Swarm learning for decentralized artificial intelligence in cancer histopathology.

Swarm learning for decentralized artificial intelligence in cancer histopathology.
复制标题

DOI:
10.1038/s41591-022-01768-5
复制
发表时间:
2022-06
期刊:
影响因子:
82.9
通讯作者:
Kather, Jakob Nikolas
Kather, Jakob Nikolas
中科院分区:
医学1区
文献类型:
--
作者:
Saldanha, Oliver Lester;Quirke, Philip;West, Nicholas P.;James, Jacqueline A.;Loughrey, Maurice B.;Grabsch, Heike, I;Salto-Tellez, Manuel;Alwers, Elizabeth;Cifci, Didem;Laleh, Narmin Ghaffari;Seibel, Tobias;Gray, Richard;Hutchins, Gordon G. A.;Brenner, Hermann;van Treeck, Marko;Yuan, Tanwei;Brinker, Titus J.;Chang-Claude, Jenny;Khader, Firas;Schuppert, Andreas;Luedde, Tom;Trautwein, Christian;Muti, Hannah Sophie;Foersch, Sebastian;Hoffmeister, Michael;Truhn, Daniel;Kather, Jakob Nikolas

文献摘要

参考文献

被引文献

相似文献

人工智能(AI)可以直接从常规组织病理学切片中预测分子改变的存在。然而,训练强大的人工智能系统需要庞大的数据集,而数据收集面临着实际、道德和法律方面的障碍。这些障碍可以通过群体学习(SL)来克服,在这种学习中,合作伙伴共同训练人工智能模型,同时避免数据传输和垄断数据治理。在这里,我们展示了SL在来自5000多名患者的十亿像素组织病理学图像的大型多中心数据集中的成功使用。我们发现使用SL训练的AI模型可以直接从苏木精和伊红(H&E)染色的结直肠癌病理切片中预测BRAF突变状态和微卫星不稳定性。我们对来自北爱尔兰、德国和美国的三个患者队列进行了人工智能模型训练,并在来自英国的两个独立数据集中验证了预测性能。我们的数据显示,sl训练的人工智能模型优于大多数本地训练的模型,并且与在合并数据集上训练的模型表现相当。此外,我们还证明了基于语言的人工智能模型具有数据效率。在未来,SL可以用于训练分布式AI模型,用于任何组织病理学图像分析任务,消除了数据传输的需要。一个分散的、保护隐私的机器学习框架,用于训练临床相关的人工智能系统,通过使用在现实环境中收集的常规组织病理学幻灯片,识别结直肠癌患者可操作的分子改变。
Artificial intelligence (AI) can predict the presence of molecular alterations directly from routine histopathology slides. However, training robust AI systems requires large datasets for which data collection faces practical, ethical and legal obstacles. These obstacles could be overcome with swarm learning (SL), in which partners jointly train AI models while avoiding data transfer and monopolistic data governance. Here, we demonstrate the successful use of SL in large, multicentric datasets of gigapixel histopathology images from over 5,000 patients. We show that AI models trained using SL can predict BRAF mutational status and microsatellite instability directly from hematoxylin and eosin (H&E)-stained pathology slides of colorectal cancer. We trained AI models on three patient cohorts from Northern Ireland, Germany and the United States, and validated the prediction performance in two independent datasets from the United Kingdom. Our data show that SL-trained AI models outperform most locally trained models, and perform on par with models that are trained on the merged datasets. In addition, we show that SL-based AI models are data efficient. In the future, SL can be used to train distributed AI models for any histopathology image analysis task, eliminating the need for data transfer. A decentralized, privacy-preserving machine learning framework used to train a clinically relevant AI system identifies actionable molecular alterations in patients with colorectal cancer by use of routine histopathology slides collected in real-world settings.
DOI: 10.1136/gut.2005087130
发表时间: 2006-08-01
期刊: GUT
影响因子: 24.5
作者:
Brenner, H.;Chang-Claude, J.;Hoffmeister, M.
通讯作者: Hoffmeister, M.
DOI: 10.1038/s41568-021-00408-3
发表时间: 2022-03
期刊: Nature reviews. Cancer
影响因子: --
作者:
Boehm KM;Khosravi P;Vanguri R;Gao J;Shah SP
通讯作者: Shah SP
DOI: 10.1016/s0140-6736(07)61866-2
发表时间: 2007-12-15
期刊: LANCET
影响因子: 168.9
作者:
Gray, Richard;Barnwell, Jennifer;Kerr, David J.
通讯作者: Kerr, David J.
DOI: 10.1038/s43018-020-0087-6
发表时间: 2020-07-27
期刊: Nature cancer
影响因子: 22.7
作者:
Kather JN;Heij LR;Grabsch HI;Loeffler C;Echle A;Muti HS;Krause J;Niehues JM;Sommer KA;Bankhead P;Kooreman LF;Schulte JJ;Cipriani NA;Buelow RD;Boor P;Ortiz-Brüchle NN;Hanby AM;Speirs V;Kochanny S;Patnaik A;Srisuwananukorn A;Brenner H;Hoffmeister M;van den Brandt PA;Jäger D;Trautwein C;Pearson AT;Luedde T
通讯作者: Luedde T
DOI: 10.1038/s41551-021-00751-8
发表时间: 2021-06
影响因子: 28.1
作者:
通讯作者: --