Numerical study of resting-state fMRI based on kernel ICA

In order to facilitate the extraction of the default mode network（DMN）, reduce the data complexity of the functional magnetic resonance imaging （fMRI）and overcome the restriction of the linearity of the mixing process encountered with the independent component analysis（ICA）, a framework of dimensionality reduction and nonlinear transformation is proposed. First, the principal component analysis（PCA）is applied to reduce the time dimension 153 594×128 of the fMRI data to 153 594×5 for simplifying complexity computation and obtaining 95% of the information. Secondly, a new kernel-based nonlinear ICA method referred as the kernel ICA（KICA）based on the Gaussian kernel is introduced to analyze the resting-state fMRI data and extract the DMN. Experimental results show that the KICA provides a better performance for the resting-state fMRI data analysis compared with the classical ICA. Furthermore, the DMN is accurately extracted and the noise is reduced.

fMRI盲信号分离中的时间和空间独立成分分析法的时空特性比较

目的采用空间独立成分分析法(sICA)和时间独立成分分析法(tICA)对功能磁共振成像(fMRI)信号进行分离,比较信号间的时空特性对2种独立成分分析方法性能的影响。方法模拟fMRI数据,并将2组独立的信号以及它们的线性混合信号叠加到空间独立的区域,分别利用Infomax、Combi、FBSS和ICA-EMB 4种算法实现sICA和tICA,并对模拟数据中的3组信号进行提取和分离。结果 sICA只能分离空间独立且时间高度独立的信号,无法分离空间相关、时间独立的信号;tICA不仅能够准确分离空间和时间高度独立信号,而且能够准确分离空间高度相关、时间独立的信号,并将时间相关信号整体提取;FBSS和ICA-EMB 2种算法较Infomax和Combi性能稳定。结论空间或时间独立性假设违背到一定程度时,sICA和tICA对信号分离的结果存在差异。应根据需要选择适合的sICA或者tICA方法对fMRI数据进行处理。

一种基于独立成份分析的fMRI时-空模型数据处理方法

独立成份分析(ICA)是信号处理领域中新近发展起来的一种很有应用前景的方法,而脑功能磁共振(fMRI)信号的有效分离与识别是一个正在研究和试验之中的技术领域。因此,发展基于ICA的fMRI数据处理方法具有明显的理论价值和应用前景。本文首先介绍了ICA原理,分析了现行ICA-fMRI方法采用的信号与噪声的空域分布相互独立的信号模型所存在的明显不足,然后提出了微域中的信号与噪声的时域过程相互独立的fMRI信号模型熏从而建立了一种新的fMRI数据处理方法:邻域独立成份相关法。合理的fMRI实验数据处理结果验证了新方法的合理性。

独立成分分析实现成组fMRI数据的信号分离

采用基于row-wise的ICA(独立成分分析)组分析方法,分析了相同任务下采集的一组fMRI数据。结果表明:该方法可以较好地提取出所有被试者中具有共同时间序列的信号。

基于DIVA模型的脑电信号处理方法研究

DIVA(Directions Into of Articulators)模型是一种为了生成单词、音节或者音素而控制模拟声道运动的自适应神经网络模型,其依赖的输入信号是从人体大脑中采集到的脑电信号。针对汉语神经分析系统研究中非侵入式脑机接口采集到的脑电数据存在的分辨率低、干扰大的问题,文中提出一种基于DIVA模型对脑电信号进行约束处理的方法。首先利用独立分量分析方法剔除原始信号中的噪声,提取有效事件相关电位(Event-Related Potentials,ERP)成分;然后以模拟生成的功能性磁共振成像(functional Magnetic Resonance Imaging,fMRI)数据的激活点的空间信息作为限制条件,对提取出的ERP成分进行精确定位。通过对实验数据进行分析处理并模拟受试者的激活脑区,验证了所提方法的正确性和有效性。

脑图像数据中的独立分量分析方法

针对脑功能磁共振成像在处理数据时空间维数较大的问题,提出一种空间独立分量分析(ICA)方法。研究空间ICA方法的基本模型结构和空间ICA的3种常见算法,即Infomax算法、Fixed-Point算法和Orth-Infomax算法。设计中文词义辨别实验,并使用线性相关方法进行算法比较。实验结果表明,与Infomax算法、Fixed-Point算法相比,Orth-Infomax算法任务相关分量的时间序列与参考函数的平均相关系数最大,具有较高的求解质量和求解效率,能够有效处理脑功能磁共振成像系统中存在的大量数据。

Discrimination for minimal hepatic encephalopathy based on Bayesian modeling of default mode network

In order to classify the minimal hepatic encephalopathy （MHE） patients from healthy controls, the independent component analysis （ICA） is used to generate the default mode network （DMN） from resting-state functional magnetic resonance imaging （fMRI）. Then a Bayesian voxel- wised method, graphical-model-based multivariate analysis （GAMMA）, is used to explore the associations between abnormal functional integration within DMN and clinical variable. Without any prior knowledge, five machine learning methods, namely, support vector machines （SVMs）, classification and regression trees （ CART ）, logistic regression, the Bayesian network, and C4.5, are applied to the classification. The functional integration patterns were alternative within DMN, which have the power to predict MHE with an accuracy of 98%. The GAMMA method generating functional integration patterns within DMN can become a simple, objective, and common imaging biomarker for detecting MIIE and can serve as a supplement to the existing diagnostic methods.

