Partial least squares for discrimination in fMRI data

Multivariate methods for discrimination were used in the comparison of brain activation patterns between groups of cognitively normal women who are at either high or low Alzheimer's disease risk based on family history and apolipoprotein-E4 status. Linear discriminant analysis (LDA) was preceded by dimension reduction using principal component analysis (PCA), partial least squares (PLS) or a new oriented partial least squares (OrPLS) method. The aim was to identify a spatial pattern of functionally connected brain regions that was differentially expressed by the risk groups and yielded optimal classification accuracy. Multivariate dimension reduction is required prior to LDA when the data contain more feature variables than there are observations on individual subjects. Whereas PCA has been commonly used to identify covariance patterns in neuroimaging data, this approach only identifies gross variability and is not capable of distinguishing among-groups from within-groups variability. PLS and OrPLS provide a more focused dimension reduction by incorporating information on class structure and therefore lead to more parsimonious models for discrimination. Performance was evaluated in terms of the cross-validated misclassification rates. The results support the potential of using functional magnetic resonance imaging as an imaging biomarker or diagnostic tool to discriminate individuals with disease or high risk.     

The effect of sensorimotor activation on functional connectivity mapping with MRI

The correlations in the fluctuations in the blood oxygenation level-dependent (BOLD) MRI signal between anatomically distinct regions of the cortex that are known components of functional systems have been previously studied as possible indicators of functional connectivity. The objective of this study was to examine the effect of sensorimotor brain activity, as assessed by task-based functional magnetic resonance imaging (fMRI), on functional connectivity indices in the same region. Regions of activation for sequential finger motion were determined using a task-based, block-design fMRI study. Functional connectivity measurements based on interregional correlations were acquired at rest and during continuous, sequential finger motion. Connectivity indices were determined using normalized mean correlations within and between three regions of interest activated for the finger motion task. Connectivity indices were also determined for a control region that was not activated for the task. Continuous motor tasks performed during BOLD measurements did not significantly affect the functional connectivity as compared to the connectivity at rest within or between regions known to be activated by the task. However, there appeared to be a trend suggesting a slight reduction in connectivity indices during the motor task. The connectivity within and between those areas not activated for the task remained unchanged between conditions. These results suggest that in the motor system investigated, the recruitment of neurons to perform a specific task may moderately reduce the degree of hemodynamic coupling within and between regions.     

Dissecting cognitive stages with time-resolved fMRI data: a comparison of fuzzy clustering and independent component analysis

In combination with cognitive tasks entailing sequences of sensory and cognitive processes, event-related acquisition schemes allow using functional MRI to examine not only the topography but also the temporal sequence of cortical activation across brain regions (time-resolved fMRI). In this study, we compared two data-driven methods--fuzzy clustering method (FCM) and independent component analysis (ICA)--in the context of time-resolved fMRI data collected during the performance of a newly devised visual imagery task. We analyzed a multisubject fMRI data set using both methods and compared their results in terms of within- and between-subject consistency and spatial and temporal correspondence of obtained maps and time courses. Both FCM and spatial ICA allowed discriminating the contribution of distinct networks of brain regions to the main cognitive stages of the task (auditory perception, mental imagery and behavioural response), with good agreement across methods. Whereas ICA worked optimally on the original time series, averaging with respect to the task onset (and thus introducing some a priori information on the stimulation protocol) was found to be indispensable in the case of FCM. On averaged time series, FCM led to a richer decomposition of the spatio-temporal patterns of activation and allowed a finer separation of the neurocognitive processes subserving the mental imagery task. This study confirms the efficacy of the two examined methods in the data-driven estimation of hemodynamic responses in time-resolved fMRI studies and provides empirical guidelines to their use.     

Assessing functional connectivity in the human brain by fMRI

Functional magnetic resonance imaging (fMRI) is widely used to detect and delineate regions of the brain that change their level of activation in response to specific stimuli and tasks. Simple activation maps depict only the average level of engagement of different regions within distributed systems. FMRI potentially can reveal additional information about the degree to which components of large-scale neural systems are functionally coupled together to achieve specific tasks. In order to better understand how brain regions contribute to functionally connected circuits, it is necessary to record activation maps either as a function of different conditions, at different times or in different subjects. Data obtained under different conditions may then be analyzed by a variety of techniques to infer correlations and couplings between nodes in networks. Several multivariate statistical methods have been adapted and applied to analyze variations within such data. An approach of particular interest that is suited to studies of connectivity within single subjects makes use of acquisitions of runs of MRI images obtained while the brain is in a so-called steady state, either at rest (i.e., without any specific stimulus or task) or in a condition of continuous activation. Interregional correlations between fluctuations of MRI signal potentially reveal functional connectivity. Recent studies have established that interregional correlations between different components of circuits in each of the visual, language, motor and working memory systems can be detected in the resting state. Correlations at baseline are changed during the performance of a continuous task. In this review, various methods available for assessing connectivity are described and evaluated.     

