Privacy-preserving quality control of neuroimaging datasets in federated environments.
Privacy-preserving quality control of neuroimaging datasets in federated environments.
复制标题
DOI：
10.1002/hbm.25788
复制
发表时间：
2022-05
影响因子：
4.8
通讯作者：
Plis SM
中科院分区：
文献类型：
--
作者：
Saha DK;Calhoun VD;Du Y;Fu Z;Kwon SM;Sarwate AD;Panta SR;Plis SM
罕见病数据的隐私问题、机构或IRB政策、访问本地计算或存储资源或下载能力是可能排除将数据汇集到单个研究中心进行分析的原因之一。越来越多的多地点项目和联盟被组建起来，在这种约束下，在联邦环境中开展生产性研究。在这种情况下，通过本地计算的全局聚合将分散数据整体可视化的质量控制工具尤为重要，因为它可以筛选无法以其他方式联合评估的样本。为了解决这个问题，我们提出了两种算法：分散数据随机邻居嵌入，dSNE，以及它的差分私有对应，DP‐dSNE。我们利用公开的数据集，同时映射数据样本位于不同的网站，根据其相似性。即使数据从未离开过各个网站，dSNE也不提供任何正式的隐私保证。为了克服这一点，我们依靠差分隐私：一种正式的数学保证，可以保护个人不被识别为数据集的贡献者。我们使用AdaCliP实现DP‐dSNE，AdaCliP是最近提出的一种方法，用于在每次迭代中向梯度添加更少的噪声。我们引入度量嵌入质量的指标，并验证我们的算法对这些指标对他们的集中对应的两个玩具数据集。我们对六个多站点神经成像数据集的验证显示了可视化和离群值检测的质量控制任务的有希望的结果，突出了我们的私有，分散的可视化方法的潜力。罕见病数据的隐私问题、机构或IRB政策、访问本地计算或存储资源或下载能力是可能排除将数据汇集到单个研究中心进行分析的原因之一。越来越多的多站点项目和联盟在联邦环境中运作，在这种限制下进行生产性研究。在这种情况下，通过本地计算的全局聚合将分散数据整体可视化的质量控制工具尤为重要，因为它可以筛选无法以其他方式联合评估的样本。为了解决这个问题，我们提出了两种算法：分散数据随机邻居嵌入，dSNE，以及它的差分私有对应，DP‐dSNE。我们对六个多站点神经成像数据集的验证显示了可视化和离群值检测的质量控制任务的有希望的结果，突出了我们的私有，分散的可视化方法的潜力。
Privacy concerns for rare disease data, institutional or IRB policies, access to local computational or storage resources or download capabilities are among the reasons that may preclude analyses that pool data to a single site. A growing number of multisite projects and consortia were formed to function in the federated environment to conduct productive research under constraints of this kind. In this scenario, a quality control tool that visualizes decentralized data in its entirety via global aggregation of local computations is especially important, as it would allow the screening of samples that cannot be jointly evaluated otherwise. To solve this issue, we present two algorithms: decentralized data stochastic neighbor embedding, dSNE, and its differentially private counterpart, DP‐dSNE. We leverage publicly available datasets to simultaneously map data samples located at different sites according to their similarities. Even though the data never leaves the individual sites, dSNE does not provide any formal privacy guarantees. To overcome that, we rely on differential privacy: a formal mathematical guarantee that protects individuals from being identified as contributors to a dataset. We implement DP‐dSNE with AdaCliP, a method recently proposed to add less noise to the gradients per iteration. We introduce metrics for measuring the embedding quality and validate our algorithms on these metrics against their centralized counterpart on two toy datasets. Our validation on six multisite neuroimaging datasets shows promising results for the quality control tasks of visualization and outlier detection, highlighting the potential of our private, decentralized visualization approach. Privacy concerns for rare disease data, institutional or IRB policies, access to local computational or storage resources or download capabilities are among the reasons that may preclude analyses that pool data to a single site. A growing number of multi‐site projects and consortia were formed to function in the federated environment to conduct productive research under constraints of this kind. In this scenario, a quality control tool that visualizes decentralized data in its entirety via global aggregation of local computations is especially important, as it would allow the screening of samples that cannot be jointly evaluated otherwise. To solve this issue, we present two algorithms: decentralized data stochastic neighbor embedding, dSNE, and its differentially private counterpart, DP‐dSNE. Our validation on six multisite neuroimaging datasets shows promising results for the quality control tasks of visualization and outlier detection, highlighting the potential of our private, decentralized visualization approach.
登录
查看更多内容
影响因子：
11
作者：
Di Martino, A.;Yan, C-G;Li, Q.;Denio, E.;Castellanos, F. X.;Alaerts, K.;Anderson, J. S.;Assaf, M.;Bookheimer, S. Y.;Dapretto, M.;Deen, B.;Delmonte, S.;Dinstein, I.;Ertl-Wagner, B.;Fair, D. A.;Gallagher, L.;Kennedy, D. P.;Keown, C. L.;Keysers, C.;Lainhart, J. E.;Lord, C.;Luna, B.;Menon, V.;Minshew, N. J.;Monk, C. S.;Mueller, S.;Mueller, R. A.;Nebel, M. B.;Nigg, J. T.;O'Hearn, K.;Pelphrey, K. A.;Peltier, S. J.;Rudie, J. D.;Sunaert, S.;Thioux, M.;Tyszka, J. M.;Uddin, L. Q.;Verhoeven, J. S.;Wenderoth, N.;Wiggins, J. L.;Mostofsky, S. H.;Milham, M. P.
通讯作者：
Milham, M. P.
影响因子：
4.8
作者：
Fu, Zening;Caprihan, Arvind;Calhoun, Vince D.
通讯作者：
Calhoun, Vince D.
影响因子：
7.7
作者：
Carter KW;Francis RW;Carter KW;Francis RW;Bresnahan M;Gissler M;Grønborg TK;Gross R;Gunnes N;Hammond G;Hornig M;Hultman CM;Huttunen J;Langridge A;Leonard H;Newman S;Parner ET;Petersson G;Reichenberg A;Sandin S;Schendel DE;Schalkwyk L;Sourander A;Steadman C;Stoltenberg C;Suominen A;Surén P;Susser E;Sylvester Vethanayagam A;Yusof Z;International Collaboration for Autism Registry Epidemiology
通讯作者：
International Collaboration for Autism Registry Epidemiology
影响因子：
--
作者：
Halchenko, Yaroslav O;Meyer, Kyle;Hanke, Michael
通讯作者：
Hanke, Michael
影响因子：
46.9
作者：
通讯作者：
--