南方医科大学学报

南方医科大学学报 ›› 2026, Vol. 46 ›› Issue (1): 231-238.doi: 10.12122/j.issn.1673-4254.2026.01.25

• • 上一篇    

大语言模型在肿瘤诊断中的文字报告与医学影像应用研究进展

程浩然1,2(), 严鸿斌3, 袁子云4, 庄泽鸿1,2, 孙学刚5, 姚学清1,2,6   

  1. 1.南方医科大学附属广东省人民医院（广东省医学科学院）胃肠外科普通外科，广东 广州 510080
    2.广东省人民医院赣州医院（赣州市立医院）普通外科，江西 赣州 341099
    3.南方医科大学 第一临床医学院
    4.中山市人民医院普外科，广东 中山 528400
    5.中医药学院，广东 广州 510515
    6.华南理工大学医学院，广东 广州 510641
  • 收稿日期:2025-09-02 出版日期:2026-01-20 发布日期:2026-01-16
  • 通讯作者: 姚学清 E-mail:chenghaoran@gdph.org.cn
  • 作者简介:程浩然，在读博士研究生，E-mail: chenghaoran@gdph.org.cn
  • 基金资助:
    国家自然科学基金(82260501);国家自然科学基金(82274387);广东省特支计划科技创新领军人才项目;江西省赣州市科技计划项目(202101074816)

Research progress of large language models in tumor diagnosis: applications in textual reports and medical imaging

Haoran CHENG1,2(), Hongbin YAN3, Ziyun YUAN4, Zehong ZHUANG1,2, Xuegang SUN5, Xueqing YAO1,2,6   

  1. 1.Department of Gastrointestinal Surgery, Department of General Surgery, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China
    2.Department of General Surgery, Guangdong Provincial People's Hospital Ganzhou Hospital (Ganzhou Municipal Hospital), Ganzhou 341099, China
    3.First Clinical Medical School
    4.Department of General Surgery, Zhongshan People's Hospital, Zhongshan 528400, China
    5.School of Chinese Medicine, Southern Medical University, Guangzhou 510515, China
    6.School of Medicine, South China University of Technology, Guangzhou 510641, China
  • Received:2025-09-02 Online:2026-01-20 Published:2026-01-16
  • Contact: Xueqing YAO E-mail:chenghaoran@gdph.org.cn
  • Supported by:
    National Natural Science Foundation of China(82260501)

RichHTML

1

PDF

24

摘要：

大语言模型（LLMs）作为新兴人工智能技术，凭借其优异的文字与图像处理能力，为医疗领域智能化变革提供核心支撑，显著提升临床工作效率与质量。本文系统梳理LLMs在癌症诊断领域的应用现状、技术特点及发展方向，重点聚焦两大核心场景：一是影像报告、病理报告、综合病例报告等文字报告的自动化分析与解读；二是融合文本与医学影像的多模态数据诊断。研究发现，LLMs在癌症诊断中的综合能力已可媲美普通住院医师，但在专业化诊断与精准化判断方面仍存在明显短板；同时，LLMs展现出“小参数模型适配基层场景”“多语言报告分析泛用性差异”等应用层面特征。未来需进一步开发专业化、实用化的医疗专用LLMs，通过优化微调策略、构建高质量中文医疗数据集、整合视觉语言模型等方式，推动其临床落地并弥合医疗资源差距。

关键词: 大语言模型, 人工智能, 肿瘤诊断, 病理学, 影像学

Abstract:

Large language models (LLMs) are emerging artificial intelligence technologies with strong text and image processing capabilities, offering critical support for the intelligent transformation of healthcare and improving clinical efficiency and quality. This review summarizes the current applications, technical features, and future directions of LLMs in cancer diagnosis, focusing on two key scenarios: automated analysis of textual reports (e.g., imaging, pathology, and case summaries) and multimodal diagnosis combining text and medical images. Findings show that LLMs now perform at a level comparable to general resident physicians in cancer diagnosis but are still incapable of making specialized and precise judgments. They also exhibit application-specific traits, such as parameter-efficient models adapted for grassroots-level scenario and divergent versatility in multilingual report analysis. Future efforts should prioritize developing specialized, practical medical LLMs through optimized fine-tuning strategies, construction of high-quality Chinese medical datasets, and integration with vision-language models to promote the clinical application of these models and increase the accessibility of healthcare resources.

Key words: large language models, artificial intelligence, cancer diagnosis, pathology, medical imaging