Detecting functional magnetic resonance imaging activation in white matter: Interhemispheric transfer across the corpus callosum

Background  

It is generally believed that activation in functional magnetic resonance imaging (fMRI) is restricted to gray matter. Despite this, a number of studies have reported white matter activation, particularly when the corpus callosum is targeted using interhemispheric transfer tasks. These findings suggest that fMRI signals may not be neatly confined to gray matter tissue. In the current experiment, 4 T fMRI was employed to evaluate whether it is possible to detect white matter activation. We used an interhemispheric transfer task modelled after neurological studies of callosal disconnection. It was hypothesized that white matter activation could be detected using fMRI.     

Comparison of pattern recognition methods in classifying high-resolution BOLD signals obtained at high magnetic field in monkeys

Pattern recognition methods have shown that functional magnetic resonance imaging (fMRI) data can reveal significant information about brain activity. For example, in the debate of how object categories are represented in the brain, multivariate analysis has been used to provide evidence of a distributed encoding scheme [Science 293:5539 (2001) 2425–2430]. Many follow-up studies have employed different methods to analyze human fMRI data with varying degrees of success [Nature reviews 7:7 (2006) 523–534]. In this study, we compare four popular pattern recognition methods: correlation analysis, support-vector machines (SVM), linear discriminant analysis (LDA) and Gaussian naïve Bayes (GNB), using data collected at high field (7 Tesla) with higher resolution than usual fMRI studies. We investigate prediction performance on single trials and for averages across varying numbers of stimulus presentations. The performance of the various algorithms depends on the nature of the brain activity being categorized: for several tasks, many of the methods work well, whereas for others, no method performs above chance level. An important factor in overall classification performance is careful preprocessing of the data, including dimensionality reduction, voxel selection and outlier elimination.     

Combining independent component analysis and correlation analysis to probe interregional connectivity in fMRI task activation datasets

A new approach in studying interregional functional connectivity using functional magnetic resonance imaging (fMRI) is presented. Functional connectivity may be detected by means of cross correlating time course data from functionally related brain regions. These data exhibit high temporal coherence of low frequency fluctuations due to synchronized blood flow changes. In the past, this fMRI technique for studying functional connectivity has been applied to subjects that performed no prescribed task ("resting" state). This paper presents the results of applying the same method to task-related activation datasets. Functional connectivity analysis is first performed in areas not involved with the task. Then a method is devised to remove the effects of activation from the data using independent component analysis (ICA) and functional connectivity analysis is repeated. Functional connectivity, which is demonstrated in the "resting brain," is not affected by tasks which activate unrelated brain regions. In addition, ICA effectively removes activation from the data and may allow us to study functional connectivity even in the activated regions.     

Surface-based functional magnetic resonance imaging analysis of partial brain echo planar imaging data at 1.5 T

Surface-based functional magnetic resonance imaging (fMRI) analysis is more sensitive and accurate than volume-based analysis for detecting neural activation. However, these advantages are less important in practical fMRI experiments with commonly used 1.5-T magnetic resonance devices because of the resolution gap between the echo planar imaging data and the cortical surface models. We expected high-resolution segmented partial brain echo planar imaging (EPI) data to overcome this problem, and the activation patterns of the high-resolution data could be different from the low-resolution data. For the practical applications of surface-based fMRI analysis using segmented EPI techniques, the effects of some important factors (e.g., activation patterns, registration and local distortions) should be intensively evaluated because the results of surface-based fMRI analyses could be influenced by them. In this study, we demonstrated the difference between activations detected from low-resolution EPI data, which were covering whole brain, and high-resolution segmented EPI data covering partial brain by volume- and surface-based analysis methods. First, we compared the activation maps of low- and high-resolution EPI datasets detected by volume- and surface-based analyses, with the spatial patterns of activation clusters, and analyzed the distributions of activations in occipital lobes. We also analyzed the high-resolution EPI data covering motor areas and fusiform gyri of human brain, and presented the differences of activations detected by volume- and surface-based methods.     

