arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.09461cs.AIcs.CR
收藏

通过隐私保护型人工智能协作推进COVID-19诊断

Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence

Tongji Hospital and Medical College, Huazhong University of Science and Technology(华中科技大学同济医院与医学院);Huazhong University of Science and Technology(华中科技大学);University of Cambridge(剑桥大学);Union Hospital of Tongji Medical College, Huazhong University of Science and Technology(华中科技大学同济医学院附属协和医院);CalmCar Inc(CalmCar公司);Wuhan Blood Centre(武汉血液中心);MSA Capital;The National Centre for Drug Screening, Shanghai Institute of Materia Medica, Chinese Academy of Sciences(国家新药筛选中心,中国科学院上海药物研究所);Johns Hopkins Hospital & Medicine Institute(约翰斯·霍普金斯医院与医学研究所);Stanford University(斯坦福大学);Wuhan Central Hospital(武汉中心医院);Wuhan Children's Hospital(武汉儿童医院);Mahidol University(玛希隆大学);University of Texas MD Anderson Cancer Centre(德克萨斯大学MD安德森癌症中心);AstraZeneca(阿斯利康);Alan Turing Institute(艾伦·图灵研究所);Affiliated Tianyou Hospital, Wuhan University of Science and Technology(武汉科技大学附属天佑医院)
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 Zh… 展开作者

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 Escudero Sanchez, Evis Sala, Daniel Rubin, Adrian Weller, Joan Lasenby, Chuangsheng Zheng, Jianming Wang, Zhen Li, Carola-Bibiane Schönlieb, Tian Xia

AI总结:

为解决医疗数据隐私顾虑导致的COVID-19 AI诊断模型训练数据不足问题,本研究发起UCADI倡议,基于联邦学习框架在23家医院分布式训练模型,性能优于本地模型且比肩放射科医生,推动了隐私保护AI在数字健康的应用。

摘要:

人工智能(AI)为简化COVID-19诊断流程提供了极具前景的替代方案。然而,围绕安全性与可信度的担忧阻碍了大规模代表性医疗数据的收集,给训练可在临床实践中良好泛化的模型带来了巨大挑战。为解决这一问题,我们发起了Unified CT-COVID AI Diagnostic Initiative(UCADI,统一CT-COVID人工智能诊断倡议),在该框架下,AI模型可在联邦学习框架(federated learning framework,FL)的支持下,于各宿主机构分布式训练并独立运行,无需共享数据。\n我们的研究表明,该FL模型的表现大幅优于所有本地模型(中国地区测试灵敏度/特异度为0.973/0.951,英国地区为0.730/0.942),性能与一组专业放射科医生相当。我们进一步在留存数据集(从FL参与机构之外的另外两家医院收集)和异质数据集(使用造影剂采集)上评估了模型,为模型决策提供了可视化解释,并分析了联邦训练过程中模型性能与通信成本之间的权衡关系。本研究基于来自中、英两国23家医院的3336名患者的9573份胸部计算机断层扫描影像(CTs)。总体而言,我们的工作提升了将联邦学习用于数字健康领域隐私保护型AI的应用前景。

英文摘要:

Artificial intelligence (AI) provides a promising substitution 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-generalised model in clinical practices. To address this, we launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the AI model can be distributedly trained and independently executed at each host institution under a federated learning framework (FL) without data sharing. Here we show that our FL model outperformed all the local models by a large yield (test sensitivity /specificity in China: 0.973/0.951, in the UK: 0.730/0.942), achieving comparable performance with a panel of professional radiologists. We further evaluated the model on the hold-out (collected from another two hospitals leaving out the FL) 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 (CTs) from 3,336 patients collected from 23 hospitals located in China and the UK. Collectively, our work advanced the prospects of utilising federated learning for privacy-preserving AI in digital health.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