克服人工智能在病理学中应用的挑战。
Overcoming the challenges to implementation of artificial intelligence in pathology.
机构信息
Experimental Pathology, Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
Department of Medicine I, University Hospital and Faculty of Medicine, Technical University Dresden, Dresden, Germany.
出版信息
J Natl Cancer Inst. 2023 Jun 8;115(6):608-612. doi: 10.1093/jnci/djad048.
Abstract
Pathologists worldwide are facing remarkable challenges with increasing workloads and lack of time to provide consistently high-quality patient care. The application of artificial intelligence (AI) to digital whole-slide images has the potential of democratizing the access to expert pathology and affordable biomarkers by supporting pathologists in the provision of timely and accurate diagnosis as well as supporting oncologists by directly extracting prognostic and predictive biomarkers from tissue slides. The long-awaited adoption of AI in pathology, however, has not materialized, and the transformation of pathology is happening at a much slower pace than that observed in other fields (eg, radiology). Here, we provide a critical summary of the developments in digital and computational pathology in the last 10 years, outline key hurdles and ways to overcome them, and provide a perspective for AI-supported precision oncology in the future.
摘要
全世界的病理学家都面临着巨大的挑战，包括工作量不断增加和缺乏时间来提供始终如一的高质量患者护理。人工智能 (AI) 在数字全切片图像中的应用有可能通过支持病理学家提供及时准确的诊断，并通过直接从组织切片中提取预后和预测生物标志物来支持肿瘤学家，从而实现专家病理学和负担得起的生物标志物的普及。然而，人们期待已久的 AI 在病理学中的应用并没有实现，病理学的转变速度比其他领域（例如放射学）要慢得多。在这里，我们对过去 10 年数字和计算病理学的发展进行了批判性总结，概述了关键障碍及其克服方法，并为未来人工智能支持的精准肿瘤学提供了展望。
相似文献
1
Overcoming the challenges to implementation of artificial intelligence in pathology.克服人工智能在病理学中应用的挑战。
J Natl Cancer Inst. 2023 Jun 8;115(6):608-612. doi: 10.1093/jnci/djad048.
2
Artificial intelligence in digital pathology - new tools for diagnosis and precision oncology.人工智能在数字病理学中的应用——诊断和精准肿瘤学的新工具。
Nat Rev Clin Oncol. 2019 Nov;16(11):703-715. doi: 10.1038/s41571-019-0252-y. Epub 2019 Aug 9.
3
Predicting gene mutation status via artificial intelligence technologies based on multimodal integration (MMI) to advance precision oncology.基于多模态整合（MMI）的人工智能技术预测基因突变状态，以推进精准肿瘤学。
Semin Cancer Biol. 2023 Jun;91:1-15. doi: 10.1016/j.semcancer.2023.02.006. Epub 2023 Feb 19.
4
Emerging role of deep learning-based artificial intelligence in tumor pathology.深度学习人工智能在肿瘤病理学中的新兴作用。
Cancer Commun (Lond). 2020 Apr;40(4):154-166. doi: 10.1002/cac2.12012. Epub 2020 Apr 11.
5
Artificial intelligence in anatomical pathology: building a strong foundation for precision medicine.解剖病理学中的人工智能：为精准医学筑牢基础。
Hum Pathol. 2023 Feb;132:31-38. doi: 10.1016/j.humpath.2022.07.008. Epub 2022 Jul 20.
6
Applying Artificial Intelligence to Address the Knowledge Gaps in Cancer Care.应用人工智能解决癌症护理中的知识空白。
Oncologist. 2019 Jun;24(6):772-782. doi: 10.1634/theoncologist.2018-0257. Epub 2018 Nov 16.
7
Revolutionizing Digital Pathology With the Power of Generative Artificial Intelligence and Foundation Models.利用生成式人工智能和基础模型推动数字病理学革命。
Lab Invest. 2023 Nov;103(11):100255. doi: 10.1016/j.labinv.2023.100255. Epub 2023 Sep 26.
8
Artificial intelligence and digital biomarker in precision pathology guiding immune therapy selection and precision oncology.人工智能和数字生物标志物在精准病理学指导免疫治疗选择和精准肿瘤学中的应用。
Cancer Rep (Hoboken). 2023 Jul;6(7):e1796. doi: 10.1002/cnr2.1796. Epub 2023 Feb 22.
9
Computational pathology in cancer diagnosis, prognosis, and prediction - present day and prospects.癌症诊断、预后和预测中的计算病理学 - 现状与展望。
J Pathol. 2023 Aug;260(5):551-563. doi: 10.1002/path.6163. Epub 2023 Aug 14.
10
Precision immunoprofiling by image analysis and artificial intelligence.通过图像分析和人工智能进行精准免疫组化分析。
Virchows Arch. 2019 Apr;474(4):511-522. doi: 10.1007/s00428-018-2485-z. Epub 2018 Nov 23.
引用本文的文献
1
Artificial Intelligence-Based Pathology to Assist Prediction of Neoadjuvant Therapy Responses for Breast Cancer.基于人工智能的病理学辅助预测乳腺癌新辅助治疗反应
Cancer Med. 2025 Aug;14(15):e71132. doi: 10.1002/cam4.71132.
2
Automating liver biopsy segmentation with a robust, open-source tool for pathology research: the HOTSPoT model.利用一个用于病理学研究的强大开源工具实现肝活检分割自动化：HOTSPoT模型。
NPJ Digit Med. 2025 Jul 18;8(1):455. doi: 10.1038/s41746-025-01870-1.
