Bayesian reconstruction of multiscale local contrast images from brain activity
Bayesian reconstruction of multiscale local contrast images from brain activity
复制标题
大脑活动的多尺度局部对比图像的贝叶斯重建
DOI：
10.1016/j.jneumeth.2013.08.020
复制
发表时间：
2013-10
影响因子：
3
通讯作者：
Zhang Jiacai
中科院分区：
文献类型：
--
作者：
Song Sutao;Ma Xinyue;Zhan Yu;Zhan Zhichao;Yao Li;Zhang Jiacai
背景功能磁共振成像（fMRI）技术的最新进展使得从大脑活动重建对比度定义的视觉图像成为可能。以这种方式，刺激图像被表示为具有不同尺度的一组元素图像的加权和。使用受试者观看刺激图像时记录的功能磁共振成像活动来解码局部图像的对比度权重。多变量方法，例如稀疏多项逻辑回归模型 (SMLR)，已被证明对于学习初级视觉皮层体素的 fMRI 模式与刺激图像对比度之间的映射是有效的。然而SMLR方法在实际应用中非常耗时。新方法提出了基于独立成分分析的朴素贝叶斯分类器(NB-ICA)来高效解码多尺度局部图像的对比度。首先，通过 ICA 分解获得 fMRI 数据的时间独立分量，将其视为 NB 分类器的新特征。其次，基于NB估计理论计算每个局部元素图像的对比度。结果NB-ICA方法可用于重建新的视觉图像。表示图像和重建图像之间的平均空间相关性为 0.41 ± 0.13 (p< 0.001)。与现有方法相比，以重建精度为代价，NB-ICA 比 SMLR 更有效，将计算时间从几小时缩短到几秒。结论 提出了一种称为 NB-ICA 的新方法，可以有效地从 fMRI 数据重建对比度定义的视觉图像。该研究为脑机接口研究提供理论支持，也为实时fMRI数据的研究提供思路。
BackgroundRecent advances in functional magnetic resonance imaging (fMRI) techniques make it possible to reconstruct contrast-defined visual images from brain activity. In this manner, the stimulus images are represented as the weighted sum of a set of element images with different scales. The contrast weight of local images were decoded using fMRI activity recorded when the subject was viewing the stimulus images. Multivariate methods, such as the sparse multinomial logistic regression model (SMLR), have been proven effective for learning the mapping between fMRI patterns of primary visual cortex voxels and contrast of stimulus images. However, the SMLR method is highly time-consuming in practical application.New methodThe Naive Bayesian classifier based on independent component analysis (NB-ICA) is proposed to efficiently decode the contrast of multi-scale local images. First, temporal independent components of fMRI data which were treated as new features for NB classifier were acquired by ICA decomposition. Second, the contrast for each local element image was computed based on NB estimation theory.ResultsNB-ICA method can be used to reconstruct novel visual images. The average spatial correlation between the represented and reconstructed images was 0.41 ± 0.13 (p< 0.001).Comparison with existing method(s)At the expense of reconstruction accuracy, NB-ICA is more efficient than SMLR which reduces the computation time from hours to seconds.ConclusionsA new method, termed NB-ICA, is proposed and can efficiently reconstruct contrast-defined visual images from fMRI data. This study provides theoretical support for brain-computer interface research and also provides ideas for the study of real-time fMRI data.
登录
查看更多内容
影响因子：
6.1
作者：
Martínez-Murcia FJ;Górriz JM;Ramírez J;Puntonet CG;Illán IA;Alzheimer's Disease Neuroimaging Initiative
通讯作者：
Alzheimer's Disease Neuroimaging Initiative
影响因子：
9.2
作者：
Nishimoto, Shinji;Vu, An T.;Naselaris, Thomas;Benjamini, Yuval;Yu, Bin;Gallant, Jack L.
通讯作者：
Gallant, Jack L.
影响因子：
9.2
作者：
Kamitani, Yukiyasu;Tong, Frank
通讯作者：
Tong, Frank
DOI：
10.1007/978-3-540-92910-9_13
发表时间：
2012
期刊：
--
影响因子：
--
作者：
Seungjin Choi
通讯作者：
Seungjin Choi
影响因子：
4.8
作者：
Esposito, F;Formisano, E;Di Salle, F
通讯作者：
Di Salle, F