小波域功能磁共振图像的处理和功能区的检测

传统的Gaussian变换不能够很好地去除功能磁共振图像当中的相关性噪声,影响对功能区的检测结果.为了更准确地检测和定位功能区,提出了基于小波变换的方法对功能磁共振图像进行处理.首先采用非线性小波变换阈值法在小波域对功能磁共振图像进行降噪处理;然后结合小波域的错误发现率算法对脑激活区进行检验.多套数据的统计结果表明,与传统的Gaussian变换相比,文中方法在保持检出敏感性的同时减少检测结果中假阳性点的数量,具有较高的检出特异性和定位可靠性.     

基于受限玻尔兹曼机的脑功能连通性检测方法

为解决受限玻尔兹曼机(RBM)在功能磁共振成像(fMRI)脑功能连通性检测中遇到的体素数量过多和模型参数难以选择的问题,提出一种结合主成分分析(PCA)和Bootstrap区间估计的受限玻尔兹曼机方法,选出fMRI数据中的部分体素,从而削减体素数量。以经体素削减处理后剩余体素的时间过程作为样本,采用改进的学习算法训练RBM,根据模型权重参数重建脑功能网络空间图谱。实验结果表明,在单被试fMRI脑功能联通性检测中,基于RBM的方法在空间域和时间域中的分析结果明显优于稀疏近似联合受限玻尔兹曼机方法。基于RBM的方法和Infomax ICA方法的空间域ROC曲线非常接近,但前者在时间域上的时间过程与实验刺激BLOCK的相关性更高。实验结果表明,基于RBM的方法能够有效地降低样本中的体素数量和模型参数选择的复杂度,提高RBM在fMRI数据分析中的性能。     

空间机器人动力学参数在轨辨识方法

针对机器人动力学参数识别问题,提出了基于有限遥测信息的空间机器人动力学参数在轨辨识方法.首先深入分析了各动力学参数对系统角动量的影响程度,并进行了参数重组,然后依据空间机器人系统的角动量守恒原理,推导了动力学参数与系统角动量之间的映射关系,最后,利用Gauss-Seidel迭代方法获得辨识结果.仿真表明,该方法能够快速地辨识出相关的动力学参数,方法利用遥测获得的飞行数据不需要额外的测量设备或者操作程序,为空间机器人动力学参数在轨实时辨识提供了理论方法.     

面向骨骼受损类型判别的体素模板构建

针对骨骼受损类型判断较为困难的问题,提出一种面向骨骼受损类型判别的体素模板构建方法,旨在指导医生进行快速判断。首先,在骨骼平均化点云模型的基础上构建最小包围盒,根据空间分辨率对包围盒进行划分,遍历判断后生成体素骨骼模板;然后,建立受损类型与体素模板之间的对应信息,生成受损类型库;最后,将目标骨骼映射到模板上,根据映射后模板上的受损体素区域指导医生判断出受损类型。实验结果表明,该方法能辅助医生直观、快速地判断目标骨骼受损类型,有利于后期面向目标骨骼进行自动判别研究。     

基于拉普拉斯特征映射的传递函数设计方法

为降低体绘制中传递函数参数选择的盲目性和设计的复杂性,提出一种基于拉普拉斯特征映射的传递函数设计方法.提取体数据中各种特征信息构建高维传递函数参数空间,通过拉普拉斯特征映射将其映射到保持了体数据局部流形结构和高维参数空间分类能力的二维参数空间,在此嵌入空间上设计一种基于k-means聚类的传递函数,得到了较好的体数据分类和绘制结果.通过在一组体数据上的实验验证了该方法的有效性.     

基于神经网络和体素模板的骨骼受损类型判别

针对骨骼受损类型复杂多样、难以自动判别的问题,提出一种基于神经网络和体素模板的骨骼受损类型自动判别方法.首先构建一种区域分割且规则化的体素模板,以有效地表征形态结构不规则的骨骼受损区域;然后建立一种受损骨骼与体素模板之间的同构映射,用于提取受损区域的体素信息,并依此生成受损类型体素样本库;再结合医学先验知识定义一种受损区域体素间的约束关系,将连续受损区域作为单元,对同类型样本进行组合以扩充样本库;最后设计和训练神经网络模型对骨骼的受损类型进行自动判别.实验中采集352份股骨受损样本,其预测结果与骨科医师的临床诊断结论相比,准确率达97％,且分类准确率、时间性能和所识别的受损类型数目优于现有文献方法,结果表明,该方法能够辅助医生快速、有效地判断患者骨骼的受损类型,为骨折手术中内固定植入物的选取提供理论基础.     

