Mitigating site effects in covariance for machine learning in neuroimaging data.
Mitigating site effects in covariance for machine learning in neuroimaging data.
复制标题
DOI：
10.1002/hbm.25688
复制
发表时间：
2022-03
影响因子：
4.8
通讯作者：
Alzheimer's Disease Neuroimaging Initiative
中科院分区：
文献类型：
--
作者：
Chen AA;Beer JC;Tustison NJ;Cook PA;Shinohara RT;Shou H;Alzheimer's Disease Neuroimaging Initiative
为了获得更大的样本来回答神经科学中的复杂问题，研究人员越来越多地转向多部位神经影像学研究。然而，这些研究受到跨多个站点获取的图像差异的阻碍。这些效应已被证明会使位点之间的比较产生偏差，掩盖生物学上有意义的关联，甚至引入虚假的关联。为了解决这个问题，该领域一直专注于通过消除测量均值和方差中与站点相关的影响来协调数据。随着多中心成像的普及，机器学习（ML）在神经成像中的使用也变得越来越普遍。这些方法已被证明提供了改进的灵敏度、特异性和功效，这是由于它们对大脑中测量结果之间的联合关系进行了建模。在这项工作中，我们证明了去除站点的平均值和方差的影响的方法可能是不够的ML。这源于这样一个事实，即这种方法未能解决测量之间的相关性如何在不同地点之间变化。来自阿尔茨海默病神经影像学倡议的数据显示，不同地点之间存在相当大的协方差差异，流行的协调技术并不能解决这个问题。然后，我们提出了一种名为“纠正协方差批量效应”（CovBat）的新型协调方法，该方法消除了均值、方差和协方差中的地点效应。我们应用CovBat，并表明中心内相关矩阵成功协调。此外，我们发现ML方法在应用我们提出的协调后无法区分扫描仪制造商，并且CovBat协调的数据保留了对疾病组的准确预测。多部位神经影像学研究受到多个部位采集的图像差异的阻碍，通常称为部位效应。在这项工作中，我们证明了在均值和方差中消除站点效应的方法可能不足以用于机器学习。在应用我们提出的协调方法CovBat后，我们发现机器学习方法在应用我们提出的协调后无法区分扫描仪制造商，并且CovBat协调的数据保留了对疾病组的准确预测。
To acquire larger samples for answering complex questions in neuroscience, researchers have increasingly turned to multi‐site neuroimaging studies. However, these studies are hindered by differences in images acquired across multiple sites. These effects have been shown to bias comparison between sites, mask biologically meaningful associations, and even introduce spurious associations. To address this, the field has focused on harmonizing data by removing site‐related effects in the mean and variance of measurements. Contemporaneously with the increase in popularity of multi‐center imaging, the use of machine learning (ML) in neuroimaging has also become commonplace. These approaches have been shown to provide improved sensitivity, specificity, and power due to their modeling the joint relationship across measurements in the brain. In this work, we demonstrate that methods for removing site effects in mean and variance may not be sufficient for ML. This stems from the fact that such methods fail to address how correlations between measurements can vary across sites. Data from the Alzheimer's Disease Neuroimaging Initiative is used to show that considerable differences in covariance exist across sites and that popular harmonization techniques do not address this issue. We then propose a novel harmonization method called Correcting Covariance Batch Effects (CovBat) that removes site effects in mean, variance, and covariance. We apply CovBat and show that within‐site correlation matrices are successfully harmonized. Furthermore, we find that ML methods are unable to distinguish scanner manufacturer after our proposed harmonization is applied, and that the CovBat‐harmonized data retain accurate prediction of disease group. Multi‐site neuroimaging studies are hindered by differences in images acquired across multiple sites, often referred to as site effects. In this work, we demonstrate that methods for removing site effects in mean and variance may not be sufficient for machine learning. After applying our proposed harmonization method CovBat, we find that machine learning methods are unable to distinguish scanner manufacturer after our proposed harmonization is applied, and that the CovBat‐harmonized data retain accurate prediction of disease group.
登录
查看更多内容
影响因子：
4.3
作者：
Klein A;Tourville J
通讯作者：
Tourville J
影响因子：
5.7
作者：
Kruggel, Frithjof;Turner, Jessica;Muftuler, L. Tugan
通讯作者：
Muftuler, L. Tugan
影响因子：
6.6
作者：
Koutsouleris, Nikolaos;Davatzikos, Christos;Meisenzahl, Eva
通讯作者：
Meisenzahl, Eva
影响因子：
2.2
作者：
Gregorutti, Baptiste;Michel, Bertrand;Saint-Pierre, Philippe
通讯作者：
Saint-Pierre, Philippe
影响因子：
10.6
作者：
Gao, Yuan;Liu, Yingchao;Yu, Jinhua
通讯作者：
Yu, Jinhua