Structured Report Generation for Breast Cancer Imaging Based on Large Language Modeling: A Comparative Analysis of GPT-4 and DeepSeek

作者：Kun Chen, Xuefeng Hou, Xiaofeng Li, Wengui Xu, Heqing Yi · 发表于：Academic Radiology · 年份：2025 · DOI：10.1016/j.acra.2025.07.046 · 被引用次数：10 · 研究领域：Radiomics and Machine Learning in Medical Imaging、AI in cancer detection、Artificial Intelligence in Healthcare and Education

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 Deep...