Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence
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 pr...
Saved in:
Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Published: |
2022
|
Subjects: | |
Online Access: | https://repository.li.mahidol.ac.th/handle/123456789/76625 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Mahidol University |
id |
th-mahidol.76625 |
---|---|
record_format |
dspace |
spelling |
th-mahidol.766252022-08-04T15:25:47Z Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence Xiang Bai Hanchen Wang Liya Ma Yongchao Xu Jiefeng Gan Ziwei Fan Fan Yang Ke Ma Jiehua Yang Song Bai Chang Shu Xinyu Zou Renhao Huang Changzheng Zhang Xiaowu Liu Dandan Tu Chuou Xu Wenqing Zhang Xi Wang Anguo Chen Yu Zeng Dehua Yang Ming Wei Wang Nagaraj Holalkere Neil J. Halin Ihab R. Kamel Jia Wu Xuehua Peng Xiang Wang Jianbo Shao Pattanasak Mongkolwat Jianjun Zhang Weiyang Liu Michael Roberts Zhongzhao Teng Lucian Beer Lorena E. Sanchez Evis Sala Daniel L. Rubin Adrian Weller Joan Lasenby Chuangsheng Zheng Jianming Wang Zhen Li Carola Schönlieb Tian Xia Department of Radiology Department of Engineering Faculty of Mathematics Alan Turing Institute Stanford University School of Medicine Shanghai Institute of Materia Medica, Chinese Academy of Sciences Huazhong University of Science and Technology Tufts University University of Texas MD Anderson Cancer Center Wuhan University of Science and Technology Mahidol University Stanford University AstraZeneca The Central Hospital of Wuhan The Johns Hopkins Hospital Tongji Medical College MSA Capital CalmCar Inc Wuhan Children's Hospital Wuhan Blood Centre Computer Science 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. 2022-08-04T08:25:47Z 2022-08-04T08:25:47Z 2021-12-01 Article Nature Machine Intelligence. Vol.3, No.12 (2021), 1081-1089 10.1038/s42256-021-00421-z 25225839 2-s2.0-85121384145 https://repository.li.mahidol.ac.th/handle/123456789/76625 Mahidol University SCOPUS https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85121384145&origin=inward |
institution |
Mahidol University |
building |
Mahidol University Library |
continent |
Asia |
country |
Thailand Thailand |
content_provider |
Mahidol University Library |
collection |
Mahidol University Institutional Repository |
topic |
Computer Science |
spellingShingle |
Computer Science Xiang Bai Hanchen Wang Liya Ma Yongchao Xu Jiefeng Gan Ziwei Fan Fan Yang Ke Ma Jiehua Yang Song Bai Chang Shu Xinyu Zou Renhao Huang Changzheng Zhang Xiaowu Liu Dandan Tu Chuou Xu Wenqing Zhang Xi Wang Anguo Chen Yu Zeng Dehua Yang Ming Wei Wang Nagaraj Holalkere Neil J. Halin Ihab R. Kamel Jia Wu Xuehua Peng Xiang Wang Jianbo Shao Pattanasak Mongkolwat Jianjun Zhang Weiyang Liu Michael Roberts Zhongzhao Teng Lucian Beer Lorena E. Sanchez Evis Sala Daniel L. Rubin Adrian Weller Joan Lasenby Chuangsheng Zheng Jianming Wang Zhen Li Carola Schönlieb Tian Xia Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence |
description |
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. |
author2 |
Department of Radiology |
author_facet |
Department of Radiology Xiang Bai Hanchen Wang Liya Ma Yongchao Xu Jiefeng Gan Ziwei Fan Fan Yang Ke Ma Jiehua Yang Song Bai Chang Shu Xinyu Zou Renhao Huang Changzheng Zhang Xiaowu Liu Dandan Tu Chuou Xu Wenqing Zhang Xi Wang Anguo Chen Yu Zeng Dehua Yang Ming Wei Wang Nagaraj Holalkere Neil J. Halin Ihab R. Kamel Jia Wu Xuehua Peng Xiang Wang Jianbo Shao Pattanasak Mongkolwat Jianjun Zhang Weiyang Liu Michael Roberts Zhongzhao Teng Lucian Beer Lorena E. Sanchez Evis Sala Daniel L. Rubin Adrian Weller Joan Lasenby Chuangsheng Zheng Jianming Wang Zhen Li Carola Schönlieb Tian Xia |
format |
Article |
author |
Xiang Bai Hanchen Wang Liya Ma Yongchao Xu Jiefeng Gan Ziwei Fan Fan Yang Ke Ma Jiehua Yang Song Bai Chang Shu Xinyu Zou Renhao Huang Changzheng Zhang Xiaowu Liu Dandan Tu Chuou Xu Wenqing Zhang Xi Wang Anguo Chen Yu Zeng Dehua Yang Ming Wei Wang Nagaraj Holalkere Neil J. Halin Ihab R. Kamel Jia Wu Xuehua Peng Xiang Wang Jianbo Shao Pattanasak Mongkolwat Jianjun Zhang Weiyang Liu Michael Roberts Zhongzhao Teng Lucian Beer Lorena E. Sanchez Evis Sala Daniel L. Rubin Adrian Weller Joan Lasenby Chuangsheng Zheng Jianming Wang Zhen Li Carola Schönlieb Tian Xia |
author_sort |
Xiang Bai |
title |
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence |
title_short |
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence |
title_full |
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence |
title_fullStr |
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence |
title_full_unstemmed |
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence |
title_sort |
advancing covid-19 diagnosis with privacy-preserving collaboration in artificial intelligence |
publishDate |
2022 |
url |
https://repository.li.mahidol.ac.th/handle/123456789/76625 |
_version_ |
1763495403958829056 |