Mapping rabbit whisker barrels using discriminant analysis of high field fMRI data.

High field (>4T) functional magnetic resonance imaging (fMRI) techniques provide increased spatial resolution that enables the noninvasive, repeatable study of the sensory cortices at the level of their basic functional units. The examination of these units is important for studies of sensory information processing, learning- or experience-related brain plasticity, or the fundamental relationship between hemodynamic and neuronal activity. However functional units cannot always be distinguished from their surrounding areas by conventional activation mapping methods such as correlation or hypothesis tests, which only consider temporal variation within each individual voxel. We report a novel method to detect individual whisker barrels by using discriminant analysis to jointly characterize high order dependency among multiple voxels. Our results in the whisker barrel cortex of the awake rabbit indicate that the proposed method can differentiate reliably small clusters of activated voxels corresponding to individual whisker barrels within larger areas of functional activation, even in the case of adjacent whiskers in unanesthetized subjects. This method is computationally efficient, requires no specific experimental design for fMRI acquisition, and should be applicable to studies of other sensory systems.

AA Comparison of Dynamic Modeling Approaches for Epileptic EEG Detection and Classification.

Electroencephalogram (EEG) has been intensively used as a diagnosis tool for epilepsy. The traditional diagnostic procedure relies on a recording of EEG from several days up to a few weeks, and the recordings are visually inspected by trained medical professionals. This procedure is time consuming with a high misdiagnosis rate. In recent years, computer-aided techniques have been proposed to automate the epilepsy diagnosis by using machine learning methods to analyze EEG data. Considering the time-varying nature of EEG, the goal of this work is to characterize dynamic changes of EEG patterns for the detection and classification of epilepsy. Four different dynamic Bayesian modeling methods were evaluated using multi-subject epileptic EEG data. Experimental results show that an accuracy of 98.0% can be achieved by one of the four methods. The same method also provides an overall accuracy of 87.7% for the classification of seven different seizure types.

Functional magnetic resonance imaging of delay and trace eyeblink conditioning in the primary visual cortex of the rabbit.

The primary sensory cortices have been shown in recent years to undergo experience- and learning-related plasticity under a variety of experimental circumstances. In this study, we used functional magnetic resonance imaging (fMRI) in parallel with both delay and trace eyeblink conditioning to image the learning-related functional activation within the primary visual cortex (V1) of awake, behaving rabbits. We expected that the differing level of forebrain dependence between these two conditioning paradigms should produce a differential blood oxygenation level-dependent (BOLD) functional response in V1. Our results showed a significant expansion of activated volume within V1, particularly early in learning, after training with the more cognitively demanding trace paradigm. In contrast, the simpler delay paradigm produced an increase in the magnitude of the BOLD response in activated voxels, but no significant change in activated volume. No accompanying learning-related changes were observed in the primary somatosensory cortex, which mediates the unconditioned stimulus. These results suggest that the recruitment of additional neurons within V1 is necessary to support the more demanding memory imposed by the trace interval. To our knowledge, this work is the first functional imaging study to compare directly trace and delay eyeblink conditioning in an animal model.

Unsupervised spatiotemporal fMRI data analysis using support vector machines.

In this work we present a new support vector machine (SVM)-based method for fMRI data analysis. SVM has been shown to be a powerful, efficient data-driven tool in pattern recognition, and has been applied to the supervised classification of brain cognitive states in fMRI experiments. We examine the unsupervised mapping of activated brain regions using SVM. Specifically, the mapping process is formulated as an outlier detection problem of one-class SVM (OCSVM) that provides initial mapping results. These results are further refined by applying prototype selection and SVM reclassification. Multiple spatial and temporal features are extracted and selected to facilitate SVM learning. The proposed method was compared with correlation analysis (CA), t-test (TT), and spatial independent component analysis (SICA) methods using synthetic and experimental data. Our results show that the proposed method can provide more accurate and robust activation mapping than CA, TT and SICA, and is computationally more efficient than SICA. Besides its applicability to typical fMRI experiments, the proposed method is also a powerful tool in fMRI studies where a reliable quantification of activated brain regions is required.

