外科理论与实践 ›› 2026, Vol. 31 ›› Issue (03): 204-211.doi: 10.16139/j.1007-9610.2026.03.05

• 专家论坛 • 上一篇    下一篇

乳腺癌数字化病理与人工智能辅助诊断

阮淼, 费晓春, 笪倩()   

  1. 上海交通大学医学院附属瑞金医院病理科, 上海 200025
  • 收稿日期:2026-04-07 出版日期:2026-06-25 发布日期:2026-08-11
  • 通讯作者: 笪倩:E-mail: dq11848@rjh.com.cn
  • 作者简介:作者贡献/Authors’ contributions

    阮淼负责资料收集和撰写;费晓春负责审校、提供意见;笪倩负责指导、审查和修订。所有作者均阅读并确认最终稿。

Digital pathology and artificial intelligence-assisted diagnosis in breast cancer

RUAN Miao, FEI Xiaochun, DA Qian()   

  1. Department of Pathology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China
  • Received:2026-04-07 Online:2026-06-25 Published:2026-08-11

摘要:

乳腺癌是全球女性最常见的恶性肿瘤。近年来,随着人工智能(AI)技术的迅速发展,病理基础大模型在乳腺癌病理诊疗领域展现出巨大潜力。本文从技术架构、临床应用、前沿探索及伦理挑战四个维度,系统阐述乳腺癌数字化病理与AI辅助诊断的应用现状与发展趋势,重点介绍以Virchow、UNI、CONCH为代表的病理基础大模型在乳腺癌组织学分级、HER2精准评分、基因型预测等下游任务中的最新进展,探讨PathChat、SlideSeek等多模态生成式AI系统在推动可解释性诊断方面的突破,并就空间转录组学整合、三维(3D)病理重建等前沿方向进行展望。

关键词: 乳腺癌, 数字化病理, 人工智能, 基础大模型, 病理诊断

Abstract:

Breast cancer is the most common malignancy among women worldwide. In recent years, with the rapid development of artificial intelligence (AI) technology, foundation models in pathology have shown great potential in the diagnosis and treatment of breast cancer. This article provided a systematic overview of the current state and future directions of digital pathology and AI-assisted diagnosis for breast cancer from four dimensions: technical architecture, clinical applications, frontier explorations, and ethical challenges. We focused on the latest advances in pathology foundation models such as Virchow, UNI, and CONCH in downstream tasks including histological grading, HER2 scoring, and genotype prediction, discussed breakthroughs of multimodal generative AI systems like PathChat and SlideSeek in promoting interpretable diagnosis, and provided perspectives on emerging directions such as spatial transcriptomics integration and three-dimensional(3D) pathology reconstruction.

Key words: Breast cancer, Digital pathology, Artificial intelligence(AI), Foundation model, Pathological diagnosis

中图分类号: