外科理论与实践

外科理论与实践 >

2026 , Vol. 31 >Issue 03: 204 - 211

DOI: https://doi.org/10.16139/j.1007-9610.2026.03.05

专家论坛

乳腺癌数字化病理与人工智能辅助诊断

  • 阮淼 ,
  • 费晓春 ,
  • 笪倩
展开
  • 上海交通大学医学院附属瑞金医院病理科， 上海 200025
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。

笪倩：E-mail: dq11848@rjh.com.cn

收稿日期: 2026-04-07

  网络出版日期: 2026-08-11

收起

Digital pathology and artificial intelligence-assisted diagnosis in breast cancer

  • RUAN Miao ,
  • FEI Xiaochun ,
  • DA Qian
Expand
  • Department of Pathology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China

Received date: 2026-04-07

  Online published: 2026-08-11

Fold

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

本文引用格式

阮淼 , 费晓春 , 笪倩 . 乳腺癌数字化病理与人工智能辅助诊断[J]. 外科理论与实践, 2026 , 31(03) : 204 -211 . DOI: 10.16139/j.1007-9610.2026.03.05

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

参考文献

[1] Ivanov V, Khalid U, Gurung J, et al. Use of AI histopathology in breast cancer diagnosis[J]. Medicina(Kaunas), 2025, 61(10):1878.
[2] Li W, Ye S, Jin Z, et al. Artificial intelligence in digital pathology of breast cancer, new era of practice?[J]. Int J Surg, 2025, 111(11):8270-8283.
[3] Mckelvey B, Torres-Saavedra P A, Li J, et al. Agreement across 10 AI models in assessing HER2 expression in breast cancer whole-slide images[J]. Mod Pathol, 2026, 39(2):100944.
[4] Niazi M K K, Parwani A V, Gurcan M N. Digital pathology and artificial intelligence[J]. Lancet Oncol, 2019, 20(5):e253-e261.
[5] Lu MY, Williamson D F K, Chen T Y, et al. Data-efficient and weakly supervised computational pathology on whole-slide images[J]. Nat Biomed Eng, 2021, 5(6):555-570.
[6] Chen R J, Ding T, Lu M Y, et al. Towards a general-purpose foundation model for computational pathology[J]. Nat Med, 2024, 30(3):850-862.
[7] Vorontsov E, Bozkurt A, Casson A, et al. A foundation model for clinical-grade computational pathology and rare cancers detection[J]. Nat Med, 2024, 30(10):2924-2935.
[8] Sparano J A, Gray R J, Makower D F, et al. Adjuvant chemotherapy guided by a 21-gene expression assay in breast cancer[J]. N Engl J Med, 2018, 379(2):111-121.
[9] Lu M Y, Chen B, Williamson D F K, et al. A multimodal generative AI copilot for human pathology[J]. Nature, 2024, 634(8033):466-473.
[10] Chen C, Weishaupt L L, Williamson D F K, et al. Evidence-based diagnostic reasoning with multi-agent copilot for human pathology[J]. 2025.
[11] Wang X, Zhao J, Marostica E, et al. A pathology foundation model for cancer diagnosis and prognosis prediction[J]. Nature, 2024, 634(8035):970-978.
[12] Xu H, Usuyama N, Bagga J, et al. A whole-slide foundation model for digital pathology from real-world data[J]. Nature, 2024, 630(8015):181-188.
[13] Zhou X, Sun L, He D, et al. Knowledge-enhanced pretraining for vision-language pathology foundation model on cancer diagnosis[J]. Cancer Cell, 2026, 44(4):777-791.
[14] Kaczmarzyk J R, Van Alsten S C, Cozzo A J, et al. Towards interpretable prediction of recurrence risk in breast cancer using pathology foundation models[J]. NPJ Digit Med, 2026, 9(1):149.
[15] Chen R J, Lu M Y, Williamson D F K, et al. Scaling vision transformers to gigapixel images via hierarchical self-supervised learning[C]. arXiv,2022, 2206:02647.
[16] Li B, Zhong Y, Xing Z, et al. Hierarchical image pyramid transformer framework for automated breast cancer molecular subtyping using tissue microarrays[J]. J Pathol, 2026, 268(4):460-476.
[17] Lu M Y, Chen B, Williamson D F K, et al. A visual-language foundation model for computational pathology[J]. Nat Med, 2024, 30(3):863-874.