Selecting salient frames for spatiotemporal video modeling and segmentation.

We propose a new statistical generative model for spatiotemporal video segmentation. The objective is to partition a video sequence into homogeneous segments that can be used as "building blocks" for semantic video segmentation. The baseline framework is a Gaussian mixture model (GMM)-based video modeling approach that involves a six-dimensional spatiotemporal feature space. Specifically, we introduce the concept of frame saliency to quantify the relevancy of a video frame to the GMM-based spatiotemporal video modeling. This helps us use a small set of salient frames to facilitate the model training by reducing data redundancy and irrelevance. A modified expectation maximization algorithm is developed for simultaneous GMM training and frame saliency estimation, and the frames with the highest saliency values are extracted to refine the GMM estimation for video segmentation. Moreover, it is interesting to find that frame saliency can imply some object behaviors. This makes the proposed method also applicable to other frame-related video analysis tasks, such as key-frame extraction, video skimming, etc. Experiments on real videos demonstrate the effectiveness and efficiency of the proposed method.

Data-Driven and Predefined ROI-Based Quantification of Long-Term Resting-State fMRI Reproducibility.

Resting-state functional magnetic resonance imaging (fMRI) is a promising tool for neuroscience and clinical studies. However, there exist significant variations in strength and spatial extent of resting-state functional connectivity over repeated sessions in a single or multiple subjects with identical experimental conditions. Reproducibility studies have been conducted for resting-state fMRI where the reproducibility was usually evaluated in predefined regions-of-interest (ROIs). It was possible that reproducibility measures strongly depended on the ROI definition. In this work, this issue was investigated by comparing data-driven and predefined ROI-based quantification of reproducibility. In the data-driven analysis, the reproducibility was quantified using functionally connected voxels detected by a support vector machine (SVM)-based technique. In the predefined ROI-based analysis, all voxels in the predefined ROIs were included when estimating the reproducibility. Experimental results show that (1) a moderate to substantial within-subject reproducibility and a reasonable between-subject reproducibility can be obtained using functionally connected voxels identified by the SVM-based technique; (2) in the predefined ROI-based analysis, an increase in ROI size does not always result in higher reproducibility measures; (3) ROI pairs with high connectivity strength have a higher chance to exhibit high reproducibility; (4) ROI pairs with high reproducibility do not necessarily have high connectivity strength; (5) the reproducibility measured from the identified functionally connected voxels is generally higher than that measured from all voxels in predefined ROIs with typical sizes. The findings (2) and (5) suggest that conventional ROI-based analyses would underestimate the resting-state fMRI reproducibility.

Spatially regularized machine learning for task and resting-state fMRI.

BACKGROUND: Reliable mapping of brain function across sessions and/or subjects in task- and resting-state has been a critical challenge for quantitative fMRI studies although it has been intensively addressed in the past decades. NEW METHOD: A spatially regularized support vector machine (SVM) technique was developed for the reliable brain mapping in task- and resting-state. Unlike most existing SVM-based brain mapping techniques, which implement supervised classifications of specific brain functional states or disorders, the proposed method performs a semi-supervised classification for the general brain function mapping where spatial correlation of fMRI is integrated into the SVM learning. The method can adapt to intra- and inter-subject variations induced by fMRI nonstationarity, and identify a true boundary between active and inactive voxels, or between functionally connected and unconnected voxels in a feature space. RESULTS: The method was evaluated using synthetic and experimental data at the individual and group level. Multiple features were evaluated in terms of their contributions to the spatially regularized SVM learning. Reliable mapping results in both task- and resting-state were obtained from individual subjects and at the group level. COMPARISON WITH EXISTING METHODS: A comparison study was performed with independent component analysis, general linear model, and correlation analysis methods. Experimental results indicate that the proposed method can provide a better or comparable mapping performance at the individual and group level. CONCLUSIONS: The proposed method can provide accurate and reliable mapping of brain function in task- and resting-state, and is applicable to a variety of quantitative fMRI studies.

Improving brain-computer interface classification using adaptive common spatial patterns.

Common Spatial Patterns (CSP) is a widely used spatial filtering technique for electroencephalography (EEG)-based brain-computer interface (BCI). It is a two-class supervised technique that needs subject-specific training data. Due to EEG nonstationarity, EEG signal may exhibit significant intra- and inter-subject variation. As a result, spatial filters learned from a subject may not perform well for data acquired from the same subject at a different time or from other subjects performing the same task. Studies have been performed to improve CSP's performance by adding regularization terms into the training. Most of them require target subjects' training data with known class labels. In this work, an adaptive CSP (ACSP) method is proposed to analyze single trial EEG data from single and multiple subjects. The method does not estimate target data's class labels during the adaptive learning and updates spatial filters for both classes simultaneously. The proposed method was evaluated based on a comparison study with the classic CSP and several CSP-based adaptive methods using motor imagery EEG data from BCI competitions. Experimental results indicate that the proposed method can improve the classification performance as compared to the other methods. For circumstances where true class labels of target data are not instantly available, it was examined if adding classified target data to training data would improve the ACSP learning. Experimental results show that it would be better to exclude them from the training data. The proposed ACSP method can be performed in real-time and is potentially applicable to various EEG-based BCI applications.

A SVM-based quantitative fMRI method for resting-state functional network detection.

Resting-state functional magnetic resonance imaging (fMRI) aims to measure baseline neuronal connectivity independent of specific functional tasks and to capture changes in the connectivity due to neurological diseases. Most existing network detection methods rely on a fixed threshold to identify functionally connected voxels under the resting state. Due to fMRI non-stationarity, the threshold cannot adapt to variation of data characteristics across sessions and subjects, and generates unreliable mapping results. In this study, a new method is presented for resting-state fMRI data analysis. Specifically, the resting-state network mapping is formulated as an outlier detection process that is implemented using one-class support vector machine (SVM). The results are refined by using a spatial-feature domain prototype selection method and two-class SVM reclassification. The final decision on each voxel is made by comparing its probabilities of functionally connected and unconnected instead of a threshold. Multiple features for resting-state analysis were extracted and examined using an SVM-based feature selection method, and the most representative features were identified. The proposed method was evaluated using synthetic and experimental fMRI data. A comparison study was also performed with independent component analysis (ICA) and correlation analysis. The experimental results show that the proposed method can provide comparable or better network detection performance than ICA and correlation analysis. The method is potentially applicable to various resting-state quantitative fMRI studies.

A unified machine learning method for task-related and resting state fMRI data analysis.

Functional magnetic resonance imaging (fMRI) aims to localize task-related brain activation or resting-state functional connectivity. Most existing fMRI data analysis techniques rely on fixed thresholds to identify active voxels under a task condition or functionally connected voxels in the resting state. Due to fMRI non-stationarity, a fixed threshold cannot adapt to intra- and inter-subject variation and provide a reliable mapping of brain function. In this work, a machine learning method is proposed for a unified analysis of both task-related and resting state fMRI data. Specifically, the mapping of brain function in a task condition or resting state is formulated as an outlier detection process. Support vector machines are used to provide an initial mapping and refine mapping results. The method does not require a fixed threshold for the final decision, and can adapt to fMRI non-stationarity. The proposed method was evaluated using experimental data acquired from multiple human subjects. The results indicate that the proposed method can provide reliable mapping of brain function, and is applicable to various quantitative fMRI studies.

A kernel machine-based fMRI physiological noise removal method.