Regional brain activity after prolonged cholinergic enhancement in early Alzheimer's disease

This functional magnetic resonance imaging (fMRI) study examined changes in brain activation after prolonged (20 weeks) and stabilized treatment with the cholinesterase inhibitor galantamine in a small group of patients with very mild Alzheimer's disease (AD). Two cognitive activation paradigms were chosen: one requiring semantic association and the other relying on attention and requiring target detection. A group of age- and education-matched healthy controls was also scanned for comparison. A modest (but not statistically significant) improvement in behavioral scores after treatment was observed in both fMRI tasks. There were brain activation increases in the semantic association task after treatment, and the differences in brain activation present in the comparison of AD patients' baseline images with those of controls were not detectable after treatment. In the target detection task, regions that were activated in the elderly controls but not in the baseline images of the AD group also showed significant activation after treatment. Overall, however, the increases were modest and might reflect the heterogeneity of clinical response to treatment in this small group. Future pharmacological fMRI studies should include clinical response as a factor in the analysis of cholinergic enhancement effects in AD patients.     

非线性流行降维与近红外光谱分析技术的大米贮藏期快速判别

提出一种基于流行降维的近红外光谱技术快速判别大米贮藏期的新方法。采用近红外光谱仪获取陈年米和新米的反射光谱特征曲线,利用直接正交信号矫正法(direct orthogonal signal correction, DOSC)对原始光谱进行预处理,滤除光谱数据中与因变量Y矩阵无关的信号,以消除无关信息对后续特征变量建模精度的影响。采用Durbin-Watson和Run测试法定性分析光谱数据结构的非线性性,并利用增强偏残差图(augmented partial residual plot)定量分析大米光谱曲线的非线性程度。分别采用线性流行降维法包括主成分分析法(PCA)和多维尺度分析法(MDS)以及非线性流行降维法包括等距映射法(ISOMAP)、局部线性嵌入法(LLE)和拉普拉斯特征映射法(LE)提取预处理后光谱数据的本征变量,并结合核偏最小二乘方法(KPLS)建立本征变量与贮藏时间属性之间的耦合模型。实验用陈年米和新米的样本数均为200个,随机将训练集和测试集样本划分为300个和100个。通过比较各个模型的预测结果得出,基于ISOMAP非线性降维法提取的40个本征变量建立的回归模型预测效果最好,预测相关系数(R2_P)、预测均方根误差(RMSEP)和预测相对分析误差值(RPD)分别为0.917,0.187和2.698。实验结果说明提出的方法对于大米贮藏期具有很好的鉴别能力,该研究为今后大米贮藏期的快速无损检测提供了科学的手段。     

Real-time animal functional magnetic resonance imaging and its application to neuropharmacological studies

In pharmacological magnetic resonance imaging (phMRI) with anesthetized animals, there is usually only a single time window to observe the dynamic signal change to an acute drug administration since subsequent drug injections are likely to result in altered response properties (e.g., tolerance). Unlike the block-design experiments in which fMRI signal can be elicited with multiple repetitions of a task, these single-event experiments require stable baseline in order to reliably identify drug-induced signal changes. Such factors as subject motion, scanner instability and/or alterations in physiological conditions of the anesthetized animal could confound the baseline signal. The unique feature of such functional MRI (fMRI) studies necessitates a technique that is able to monitor MRI signal in a real-time fashion and to interactively control certain experimental procedures. In the present study, an approach for real-time MRI on a Bruker scanner is presented. The custom software runs on the console computer in parallel with the scanner imaging software, and no additional hardware is required. The utility of this technique is demonstrated in manganese-enhanced MRI (MEMRI) with acute cocaine challenge, in which temporary disruption of the blood-brain barrier (BBB) is a critical step for MEMRI experiments. With the aid of real-time MRI, we were able to assess the outcome of BBB disruption following bolus injection of hyperosmolar mannitol in a near real-time fashion prior to drug administration, improving experimental success rate. It is also shown that this technique can be applied to monitor baseline physiological conditions in conventional fMRI experiments using blood oxygenation level-dependent (BOLD) contrast, further demonstrating the versatility of this technique.     