GPU并行计算加速的实时可视外壳三维重建及其虚实交互

针对现有的基于图像的三维重建方法难以实现真实物体的快速三维重建,无法满足虚实交互等应用需求的问题,提出一种基于GPU并行计算的实时三维重建及其虚实交互方法.首先把物体所在空间剖分成具有数据独立性的体素集合,结合可视外壳重建算法和精确行进立方体算法并行遍历每个体素得到体素状态序列;然后并行压缩体素状态序列得到非空体素集合,对非空体素进行并行三角形网格化,并利用图形硬件的多重纹理映射和可编程功能进行基于像素的纹理映射;最后假定虚拟物体的粒子为运动受限的拉格朗日流体粒子,重建物体网格顶点为流体边界,通过流体动力学方程的并行光滑粒子动力学方法求解来计算虚实交互.实验结果表明,该方法在GPU上进行完全并行求解,在32×32×32的空间剖分精度下,实现了实时三维重建和20帧/s左右的虚实交互计算,适用于计算机图形学和虚拟现实等领域中的虚实交互应用.     

彩色体三维显示系统上基于GPU的实时均匀体素化算法

为了使基于旋转屏的彩色体三维显示设备在显示动态场景时实时且高分辨率、高质量地实现圆柱体空间彩色体素化,提出了一种基于GPU的算法.首先在长方体空间内完成对三维场景的实时彩色体素化,将生成的数据保存于多张纹理工作表中;然后采取多对多映射的方法对这些工作表进行重采样,得到该场景在圆柱体空间内均匀的彩色体素化结果.实验结果表明,该算法在GPU内完成,达到了实时性要求,并在基于LED旋转屏的体三维显示设备上获得了令人满意的三维虚拟场景再现效果.     

不确定脑网络的异常拓扑分析及分类研究

静息态功能脑网络在脑疾病研究中得到了广泛的应用。然而传统的功能连接网络分析主要集中在确定图上,忽视了大脑区域之间的不确定信息。基于此,对不确定脑网络进行了研究,该方法不需要进行阈值选择,而且可以更准确地对功能连接网络进行建模。同时,将频繁子图挖掘应用到了不确定图上,并提出了几种新的判别性特征选择方法。分类结果显示,基于不确定脑网络的磁共振影像分类方法有效地提高了抑郁症诊断的准确率。     

基于显著性背景引导的弱监督语义分割网络

目前基于图像级标注的弱监督语义分割方法大多依赖类激活初始响应以定位分割对象区域.然而,类激活响应图通常只集中在对象最具辨别性的区域,存在目标区域范围较小、边界模糊等缺点,导致最终分割区域不完整.针对此问题,文中提出基于显著性背景引导的弱监督语义分割网络.首先通过图像显著性映射和背景迭代产生背景种子区域.然后将其与分类网络生成的类激活映射图融合,获取有效的伪像素标签,用于训练语义分割模型.分割过程不再完全依赖最具判别性的类激活区域,而是通过图像显著性背景特征与类激活响应信息相互补充,这样可提供更精确的像素标签,提升分割网络的性能.在PASCAL VOC 2012数据集上的实验验证文中方法的有效性,同时分割性能较优.     

Identifying distributed and overlapping clusters of hemodynamic synchrony in fMRI data sets

Natural sensory stimuli elicit complex brain responses that manifest in fMRI as widely distributed and overlapping clusters of hemodynamic responses. We propose a statistical signal processing method for finding synchronous hemodynamic activity that directly or transiently reflects information about the experimental condition. When applied to fMRI data, the method searches for voxels with activation patterns exhibiting high coherence and simultaneously high variance across brain scans. The crux of the method is functional principal component analysis (fPCA) of activation patterns stored in a two-dimensional data matrix, with rows and columns representing voxels and scans, respectively. Without external information, fPCA is performed directly on this data matrix. Otherwise, the data matrix is first transformed to highlight a specific source of variation, enabling fully or partially supervised fPCA with a single parameter determining the degree of supervision. We evaluated our method on a public benchmark of fMRI scans of subjects viewing natural movies. Our method turns out to be very suitable for flexibly uncovering distributed and overlapping hemodynamic patterns that distinguish well between experimental conditions or cognitive states.     

