Deep learning for neuroimaging: a validation study.

Deep learning for neuroimaging: a validation study.
复制标题

DOI:
10.3389/fnins.2014.00229
复制
发表时间:
2014
影响因子:
4.3
通讯作者:
Calhoun VD
Calhoun VD
中科院分区:
医学2区
文献类型:
--
作者:
Plis SM;Hjelm DR;Salakhutdinov R;Allen EA;Bockholt HJ;Long JD;Johnson HJ;Paulsen JS;Turner JA;Calhoun VD

文献摘要

参考文献

被引文献

相似文献

深度学习方法最近在分类和表示学习任务方面取得了显着进展。这些任务对于脑成像和神经科学发现非常重要,使得这些方法对于移植到神经成像工具箱中具有吸引力。这些方法的成功在一定程度上是因为深度学习模型的灵活性。然而,这种灵活性使得移植到新区域的过程成为一个困难的参数优化问题。在这项工作中,我们展示了我们将深度学习方法应用于结构和功能脑成像数据的结果(和可行的参数范围)。这些方法包括深度信念网络和它们的构建块受限玻尔兹曼机。我们还描述了一种新的基于约束的方法来可视化高维数据。我们使用它来分析参数选择对数据转换的影响。我们的研究结果表明,深度学习方法能够学习生理上重要的表示,并检测神经成像数据中的潜在关系。
Deep learning methods have recently made notable advances in the tasks of classification and representation learning. These tasks are important for brain imaging and neuroscience discovery, making the methods attractive for porting to a neuroimager's toolbox. Success of these methods is, in part, explained by the flexibility of deep learning models. However, this flexibility makes the process of porting to new areas a difficult parameter optimization problem. In this work we demonstrate our results (and feasible parameter ranges) in application of deep learning methods to structural and functional brain imaging data. These methods include deep belief networks and their building block the restricted Boltzmann machine. We also describe a novel constraint-based approach to visualizing high dimensional data. We use it to analyze the effect of parameter choices on data transformations. Our results show that deep learning methods are able to learn physiologically important representations and detect latent relations in neuroimaging data.
DOI: 10.1093/cercor/bhs352
发表时间: 2014-03-01
期刊: CEREBRAL CORTEX
影响因子: 3.7
作者:
Allen, Elena A.;Damaraju, Eswar;Calhoun, Vince D.
通讯作者: Calhoun, Vince D.
DOI: 10.1109/tmi.2002.1009383
发表时间: 2002-05-01
影响因子: 10.6
作者:
Freire, L;Roche, A;Mangin, JF
通讯作者: Mangin, JF
DOI: 10.1016/j.ijpsycho.2007.05.016
发表时间: 2008-03-01
影响因子: 3
作者:
Moosmann, Matthias;Eichele, Tom;Calhoun, Vince D.
通讯作者: Calhoun, Vince D.
DOI: 10.1016/j.neuroimage.2014.03.048
发表时间: 2014-08-01
期刊: NeuroImage
影响因子: 5.7
作者:
Hjelm RD;Calhoun VD;Salakhutdinov R;Allen EA;Adali T;Plis SM
通讯作者: Plis SM
DOI: 10.1016/j.schres.2008.02.007
发表时间: 2008-04-01
影响因子: 4.5
作者:
Meda, Shashwath A.;Giuliani, Nicole R.;Pearlson, Godfrey D.
通讯作者: Pearlson, Godfrey D.