Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence
文献类型：期刊论文
| 作者 | Bai, Xiangd2,3; Wang, Hanchen4; Ma, Liya2; Xu, Yongchao2; Gan, Jiefeng3; Fan, Ziwei3; Yang, Fan5; Ma, Ke3; Yang, Jiehua3; Bai, Song3 |
| 刊名 | NATURE MACHINE INTELLIGENCE
 |
| 出版日期 | 2021-12-01 |
| 卷号 | 3期号:12页码:1081-1089 |
| DOI | 10.1038/s42256-021-00421-z |
| 通讯作者 | Bai, Xiangd(xbai@hust.edu.cn) ; Zheng, Chuangsheng(cszheng@163.com) ; Wang, Jianming(jmwang@163.com) ; Li, Zhen(zhenli@hust.edu.cn) ; Schonlieb, Carola(cbs31@cam.ac.uk) ; Xia, Tian(tianxia@hust.edu.cn) |
| 英文摘要 | Artificial intelligence provides a promising solution for streamlining COVID-19 diagnoses; however, concerns surrounding security and trustworthiness impede the collection of large-scale representative medical data, posing a considerable challenge for training a well-generalized model in clinical practices. To address this, we launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the artificial intelligence (AI) model can be distributedly trained and independently executed at each host institution under a federated learning framework without data sharing. Here we show that our federated learning framework model considerably outperformed all of the local models (with a test sensitivity/specificity of 0.973/0.951 in China and 0.730/0.942 in the United Kingdom), achieving comparable performance with a panel of professional radiologists. We further evaluated the model on the hold-out (collected from another two hospitals without the federated learning framework) and heterogeneous (acquired with contrast materials) data, provided visual explanations for decisions made by the model, and analysed the trade-offs between the model performance and the communication costs in the federated training process. Our study is based on 9,573 chest computed tomography scans from 3,336 patients collected from 23 hospitals located in China and the United Kingdom. Collectively, our work advanced the prospects of utilizing federated learning for privacy-preserving AI in digital health. The COVID-19 pandemic sparked the need for international collaboration in using clinical data for rapid development of diagnosis and treatment methods. But the sensitive nature of medical data requires special care and ideally potentially sensitive data would not leave the organization which collected it. Xiang Bai and colleagues present a privacy-preserving AI framework for CT-based COVID-19 diagnosis and demonstrate it on data from 23 hospitals in China and the United Kingdom. |
| WOS关键词 | PNEUMONIA |
| 资助项目 | HUST COVID-19 Rapid Response Call[2020kfyXGYJ021] ; HUST COVID-19 Rapid Response Call[2020kfyXGYJ031] ; HUST COVID-19 Rapid Response Call[2020kfyXGYJ093] ; HUST COVID-19 Rapid Response Call[2020kfyXGYJ094] ; National Natural Science Foundation of China[61703171] ; National Natural Science Foundation of China[81771801] ; National Cancer Institute, National Institutes of Health[U01CA242879] ; Thammasat University Research fund under the NRCT[25/2561] ; Cambridge Trust ; Kathy Xu Fellowship ; Centre for Advanced Photonics and Electronics ; Cambridge Philosophical Society ; AstraZeneca ; Intel ; DRAGON consortium ; Turing AI Fellowship[EP/V025379/1] ; Alan Turing Institute ; Leverhulme Trust via CFI ; DRAGON ; Royal Society Wolfson Fellowship ; EPSRC[EP/S026045/1] ; EPSRC[EP/T003553/1] ; EPSRC[EP/N014588/1] ; EPSRC[EP/T017961] ; Wellcome Innovator Award[RG98755] ; Leverhulme Trust project Unveiling the invisible ; European Union[777826 NoMADS] ; Cantab Capital Institute for the Mathematics of Information |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| 出版者 | NATURE PORTFOLIO |
| WOS记录号 | WOS:000730505100007 |
| 源URL | [http://119.78.100.183/handle/2S10ELR8/299184]  |
| 专题 | 中国科学院上海药物研究所 |
| 通讯作者 | Bai, Xiangd; Zheng, Chuangsheng; Wang, Jianming; Li, Zhen; Schonlieb, Carola; Xia, Tian |
| 作者单位 | 1.CalmCar Inc, Suzhou, Peoples R China 2.Huazhong Univ Sci & Technol, Tongji Hosp & Med Coll, Dept Radiol, Wuhan, Peoples R China 3.Huazhong Univ Sci & Technol, Sch Artificial Intelligence & Automat, Wuhan, Peoples R China 4.Univ Cambridge, Dept Engn, Cambridge, England 5.Huazhong Univ Sci & Technol, Union Hosp, Dept Radiol, Tongji Med Coll, Wuhan, Peoples R China 6.HUST HW Joint Innovat Lab, Wuhan, Peoples R China 7.Wuhan Blood Ctr, Wuhan, Peoples R China 8.MSA Capital, Beijing, Peoples R China 9.Chinese Acad Sci, Shanghai Inst Mat Med, Natl Ctr Drug Screening, Shanghai, Peoples R China 10.Tufts Univ, Sch Med, CardioVasc & Intervent Radiol,Radiol, Radiol Qual & Operat,Cardiovasc Ctr,Tufts Med Ctr, Medford, OR USA |
| 推荐引用方式 GB/T 7714 | Bai, Xiangd,Wang, Hanchen,Ma, Liya,et al. Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence[J]. NATURE MACHINE INTELLIGENCE,2021,3(12):1081-1089. |
| APA | Bai, Xiangd.,Wang, Hanchen.,Ma, Liya.,Xu, Yongchao.,Gan, Jiefeng.,...&Xia, Tian.(2021).Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence.NATURE MACHINE INTELLIGENCE,3(12),1081-1089. |
| MLA | Bai, Xiangd,et al."Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence".NATURE MACHINE INTELLIGENCE 3.12(2021):1081-1089. |
入库方式： OAI收割
来源：上海药物研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。