Neural correlates of a clinical continuous performance test

Functional magnetic resonance imaging (fMRI) was performed in 30 healthy adults to identify the location, magnitude, and extent of activation in brain regions that are engaged during the performance of Conners' Continuous Performance Test (CPT). Performance on the task during fMRI was highly correlated with performance on the standard Conners' CPT in the behavioral testing laboratory. An extensive neural network was activated during the task that included the frontal, cingulate, parietal, temporal, and occipital cortices; the cerebellum and the basal ganglia. There was also a network of brain regions which were more active during fixation than task. The magnitude of activation in several regions was correlated with reaction time. Among regions that were more active during task, the overall volume of supratentorial activation and cerebellar activation was greater in the left hemisphere. Frontal activation was greater in dorsal than in ventral regions, and dorsal frontal activation was bilateral. Ventral frontal region and parietal lobe activation were greater in the right hemisphere. The volume of clusters of activation in the extrastriate ventral visual pathway was greater in the left hemisphere. This network is consistent with existing models of motor control, visual object processing and attentional control and may serve as a basis for hypothesis-driven fMRI studies in clinical populations with deficits in Conners' CPT performance.     

The neural correlates of calculation ability in children: an fMRI study

Most studies investigating mental numerical processing involve adult participants and little is known about the functioning of these systems in children. The current study used functional magnetic resonance imaging (fMRI) to investigate the neural correlates of numeracy and the influence of age on these correlates with a group of adults and a group of third graders who had average to above average mathematical ability. Participants performed simple and complex versions of exact and approximate calculation tasks while in the magnet. Like adults, children activated a network of brain regions in the frontal and parietal lobes during the calculation tasks, and they recruited additional brain regions for the more complex versions of the tasks. However, direct comparisons between adults and children revealed significant differences in level of activation across all tasks. In particular, patterns of activation in the parietal lobe were significantly different as a function of age. Findings support previous claims that the parietal lobe becomes more specialized for arithmetic tasks with age.     

Biophysical and neural basis of resting state functional connectivity: Evidence from non-human primates

Functional MRI (fMRI) has evolved from simple observations of regional changes in MRI signals caused by cortical activity induced by a task or stimulus, to task-free acquisitions of images in a resting state. Such resting state signals contain low frequency fluctuations which may be correlated between voxels, and strongly correlated regions are deemed to reflect functional connectivity within synchronized circuits. Resting state functional connectivity (rsFC) measures have been widely adopted by the neuroscience community, and are being used and interpreted as indicators of intrinsic neural circuits and their functional states in a broad range of applications, both basic and clinical. However, there has been relatively little work reported that validates whether inter-regional correlations in resting state fluctuations of fMRI (rsfMRI) signals actually measure functional connectivity between brain regions, or to establish how MRI data correlate with other metrics of functional connectivity. In this mini-review, we summarize recent studies of rsFC within mesoscopic scale cortical networks (100 μm–10 mm) within a well defined functional region of primary somatosensory cortex (S1), as well as spinal cord and brain white matter in non-human primates, in which we have measured spatial patterns of resting state correlations and validated their interpretation with electrophysiological signals and anatomic connections. Moreover, we emphasize that low frequency correlations are a general feature of neural systems, as evidenced by their presence in the spinal cord as well as white matter. These studies demonstrate the valuable role of high field MRI and invasive measurements in an animal model to inform the interpretation of human imaging studies.     

Flexible statistical modelling detects clinical functional magnetic resonance imaging activation in partially compliant subjects

Clinical functional magnetic resonance imaging (fMRI) occasionally fails to detect significant activation, often due to variability in task performance. The present study seeks to test whether a more flexible statistical analysis can better detect activation, by accounting for variance associated with variable compliance to the task over time. Experimental results and simulated data both confirm that even at 80% compliance to the task, such a flexible model outperforms standard statistical analysis when assessed using the extent of activation (experimental data), goodness of fit (experimental data), and area under the operator characteristic curve (simulated data). Furthermore, retrospective examination of 14 clinical fMRI examinations reveals that in patients where the standard statistical approach yields activation, there is a measurable gain in model performance in adopting the flexible statistical model, with little or no penalty in lost sensitivity. This indicates that a flexible model should be considered, particularly for clinical patients who may have difficulty complying fully with the study task.     