基于凸优化的脑图像数据盲信号分离算法

在实际脑图像分析中,独立成分分析方法的独立性假设很难完全满足。为此,结合脑图像数据的特点,以凸优化为基础,提出利用源分量稀疏性和非负性的脑图像盲信号分离算法。相比于独立性假设,稀疏性和非负性数学假设更符合f MRI数据的自然特性。将源分量的估计过程转化为寻找由观测数据构成的凸集合端点的过程。实验结果证明,由该算法选择出的激活体素与实验任务更相关,更容易进行生理解释。

首发抑郁患者大脑注意网络的多模态影像学研究

本研究利用多模态影像学方法研究抑郁(major depressive disorder, MDD)患者在腹侧和背侧注意网络上的结构和功能改变。本研究分别对64名首发MDD患者和32名年龄、性别和教育程度与之匹配的健康对照组的多模态MRI指标进行了组间比较,包括静息状态功能磁共振成像中的低频波动分数振幅(low frequency fluctuation fraction amplitude, fALFF)和区域均匀性(regional homogeneity,ReHo)以及sMRI中的灰质体积,探索差异区域与临床量表的相关性,并进行受试者工作特征曲线分析。结果显示,首发抑郁患者在注意网络上无显著的结构差异,但右内侧额上回、左侧顶上回和辅助运动区有显著的功能差异。此外,右内侧额上回的局部一致性值与汉密尔顿评分存在显著的正相关,受试者工作特征曲线的线下面积表明,其对抑郁症具有较好的诊断识别能力。本研究加深了对抑郁患者注意网络改变的认识,可为抑郁症的早期诊断及干预治疗提供新途径。

基于功能磁共振成像(fMRI)的脑功能逻辑任务功能区BOLD信号研究

利用功能磁共振成像(fMRI)进行脑功能研究是目前的一个热点,本文以逻辑计算为认知任务,利用fMRI进行数据采集,通过SPM软件分析得到激活脑区,提取感兴趣区(Regions of interest,ROI)的平均BOLD信号(Average-BOLD),并利用主成分分析(Principal component analysis,PCA)方法提取ROI内BOLD信号(PCA-BOLD),通过Average-BOLD、PCA-BOLD信号与实验设计的逻辑任务曲线进行比较,认为PCA-BOLD信号可以更好的作为fMRI激活脑区的定量评估指标,用来衡量ROI激活强度,并进行脑功能基础研究。

A new method for fMRI data processing: Neighborhood independent component correlation algorithm and its preliminary application

Independent component analysis (ICA) is a newly developed promising technique in signal processing applications. The effective separation and discrimination of functional Magnetic Resonance Imaging (fMRI) signals is an area of active research and widespread interest. Therefore, the development of an ICA based fMRI data processing method is of obvious value both theoretically and in potential applications. In this paper, analyzed firstly is the drawback of the extant popular ICA-fMRI method where the adopted signal model assumes the independence of spatial distributions of the signals and noise. Then presented is a new fMRI signal model, which assumes the independence of temporal courses of signal and noise in a tiny spatial domain. Consequently we get a novel fMRI data processing method: Neighborhood independent component correlation algorithm. The effectiveness is elucidated through theoretical analysis and simulation tests, and finally a real fMRI data test is presented.

Segregation between the parietal memory network and the default mode network： effects of spatial smoothing and model order in ICA

Abstract A brain network consisting of two key parietal nodes, the precuneus and the posterior cingulate cortex, has emerged from recent fMRI studies. Though it is anatomically adjacent to and spatially overlaps with the default mode network （DMN）, its function has been associated with memory processing, and it has been referred to as the parietal memory network （PMN）. Independent component analysis （ICA） is the most common data-driven method used to extract PMN and DMN simultaneously. However, the effects of data preprocessing and parameter determi- nation in ICA on PMN-DMN segregation are completely unknown. Here, we employ three typical algorithms of group ICA to assess how spatial smoothing and model order influence the degree of PMN-DMN segregation. Our findings indicate that PMN and DMN can only be stably separated using a combination of low-level spatial smoothing and high model order across the three ICA algorithms. We thus argue for more considerations on parametric settings for interpreting DMN data.