Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets.

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets.
复制标题

DOI:
10.1109/cvpr52688.2022.01018
复制
发表时间:
2022-06
期刊:
Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition
影响因子:
--
通讯作者:
Singh, Vikas
Singh, Vikas
中科院分区:
其他
文献类型:
--
作者:
Lokhande, Vishnu Suresh;Chakraborty, Rudrasis;Ravi, Sathya N.;Singh, Vikas

文献摘要

参考文献

相似文献

跨机构汇集多个神经成像数据集通常可以在评估关联时提高统计能力(例如,风险因素和疾病结果之间),否则可能太弱而无法检测。当只有一个可变性来源时(例如,不同的扫描器)、域适配和匹配表示的分布在许多情况下可能就足够了。但是,在存在多个干扰变量同时影响测量的情况下,汇集数据集带来了独特的挑战,例如,数据的变化可能来自采集方法以及参与者的人口统计(性别、年龄)。不变表示学习本身不适合完全建模数据生成过程。在本文中,我们将展示如何将最近的结果在结构化空间上实例化的等变表示学习(用于研究神经网络中的对称性)与简单使用因果推理的经典结果一起提供了一个有效的实用解决方案。特别是,我们展示了我们的模型如何允许在某些假设下处理一个以上的滋扰变量,并可以在需要删除大部分样本的情况下分析汇总的科学数据集。我们的代码可在https://github.com/vsingh-group/DatasetPooling上获得
Pooling multiple neuroimaging datasets across institutions often enables improvements in statistical power when evaluating associations (e.g., between risk factors and disease outcomes) that may otherwise be too weak to detect. When there is only a single source of variability (e.g., different scanners), domain adaptation and matching the distributions of representations may suffice in many scenarios. But in the presence of more than one nuisance variable which concurrently influence the measurements, pooling datasets poses unique challenges, e.g., variations in the data can come from both the acquisition method as well as the demographics of participants (gender, age). Invariant representation learning, by itself, is ill-suited to fully model the data generation process. In this paper, we show how bringing recent results on equivariant representation learning (for studying symmetries in neural networks) instantiated on structured spaces together with simple use of classical results on causal inference provides an effective practical solution. In particular, we demonstrate how our model allows dealing with more than one nuisance variable under some assumptions and can enable analysis of pooled scientific datasets in scenarios that would otherwise entail removing a large portion of the samples. Our code is available on https://github.com/vsingh-group/DatasetPooling
DOI: 10.1016/j.neuroimage.2012.01.021
发表时间: 2012-08-15
期刊: NEUROIMAGE
影响因子: 5.7
作者:
Fischl, Bruce
通讯作者: Fischl, Bruce
DOI: 10.1109/iccv.2019.01067
发表时间: 2019-10
期刊: Proceedings. IEEE International Conference on Computer Vision
影响因子: --
作者:
Mehta R;Chakraborty R;Xiong Y;Singh V
通讯作者: Singh V
DOI: 10.1016/j.neurobiolaging.2014.04.034
发表时间: 2015-01-01
影响因子: 4.2
作者:
Eskildsen, Simon F.;Coupe, Pierrick;Collins, D. Louis
通讯作者: Collins, D. Louis
DOI: 10.1073/pnas.1510507113
发表时间: 2016-07-05
影响因子: 11.1
作者:
Bareinboim, Elias;Pearl, Judea
通讯作者: Pearl, Judea
DOI: 10.1016/j.neuroimage.2017.08.047
发表时间: 2017-11-01
期刊: NeuroImage
影响因子: 5.7
作者:
Fortin JP;Parker D;Tunç B;Watanabe T;Elliott MA;Ruparel K;Roalf DR;Satterthwaite TD;Gur RC;Gur RE;Schultz RT;Verma R;Shinohara RT
通讯作者: Shinohara RT