基于大语言模型生成乳腺癌影像结构化报告:GPT-4与DeepSeek的比较分析
该回顾性研究纳入两家机构501例乳腺癌患者的1358份自由文本影像报告(含乳腺X线、超声、MRI和PET/CT),比较GPT-4与DeepSeek生成结构化乳腺癌多模态影像整合报告的表现。两模型在数据提取、整合及TNM分期上均有较高准确率,医师满意度评分显著相关(r=0.665和0.558,P<.001),但病灶检测准确率各有优势。
要点
- GPT-4与DeepSeek生成结构化乳腺癌影像报告的数据提取、整合及TNM分期准确率均高。
- 胸膜病灶检测GPT-4准确率94.9%高于DeepSeek的79.5%,肠系膜转移DeepSeek 87.5%高于GPT-4的43.8%。
- 补充体格检查数据后,N分期准确率可提升至90%以上。
核心结论
- GPT-4和DeepSeek均能有效生成结构化乳腺癌影像报告,在数据挖掘、整合和TNM分期方面准确率高;整合这些模型到临床实践有望提高报告标准化和医师生产力。
研究设计与样本
- 回顾性分析两家机构501例乳腺癌患者的1358份自由文本影像报告,涵盖乳腺X线、超声、MRI和PET/CT,比较GPT-4与DeepSeek生成结构化报告的表现。
关键影像表现/征象
- 两模型医师满意度评分强相关,r值分别为0.665和0.558,P值均低于.001。
- 原发灶特征平均准确率GPT-4为91.7%,DeepSeek为92.1%;特征合成准确率GPT-4为93.4%,DeepSeek为93.9%。
- 转移灶识别总体准确率GPT-4为93.5%,DeepSeek为94.4%。
- 胸膜病灶检测准确率GPT-4为94.9%,DeepSeek为79.5%;肠系膜转移识别准确率DeepSeek为87.5%,GPT-4为43.8%。
诊断标准与关键数值
- T分期准确率超过92%,M分期准确率超过94%,补充体格检查数据后N分期准确率提升至90%以上。
- TNM分期正确性依据NCCN指南评估。
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
RATIONALE AND OBJECTIVES: The purpose of this study is to compare the performance of GPT-4 and DeepSeek large language models in generating structured breast cancer multimodality imaging integrated reports from free-text radiology reports including mammography, ultrasound, MRI, and PET/CT.
MATERIALS AND METHODS: A retrospective analysis was conducted on 1358 free-text reports from 501 breast cancer patients across two institutions. The study design involved synthesizing multimodal imaging data into structured reports with three components: primary lesion characteristics, metastatic lesions, and TNM staging. Input prompts were standardized for both models, with GPT-4 using predesigned instructions and DeepSeek requiring manual input. Reports were evaluated based on physician satisfaction using a Likert scale, descriptive accuracy including lesion localization, size, SUV, and metastasis assessment, and TNM staging correctness according to NCCN guidelines. Statistical analysis included McNemar tests for binary outcomes and correlation analysis for multiclass comparisons with a significance threshold of P < .05.
RESULTS: Physician satisfaction scores showed strong correlation between models with r-values of 0.665 and 0.558 and P-values below .001. Both models demonstrated high accuracy in data extraction and integration. The mean accuracy for primary lesion features was 91.7% for GPT-4% and 92.1% for DeepSeek, while feature synthesis accuracy was 93.4% for GPT4 and 93.9% for DeepSeek. Metastatic lesion identification showed comparable overall accuracy at 93.5% for GPT4 and 94.4% for DeepSeek. GPT-4 performed better in pleural lesion detection with 94.9% accuracy compared to 79.5% for DeepSeek, whereas DeepSeek achieved higher accuracy in mesenteric metastasis identification at 87.5% vs 43.8% for GPT4. TNM staging accuracy exceeded 92% for T-stage and 94% for M-stage, with N-stage accuracy improving beyond 90% when supplemented with physical exam data.
CONCLUSION: Both GPT-4 and DeepSeek effectively generate structured breast cancer imaging reports with high accuracy in data mining, integration, and TNM staging. Integrating these models into clinical practice is expected to enhance report standardization and physician productivity.
引用
- Chen K, Hou X, Li X, et al. Structured Report Generation for Breast Cancer Imaging Based on Large Language Modeling: A Comparative Analysis of GPT-4 and DeepSeek. Acad Radiol. 2025. PMID: 40780984. doi:10.1016/j.acra.2025.07.046
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。