[18] Campanella G, Chen S, Singh M, et al. A clinical benchmark of public self-supervised pathology foundation models[J]. Nat Commun, 2025, 16:3640.
[19] Xiang J, Wang X, Zhang X, et al. A vision-language foundation model for precision oncology[J]. Nature, 2025, 638(8051):769-778.
[20] Ding T, Wagner S J, Song A H, et al. A multimodal whole-slide foundation model for pathology[J]. Nat Med, 2025, 31(11):3749-3761.
[21] Wang Y H, Chang M H, Tsai H H, et al. Transformer-based HER2 scoring in breast cancer: comparative performance of a foundation and a lightweight model[J]. Diagnostics (Basel), 2025, 15(17):2131.
[22] Ochi M, Komura D, Ishikawa S. Pathology foundation models[J]. JMA J, 2025, 8(1):121-130.
[23] Frascarelli C, Venetis K, Marra A, et al. Deep learning algorithm on H&E whole slide images to characterize TP53 alterations in breast cancer[J]. Comput Struct Biotechnol J, 2024, 23:4252-4259.
[24] Li Y, Xiong X, Liu X, et al. An interpretable deep learning model for detecting BRCA pathogenic variants of breast cancer[J]. PeerJ, 2024, 12:e18098.
[25] Karasayar A H D, Kula? ?, Kapucuo?lu N. Advances in breast cancer care: the role of AI and digital pathology in precision medicine[J]. Eur J Breast Health, 2025, 21(2):93-100.
[26] Luan H, Hu T, Hu J, et al. Breast cancer homologous recombination deficiency prediction from pathological images[J]. NPJ Precis Oncol, 2025, 9(1):160.
[27] Sparano J A, Gray R J, Makower D F, et al. Clinical and genomic risk for late breast cancer recurrence and survival[J]. NEJM Evid, 2024, 3(8):EVIDoa2300267.
[28] Sparano J A, Gray R J, Ravdin P M, et al. Clinical and genomic risk to guide the use of adjuvant therapy for breast cancer[J]. N Engl J Med, 2019, 380(25):2395-2405.
[29] Kalinsky K, Barlow W E, Gralow J R, et al. 21-gene assay to inform chemotherapy benefit in node-positive breast cancer[J]. N Engl J Med, 2021, 385(25):2336-2347.
[30] Abdou Y, Barlow W E, Gralow J R, et al. Race and clinical outcomes in HR+/HER2-, node-positive breast cancer in the randomized RxPONDER trial[J]. J Natl Cancer Inst, 2025, 117(5):889-897.
[31] Shamai G, Cohen S, Binenbaum Y, et al. Deep learning on histopathological images to predict breast cancer recurrence risk and chemotherapy benefit[J]. Lancet Oncol, 26,27(4):512-526.
[32] Boehm K M, El Nahhas O S M, Marra A, et al. Multimodal histopathologic models stratify hormone receptor-positive early breast cancer[J]. Nat Commun, 2025, 16(1):2106.
[33] Gessain G, Lacroix-Triki M. Computational pathology for breast cancer: where do we stand for prognostic applications?[J]. Breast, 2025, 81:104464.
[34] Chen W, Zhang P, Tran T N, et al. A visual-omics foundation model to bridge histopathology with spatial transcriptomics[J]. Nat Methods, 2025, 22(7):1568-1582.
[35] Song A H, Williams M, Williamson D F K, et al. Analysis of 3D pathology samples using weakly supervised AI[J]. Cell, 2024, 187(10):2502-2520.
[36] Marra A, Morganti S, Pareja F, et al. Artificial intelligence entering the pathology arena in oncology: current applications and future perspectives[J]. Ann Oncol, 2025, 36:712-725.
[37] Campanella G, Kumar N, Nanda S, et al. Real-world deployment of a fine-tuned pathology foundation model for lung cancer biomarker detection[J]. Nat Med, 2025, 31(9):3002-3010.
[38] L?ng K, Josefsson V, Larsson A M, et al. Artificial intelligence-supported screen reading versus standard double reading in the Mammography Screening with Artificial Intelligence trial (MASAI): a clinical safety analysis of a randomised, controlled, non-inferiority, single-blinded, screening accuracy study[J]. Lancet Oncol, 2023, 24(8):936-944.
Options
文章导航

/

〈 〉