3
Streamlining a Patchwork - Exploring the Challenges of Digital Transformation in Pathology: Ethnographic Study.简化拼凑之物——探索病理学数字转型的挑战：人种志研究
J Med Internet Res. 2025 Jul 18;27:e63366. doi: 10.2196/63366.
4
Closing the gap in the clinical adoption of computational pathology: a standardized, open-source framework to integrate deep-learning models into the laboratory information system.缩小计算病理学临床应用方面的差距：一个将深度学习模型集成到实验室信息系统的标准化开源框架。
Genome Med. 2025 May 26;17(1):60. doi: 10.1186/s13073-025-01484-y.
5
Artificial Intelligence in Placental Pathology: New Diagnostic Imaging Tools in Evolution and in Perspective.胎盘病理学中的人工智能：不断发展与展望的新型诊断成像工具
J Imaging. 2025 Apr 3;11(4):110. doi: 10.3390/jimaging11040110.
6
Artificial Intelligence in Relation to Accurate Information and Tasks in Gynecologic Oncology and Clinical Medicine-Dunning-Kruger Effects and Ultracrepidarianism.人工智能与妇科肿瘤学和临床医学中的准确信息及任务——邓宁-克鲁格效应和不懂装懂。
Diagnostics (Basel). 2025 Mar 15;15(6):735. doi: 10.3390/diagnostics15060735.
7
SNUH methylation classifier for CNS tumors.用于中枢神经系统肿瘤的SNUH甲基化分类器。
Clin Epigenetics. 2025 Mar 12;17(1):47. doi: 10.1186/s13148-025-01824-0.
8
Multimodal histopathologic models stratify hormone receptor-positive early breast cancer.多模态组织病理学模型对激素受体阳性早期乳腺癌进行分层。
Nat Commun. 2025 Mar 2;16(1):2106. doi: 10.1038/s41467-025-57283-x.
9
The tumour histopathology "glossary" for AI developers.面向人工智能开发者的肿瘤组织病理学“术语表”。
PLoS Comput Biol. 2025 Jan 23;21(1):e1012708. doi: 10.1371/journal.pcbi.1012708. eCollection 2025 Jan.
10
Awareness and Attitude Toward Artificial Intelligence Among Medical Students and Pathology Trainees: Survey Study.医学生和病理学实习生对人工智能的认知与态度：调查研究
JMIR Med Educ. 2025 Jan 10;11:e62669. doi: 10.2196/62669.
本文引用的文献
1
Validation of MSIntuit as an AI-based pre-screening tool for MSI detection from colorectal cancer histology slides.验证 MSIntuit 作为一种基于人工智能的工具，用于从结直肠癌组织学幻灯片中进行 MSI 检测的预筛选。
Nat Commun. 2023 Nov 6;14(1):6695. doi: 10.1038/s41467-023-42453-6.
2
Artificial intelligence in histopathology: enhancing cancer research and clinical oncology.人工智能在组织病理学中的应用：增强癌症研究和临床肿瘤学。
Nat Cancer. 2022 Sep;3(9):1026-1038. doi: 10.1038/s43018-022-00436-4. Epub 2022 Sep 22.
3
A clinical decision support system optimising adjuvant chemotherapy for colorectal cancers by integrating deep learning and pathological staging markers: a development and validation study.通过深度学习和病理分期标志物整合优化结直肠癌辅助化疗的临床决策支持系统：一项开发和验证研究。
Lancet Oncol. 2022 Sep;23(9):1221-1232. doi: 10.1016/S1470-2045(22)00391-6. Epub 2022 Aug 11.
4
Medical domain knowledge in domain-agnostic generative AI.领域无关生成式人工智能中的医学领域知识。
NPJ Digit Med. 2022 Jul 11;5(1):90. doi: 10.1038/s41746-022-00634-5.
5
Swarm learning for decentralized artificial intelligence in cancer histopathology.群体学习在癌症病理组织学中的去中心化人工智能应用。
Nat Med. 2022 Jun;28(6):1232-1239. doi: 10.1038/s41591-022-01768-5. Epub 2022 Apr 25.
6
Area under the curve may hide poor generalisation to external datasets.曲线下面积可能掩盖了对外部数据集的泛化能力较差的问题。
ESMO Open. 2022 Apr;7(2):100429. doi: 10.1016/j.esmoop.2022.100429. Epub 2022 Apr 6.
7
Artificial intelligence to identify genetic alterations in conventional histopathology.人工智能识别常规组织病理学中的遗传改变。
J Pathol. 2022 Jul;257(4):430-444. doi: 10.1002/path.5898. Epub 2022 Apr 21.
8
Deep learning-enabled assessment of cardiac allograft rejection from endomyocardial biopsies.深度学习评估心内膜心肌活检中的心脏移植物排斥反应。
Nat Med. 2022 Mar;28(3):575-582. doi: 10.1038/s41591-022-01709-2. Epub 2022 Mar 21.
9
Artificial intelligence for detection of microsatellite instability in colorectal cancer-a multicentric analysis of a pre-screening tool for clinical application.人工智能检测结直肠癌微卫星不稳定性——一种用于临床应用的预筛选工具的多中心分析。
ESMO Open. 2022 Apr;7(2):100400. doi: 10.1016/j.esmoop.2022.100400. Epub 2022 Mar 2.
10
Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis.泛癌计算组织病理学揭示了突变、肿瘤组成和预后。
Nat Cancer. 2020 Aug;1(8):800-810. doi: 10.1038/s43018-020-0085-8. Epub 2020 Jul 27.
Zotero 插件