Functional magnetic resonance imaging (fMRI) technique with blood oxygenation level dependent (BOLD) contrast is a powerful tool for noninvasive mapping of brain function under task and resting states. The removal of cardiac- and respiration-induced physiological noise in fMRI data has been a significant challenge as fMRI studies seek to achieve higher spatial resolutions and characterize more subtle neuronal changes. The low temporal sampling rate of most multi-slice fMRI experiments often causes aliasing of physiological noise into the frequency range of BOLD activation signal. In addition, changes of heartbeat and respiration patterns also generate physiological fluctuations that have similar frequencies with BOLD activation. Most existing physiological noise-removal methods either place restrictive limitations on image acquisition or utilize filtering or regression based post-processing algorithms, which cannot distinguish the frequency-overlapping BOLD activation and the physiological noise. In this work, we address the challenge of physiological noise removal via the kernel machine technique, where a nonlinear kernel machine technique, kernel principal component analysis, is used with a specifically identified kernel function to differentiate BOLD signal from the physiological noise of the frequency. The proposed method was evaluated in human fMRI data acquired from multiple task-related and resting state fMRI experiments. A comparison study was also performed with an existing adaptive filtering method. The results indicate that the proposed method can effectively identify and reduce the physiological noise in fMRI data. The comparison study shows that the proposed method can provide comparable or better noise removal performance than the adaptive filtering approach.

A Study of Long-Term fMRI Reproducibility Using Data-Driven Analysis Methods.

The reproducibility of functional magnetic resonance imaging (fMRI) is important for fMRI-based neuroscience research and clinical applications. Previous studies show considerable variation in amplitude and spatial extent of fMRI activation across repeated sessions on individual subjects even using identical experimental paradigms and imaging conditions. Most existing fMRI reproducibility studies were typically limited by time duration and data analysis techniques. Particularly, the assessment of reproducibility is complicated by a fact that fMRI results may depend on data analysis techniques used in reproducibility studies. In this work, the long-term fMRI reproducibility was investigated with a focus on the data analysis methods. Two spatial smoothing techniques, including a wavelet-domain Bayesian method and the Gaussian smoothing, were evaluated in terms of their effects on the long-term reproducibility. A multivariate support vector machine (SVM)-based method was used to identify active voxels, and compared to a widely used general linear model (GLM)-based method at the group level. The reproducibility study was performed using multisession fMRI data acquired from eight healthy adults over 1.5 years' period of time. Three regions-of-interest (ROI) related to a motor task were defined based upon which the long-term reproducibility were examined. Experimental results indicate that different spatial smoothing techniques may lead to different reproducibility measures, and the wavelet-based spatial smoothing and SVM-based activation detection is a good combination for reproducibility studies. On the basis of the ROIs and multiple numerical criteria, we observed a moderate to substantial within-subject long-term reproducibility. A reasonable long-term reproducibility was also observed from the inter-subject study. It was found that the short-term reproducibility is usually higher than the long-term reproducibility. Furthermore, the results indicate that brain regions with high contrast-to-noise ratio do not necessarily exhibit high reproducibility. These findings may provide supportive information for optimal design/implementation of fMRI studies and data interpretation.

Identification and attenuation of physiological noise in fMRI using kernel techniques.

Functional magnetic resonance imaging (fMRI) techniques enable noninvasive studies of brain functional activity under task and resting states. However, the analysis of brain activity could be significantly affected by the cardiac- and respiration-induced physiological noise in fMRI data. In most multi-slice fMRI experiments, the temporal sampling rates are not high enough to critically sample the physiological noise, and the noise is aliased into frequency bands where useful brain functional signal exists, compromising the analysis. Most existing approaches cannot distinguish between the aliased noise and signal if they overlap in the frequency domain. In this work, we further developed a kernel principal component analysis based physiological removal method based on our previous work. Specifically, two kernel functions were evaluated based on a newly proposed criterion that can measure the capability of a kernel to separate the aliased physiological noise from fMRI signal. In addition, a mutual information based criterion was designed to select principal components for noise removal. The method was evaluated by human experimental fMRI studies, and the results demonstrate that the proposed method can effectively identify and attenuate the aliased physiological noise in fMRI data.