基于BI-RADS提示的大语言模型自动质控乳腺超声报告的多中心初步研究
本研究回顾性收集中国60家医院735例乳腺肿块型病变的超声报告,以多级专家审核结果为金标准。比较Qwen2.5-VL-7B大语言模型与质控人员对自由文本报告的结构化转换结果,发现模型在边缘、回声模式等关键征象的质控准确率显著更高。模型处理50份报告平均仅需13分钟,明显快于人工的212.5分钟。
要点
- 大语言模型对乳腺超声报告边缘和回声模式的质控准确率显著高于人工质控人员。
- 模型质控准确率与BI-RADS分类呈正相关,高风险报告表现更可靠。
- 模型质控效率远高于人工,50份报告仅需13分钟。
核心结论
- 基于BI-RADS提示的Qwen2.5-VL-7B大语言模型对乳腺超声报告质控准确、可靠且高效,尤其对高怀疑级别报告表现更好。
研究设计与样本
- 回顾性多中心研究,纳入中国60家医院735例经病理证实的乳腺肿块型病变超声报告。
- 每家医院质控人员将自由文本报告转换为标准化结构化输出,由多级专家审核建立金标准。
- 将Qwen2.5-VL-7B大语言模型应用于同一批自由文本报告,基于BI-RADS提示生成结构化报告。
- 比较模型与质控人员的准确率及输出耗时以分析效率。
关键影像表现/征象
- 大语言模型对乳腺病灶边缘的质控准确率为80.0%,高于人工质控的64.1%。
- 大语言模型对回声模式的质控准确率为74.0%,高于人工质控的56.1%。
- 在多发病灶的复杂报告中,模型对边缘质控的准确率仍保持优势,为79.8%对64.4%。
诊断标准与关键数值
- 模型完成50份报告质控平均耗时13分钟,人工平均耗时212.5分钟。
临床应用与阅片要点
- 大语言模型可辅助对乳腺超声自由文本报告进行结构化转换和征象质控,减少人工转写错误。
- 对边缘和回声模式等关键BI-RADS征象的自动核查,有助于提升报告的规范性和一致性。
局限性
- 研究为回顾性设计,且仅纳入经病理证实的肿块型病变报告。
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 evaluate the feasibility of using large language model (LLM) for automated quality control (QC) of breast ultrasound (US) reports.
METHODS: In this retrospective multicenter study, we collected breast US reports from 735 patients who had pathological confirmation of mass-type lesions on breast US across 60 hospitals in China. Each hospital's QC personnel converted free-text reports into standardized structured outputs. A gold standard was established through a multilevel expert review. The Qwen2.5-VL-7B LLM was applied to the same free-text reports, generating structured reports based on BI-RADS prompts. Accuracy was compared both between the LLM and QC personnel as well as the times required to produce the outputs for analysis of efficiency.
RESULTS: The LLM demonstrated higher accuracy in conducting QC for key breast lesion US features, such as margin (80.0% versus 64.1%, P < .0001) and echo pattern (74.0% versus 56.1%, P < .0001). Subgroup analysis further confirmed its robustness: in the complex reports of multiple lesions, it maintained its advantage in margin QC (79.8% versus 64.4%). The study also revealed a significant positive correlation between the LLM's QC accuracy and BI-RADS categories (from 3 to 5) (Spearman ρ = 0.264, P = .028), a trend not observed in manual QC. In terms of efficiency, the LLM completed QC for 50 reports in an average of only 13 min, faster than 212.5 min required by manual reviewers.
CONCLUSIONS: The proposed LLM-based system provides a reliable, accurate, and efficient solution for breast US reports. It achieves human-comparable performance with markedly higher efficiency, particularly in reports with high suspicion levels, offering a reliable tool to enhance report quality.
引用
- Lu, Wang, Wang, et al. Automated Quality Control of Breast Ultrasound Reports Using a BI-RADS-Prompted Large Language Model: A Pilot Multicenter Study Involving 60 Hospitals in China. J Am Coll Radiol. 2026. PMID: 42486359. doi:10.1016/j.jacr.2026.07.009
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。