Activation mapping as a percentage of local excitation: fMRI stability within scans, between scans and across field strengths

Functional magnetic resonance imaging (fMRI) does not typically yield highly reproducible maps of brain activation. Maps can vary significantly even with constant scanning parameters and consistent task performance conditions (Liu et al., Magn. Reson. Med., 2004, 52:751-760). Reproducibility is even more of a problem when comparing fMRI signal magnitude and spatial extent of activation across scans involving different task performance levels, scan durations, pulse sequences or magnetic field strengths. In this report, the consistency of fMRI was reexamined by considering the relative spatial and temporal distribution of fMRI blood oxygen level dependent (BOLD) activation signals separately from the absolute magnitude of the activation signal in each brain area. Subjects repeatedly performed the same simple motor task but under a variety of imaging conditions, using both spiral and standard echo-planar pulse sequences and at 1.5- and 4.0-T magnetic field strengths. The results demonstrate that the absolute amplitude of BOLD statistical activation signals varied significantly across time and scanning conditions, but the relative spatial pattern of BOLD activation was highly reproducible across all conditions. Analysis of realistic simulated fMRI data sets indicates that stability of relative activation patterns could provide a useful tool for assessing the accuracy of fMRI maps.     

Controlling the false positive rate in fuzzy clustering using randomization: application to fMRI activation detection

Despite its potential advantages for fMRI analysis, fuzzy C-means (FCM) clustering suffers from limitations such as the need for a priori knowledge of the number of clusters, and unknown statistical significance and instability of the results. We propose a randomization-based method to control the false-positive rate and estimate statistical significance of the FCM results. Using this novel approach, we develop an fMRI activation detection method. The ability of the method in controlling the false-positive rate is shown by analysis of false positives in activation maps of resting-state fMRI data. Controlling the false-positive rate in FCM allows comparison of different fuzzy clustering methods, using different feature spaces, to other fMRI detection methods. In this article, using simulation and real fMRI data, we compare a novel feature space that takes the variability of the hemodynamic response function into account (HRF-based feature space) to the conventional cross-correlation analysis and FCM using the cross-correlation feature space. In both cases, the HRF-based feature space provides a greater sensitivity compared to the cross-correlation feature space and conventional cross-correlation analysis. Application of the proposed method to finger-tapping fMRI data, using HRF-based feature space, detected activation in sub-cortical regions, whereas both of the FCM with cross-correlation feature space and the conventional cross-correlation method failed to detect them.     

Integration of structural and functional magnetic resonance imaging improves mild cognitive impairment detection

The identification of mild cognitive impairments (MCI) via either structural magnetic resonance imaging (sMRI) or functional MRI (fMRI) has great potential due to the non-invasiveness of the techniques. Furthermore, these techniques allow longitudinal follow-ups of single subjects via repeated measurements. sMRI- or fMRI-based biomarkers have been adopted separately to diagnose MCI; however, there has not been a systematic effort to integrate sMRI- and fMRI-based features to increase MCI detection accuracy. This study investigated whether the detection of MCI can be improved via the integration of biomarkers identified from both sMRI and fMRI modalities. Regional volume sizes and neuronal activity levels of brains from MCI subjects were compared with those from healthy controls and used to identify biomarkers from sMRI and fMRI data, respectively. In the subsequent classification phase, MCI was automatically detected using a support vector machine algorithm that employed the identified sMRI- and fMRI-based biomarkers as an input feature vector. The results indicate that the fMRI-based biomarkers provided more information for detecting MCI than the sMRI-based biomarkers. Moreover, the integrated feature sets using the sMRI- and fMRI-based biomarkers consistently showed greater detection accuracy than the feature sets based only on the fMRI-based biomarkers. The results demonstrate that integration of sMRI and fMRI modalities can provide supplemental information to improve the diagnosis of MCI relative to either the sMRI or fMRI modalities alone.     

Activation detection in event-related fMRI data based on spatio-temporal properties.

Template-based activation detection methods, such as cross-correlation, could be difficult to apply in event-related functional MRI data because accurate a priori knowledge about the activation signal patterns is often not available. As a result, several categories of template-free data analysis techniques have been introduced in the fMRI literature. One previously described template-free activation detection technique is based on the feature that activated voxels yield reproducible time course patterns as the subject undergoes the same simulation in repeated epochs. In this paper, spatial information is incorporated as a second feature and a combined univariate measure is formed. The resulting method is shown to offer measurable improvement in detecting activation regions in simulated data in a highly computationally efficient manner. Its practical utility is demonstrated with an experimental data set obtained with a visually guided motor paradigm.     

堆叠监督自动编码器的近红外光谱建模

近红外光谱中包含了物质中有机分子含氢基团的特征信息,具有维度高、冗余大等特点.传统的基于浅层校正模型,比如主成分回归、偏最小二乘回归、人工神经网络、支持向量回归等,无法提取近红外光谱数据深层的信息.提出一种基于堆叠监督自动编码器的近红外光谱建模方法,不仅可以拟合光谱数据与理化值之间复杂的非线性关系,还可以提取数据深层的...