自制人工智能在诊断病理学中的应用。

IF 5.6 2区 医学 Q1 ONCOLOGY
Julien Calderaro, Helen Morement, Frédérique Penault-Llorca, Stephen Gilbert, Jakob Nikolas Kather
{"title":"自制人工智能在诊断病理学中的应用。","authors":"Julien Calderaro, Helen Morement, Frédérique Penault-Llorca, Stephen Gilbert, Jakob Nikolas Kather","doi":"10.1002/path.6438","DOIUrl":null,"url":null,"abstract":"<p><p>Artificial intelligence (AI) methods for digital pathology have tremendous potential to improve cancer diagnostics, biomarkers, and ultimately patient care. These AI methods, if marketed and sold, require authorisation or clearance as in vitro diagnostic (IVD) devices by regulatory bodies like the Food and Drug Administration (FDA) in the USA or Notified Bodies in the European Union (EU). Many AI tools for digital pathology are unlikely to be commercially viable and taken up by commercial entities ready to navigate these complex and costly processes. However, a longstanding quality framework already exists that allows for lab-developed tests, colloquially known as 'homebrew' tests, that are locally validated and performed under the responsibility and oversight of the pathologist. Here we argue for advancing homebrew AI systems within this existing framework to enhance patients' access to supportive digital diagnostic tools. We outline how homebrew AI models are currently permitted under regulatory provisions in the USA and the European Union, how a new US FDA rule may effectively regulate them out of existence, and propose steps to facilitate the safe and effective integration of homebrew AI models in pathology practice. © 2025 The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.</p>","PeriodicalId":232,"journal":{"name":"The Journal of Pathology","volume":" ","pages":""},"PeriodicalIF":5.6000,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The case for homebrew AI in diagnostic pathology.\",\"authors\":\"Julien Calderaro, Helen Morement, Frédérique Penault-Llorca, Stephen Gilbert, Jakob Nikolas Kather\",\"doi\":\"10.1002/path.6438\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Artificial intelligence (AI) methods for digital pathology have tremendous potential to improve cancer diagnostics, biomarkers, and ultimately patient care. These AI methods, if marketed and sold, require authorisation or clearance as in vitro diagnostic (IVD) devices by regulatory bodies like the Food and Drug Administration (FDA) in the USA or Notified Bodies in the European Union (EU). Many AI tools for digital pathology are unlikely to be commercially viable and taken up by commercial entities ready to navigate these complex and costly processes. However, a longstanding quality framework already exists that allows for lab-developed tests, colloquially known as 'homebrew' tests, that are locally validated and performed under the responsibility and oversight of the pathologist. Here we argue for advancing homebrew AI systems within this existing framework to enhance patients' access to supportive digital diagnostic tools. We outline how homebrew AI models are currently permitted under regulatory provisions in the USA and the European Union, how a new US FDA rule may effectively regulate them out of existence, and propose steps to facilitate the safe and effective integration of homebrew AI models in pathology practice. © 2025 The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.</p>\",\"PeriodicalId\":232,\"journal\":{\"name\":\"The Journal of Pathology\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":5.6000,\"publicationDate\":\"2025-07-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"The Journal of Pathology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1002/path.6438\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"The Journal of Pathology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1002/path.6438","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

用于数字病理学的人工智能(AI)方法在改善癌症诊断、生物标志物以及最终的患者护理方面具有巨大的潜力。这些人工智能方法如果上市和销售,需要获得美国食品和药物管理局(FDA)或欧盟(EU)公告机构等监管机构的体外诊断(IVD)设备授权或许可。许多用于数字病理学的人工智能工具不太可能具有商业可行性,也不太可能被准备好应对这些复杂且成本高昂的流程的商业实体所采用。然而,一个长期存在的质量框架已经存在,允许实验室开发的测试,俗称“自制”测试,在病理学家的责任和监督下进行本地验证和执行。在这里,我们主张在现有框架内推进自制人工智能系统,以增强患者获得支持性数字诊断工具的机会。我们概述了目前在美国和欧盟的监管规定下,自制人工智能模型是如何被允许的,美国FDA的新规定如何有效地监管它们的存在,并提出了促进自制人工智能模型在病理实践中安全有效整合的步骤。©2025作者。《病理学杂志》由John Wiley & Sons Ltd代表大不列颠和爱尔兰病理学会出版。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
The case for homebrew AI in diagnostic pathology.

Artificial intelligence (AI) methods for digital pathology have tremendous potential to improve cancer diagnostics, biomarkers, and ultimately patient care. These AI methods, if marketed and sold, require authorisation or clearance as in vitro diagnostic (IVD) devices by regulatory bodies like the Food and Drug Administration (FDA) in the USA or Notified Bodies in the European Union (EU). Many AI tools for digital pathology are unlikely to be commercially viable and taken up by commercial entities ready to navigate these complex and costly processes. However, a longstanding quality framework already exists that allows for lab-developed tests, colloquially known as 'homebrew' tests, that are locally validated and performed under the responsibility and oversight of the pathologist. Here we argue for advancing homebrew AI systems within this existing framework to enhance patients' access to supportive digital diagnostic tools. We outline how homebrew AI models are currently permitted under regulatory provisions in the USA and the European Union, how a new US FDA rule may effectively regulate them out of existence, and propose steps to facilitate the safe and effective integration of homebrew AI models in pathology practice. © 2025 The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
The Journal of Pathology
The Journal of Pathology 医学-病理学
CiteScore
14.10
自引率
1.40%
发文量
144
审稿时长
3-8 weeks
期刊介绍: The Journal of Pathology aims to serve as a translational bridge between basic biomedical science and clinical medicine with particular emphasis on, but not restricted to, tissue based studies. The main interests of the Journal lie in publishing studies that further our understanding the pathophysiological and pathogenetic mechanisms of human disease. The Journal of Pathology welcomes investigative studies on human tissues, in vitro and in vivo experimental studies, and investigations based on animal models with a clear relevance to human disease, including transgenic systems. As well as original research papers, the Journal seeks to provide rapid publication in a variety of other formats, including editorials, review articles, commentaries and perspectives and other features, both contributed and solicited.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信