the clinical workflow, supporting safer AI integration, enhanced data quality, and compliance with regulations such as the General Data Protection Regulation (GDPR).

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Sheng W, Wang Y, Xiao L, et al. BI-RADS-compliant structured mammography reporting using locally deployed large language models under privacy constraints. Eur Radiol. 2025. PMID: 41258455. doi:10.1007/s00330-025-12147-2

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。