基于多级CBF的长流识别

针对高速网络流量难测量的问题及长流占网络流量大部分的特点,提出一种基于多级CBF的长流识别算法,对报文进行抽样,将抽取的报文通过经过一系列哈希映射到长流信息表中,查找是否存在该流信息,若存在则更新流信息,若不存在则将该报文用多级CBF结构对流信息进行过滤,报文数达到阈值的流被识别为长流,并在长流信息表中创建和维护该长流的信息.该算法在很大程度上减少了短流因为哈希冲突而被误判为长流的概率,降低了资源开销,对指定报文数为阈值的长流识别具有很好的扩展性.     

A Bayesian multilevel model for fMRI data analysis

Bayesian approaches have been proposed by several functional magnetic resonance imaging (fMRI) researchers in order to overcome the fundamental limitations of the popular statistical parametric mapping method. However, the difficulties associated with subjective prior elicitation have prevented the widespread adoption of the Bayesian methodology by the neuroimaging community. In this paper, we present a Bayesian multilevel model for the analysis of brain fMRI data. The main idea is to consider that all the estimated group effects (fMRI activation patterns) are exchangeable. This means that all the collected voxel time series are considered manifestations of a few common underlying phenomena. In contradistinction to other Bayesian approaches, we think of the estimated activations as multivariate random draws from the same distribution without imposing specific prior spatial and/or temporal information for the interaction between voxels. Instead, a two-stage empirical Bayes prior approach is used to relate voxel regression equations through correlations between the regression coefficient vectors. The adaptive shrinkage properties of the Bayesian multilevel methodology are exploited to deal with spatial variations, and noise outliers. The characteristics of the proposed model are evaluated by considering its application to two real data sets.     

基于小波变换的功能磁共振图像时间序列分步去噪

功能磁共振图像（fMRI）数据中反映大脑神经活动的感兴趣信号常受到结构噪声和随机噪声的影响。为消除上述噪声对分析激活体素的影响,对经过SPM标准预处理的体素时间序列进行Activelets小波变换,并在得到尺度系数及细节系数后,针对两类噪声的不同特点进行分步去噪。第一步,在受结构噪声影响的尺度系数上,选用独立成分分（ICA）析去识别并消除结构噪声源;第二步,提出一种改进的空域相关去噪算法在细节系数上对信号进行处理。值得注意的是,该算法利用邻域体素之间的相似性,判定所处位置的细节系数反映噪声还是神经活动。实验结果表明,经过这两步处理的数据可有效消除噪声的影响,其中框架位移减少了1.5mm,尖峰百分比减少了2%,此外由去噪后的信号获得的脑激活图中一些明显的伪激活区得到抑制。     

Phase Ambiguity Correction and Visualization Techniques for Complex-Valued ICA of Group fMRI Data

Analysis of functional magnetic resonance imaging (fMRI) data in its native, complex form has been shown to increase the sensitivity both for data-driven techniques, such as independent component analysis (ICA), and for model-driven techniques. The promise of an increase in sensitivity and specificity in clinical studies, provides a powerful motivation for utilizing both the phase and magnitude data; however, the unknown and noisy nature of the phase poses a challenge. In addition, many complex-valued analysis algorithms, such as ICA, suffer from an inherent phase ambiguity, which introduces additional difficulty for group analysis. We present solutions for these issues, which have been among the main reasons phase information has been traditionally discarded, and show their effectiveness when used as part of a complex-valued group ICA algorithm application. The methods we present thus allow the development of new fully complex data-driven and semi-blind methods to process, analyze, and visualize fMRI data.We first introduce a phase ambiguity correction scheme that can be either applied subsequent to ICA of fMRI data or can be incorporated into the ICA algorithm in the form of prior information to eliminate the need for further processing for phase correction. We also present a Mahalanobis distance-based thresholding method, which incorporates both magnitude and phase information into a single threshold, that can be used to increase the sensitivity in the identification of voxels of interest. This method shows particular promise for identifying voxels with significant susceptibility changes but that are located in low magnitude (i.e. activation) areas. We demonstrate the performance gain of the introduced methods on actual fMRI data.     

Power spectral based detection of brain activation from fMR images

An efficient method for detecting activation on single and multiple epoch functional MRI (fMRI) data based on power spectral density of time-series and hidden Markov model is presented. Conventional methods of analysis of fMRI data are generally based on time-domain correlation analysis concentrating mainly on the multiple epoch data and generally do not provide good results for single epoch data. The main focus of this study is the analysis of single epoch data, constrained by certain experiments such as pain response, sleep, administration of pharmacological agents, which can only have a single or very few stimulus cycles. Further, our method obviates the need to exclusively model the hemodynamic response function and correctly identifies the voxels with delayed activation. We demonstrate the efficacy of our method in detecting brain activation by using both synthetic and real fMRI data.     

Two dimensional CCA via penalized matrix decomposition for structure preserved fMRI data analysis

Two dimensional canonical correlation analysis (2DCCA) is a data driven method that has been used to preserve the local spatial structure of functional magnetic resonance (fMR) images and to detect brain activation patterns. 2DCCA finds pairs of left and right linear transforms by directly operating on two dimensional data (i.e., image data) such that the correlation between their projections is maximized without neglecting the local spatial structure of the data. However, in the context of high dimensional data, the performance of 2DCCA suffers from interpretability of learned projection variables. In this study, to improve the interpretability of projection variables while preserving the local spatial structure of fMR images, we propose two new 2DCCA approaches, sparse 2DCCA and regularized 2DCCA. The proposed algorithms aim at improving the activation detection performance in terms of specificity of activated voxels by directly operating on image data without rearranging fMRI slices in 1D-vectors. The validity of the proposed algorithms has been evaluated on synthetic and real fMRI datasets and it has been shown that the proposed algorithms produce activation maps with higher specificity of activated voxels compared with CCA, 2DCCA, and existing sparse 2DCCA (S2DCCA).     

Using competitive layer model implemented by Lotka–Volterra recurrent neural networks for detecting brain activated regions from fMRI data

The competitive layer model (CLM) implemented by the Lotka–Volterra recurrent neural networks (LV RNNs) is prominently characterized by its capability of binding neurons with similar feature into the same layer by competing among neurons at different layers in a column. This paper proposes to use the CLM of the LV RNN for detecting brain activated regions from the fMRI data. The correlated voxels from brain fMRI data can be obtained, and the clusters from fMRI time series can be uncovered. Experiments on synthetic and real fMRI data demonstrate the effectiveness of binding activated voxels into the ‘active’ layers of the CLM. The activated voxels can be detected more accurately than some existing methods by the proposed method.

     

Multivoxel analysis for functional magnetic resonance imaging (fMRI) based on time-series and contextual information: relationship between maternal love and brain regions as a case study

This study explores the relationship between maternal love and brain regions by using functional magnetic resonance imaging (fMRI). Also, a novel pattern analysis for fMRI based on the discovered brain regions is proposed in this work. Firstly, to identify which region responds to stimuli, a statistical t-test is used after the scan. Based on these preliminary regions of interest, this study develops discriminant features extracted from multivoxels for cognitive modeling. In total, five parameters are used in the time-series and contextual analysis, including the proposed blood-oxygen-level-dependent (BOLD) contrast edge, BOLD contrast centroid, activated voxels, mean, and variance. Furthermore, this study also proposes a test function for examining voxel activation based on variance, so that insignificant voxels and irrelevant outliers can be removed from the features. After the feature extraction from brain regions of interest, the analysis subsequently uses Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) for reducing the feature size. Lastly, this study adopts a computer-aided pattern recognizer, the Support Vector Machine (SVM), to facilitate automation of the proposed analysis. A dataset consisting of brain-scanning images from 22 subjects was used for evaluation. The statistical result shows that the neural circuitry associated with maternal bonds indeed appears in the relevant brain regions as indicated by the other research. Such regions are subsequently used for assessment of the proposed analysis. Classification result shows that the proposed approach can effectively identify activated samples. Besides, our system achieves an accuracy rate of as high as 83.33 %. A comparison among different systems reveals that the proposed system is superior to the others and establishes its feasibility.