Classifier ensembles for fMRI data analysis: an experiment

Functional magnetic resonance imaging (fMRI) is becoming a forefront brain–computer interface tool. To decipher brain patterns, fast, accurate and reliable classifier methods are needed. The support vector machine (SVM) classifier has been traditionally used. Here we argue that state-of-the-art methods from pattern recognition and machine learning, such as classifier ensembles, offer more accurate classification. This study compares 18 classification methods on a publicly available real data set due to Haxby et al. [Science 293 (2001) 2425–2430]. The data comes from a single-subject experiment, organized in 10 runs where eight classes of stimuli were presented in each run. The comparisons were carried out on voxel subsets of different sizes, selected through seven popular voxel selection methods. We found that, while SVM was robust, accurate and scalable, some classifier ensemble methods demonstrated significantly better performance. The best classifiers were found to be the random subspace ensemble of SVM classifiers, rotation forest and ensembles with random linear and random spherical oracle.     

A simple technique for holographic multiplexing

A technique for holographic multiplexing is proposed which utilizes a combination of theta modulation and carrier frequency multiplexing. Twenty two binary transparent object were multiplexed with this technique and a resolution of 10 lines/mm with good diffraction efficiency was obtained. The technique can be used for studying the sequential events at discrete time intervals.     

Strategies for reducing large fMRI data sets for independent component analysis

In independent component analysis (ICA), principal component analysis (PCA) is generally used to reduce the raw data to a few principal components (PCs) through eigenvector decomposition (EVD) on the data covariance matrix. Although this works for spatial ICA (sICA) on moderately sized fMRI data, it is intractable for temporal ICA (tICA), since typical fMRI data have a high spatial dimension, resulting in an unmanageable data covariance matrix. To solve this problem, two practical data reduction methods are presented in this paper. The first solution is to calculate the PCs of tICA from the PCs of sICA. This approach works well for moderately sized fMRI data; however, it is highly computationally intensive, even intractable, when the number of scans increases. The second solution proposed is to perform PCA decomposition via a cascade recursive least squared (CRLS) network, which provides a uniform data reduction solution for both sICA and tICA. Without the need to calculate the covariance matrix, CRLS extracts PCs directly from the raw data, and the PC extraction can be terminated after computing an arbitrary number of PCs without the need to estimate the whole set of PCs. Moreover, when the whole data set becomes too large to be loaded into the machine memory, CRLS-PCA can save data retrieval time by reading the data once, while the conventional PCA requires numerous data retrieval steps for both covariance matrix calculation and PC extractions. Real fMRI data were used to evaluate the PC extraction precision, computational expense, and memory usage of the presented methods.     

Fixed-point algorithms for constrained ICA and their applications in fMRI data analysis

Constrained independent component analysis (CICA) eliminates the order ambiguity of standard ICA by incorporating prior information into the learning process to sort the components intrinsically. However, the original CICA (OCICA) and its variants depend on a learning rate, which is not easy to be tuned for various applications. To solve this problem, two learning-rate-free CICA algorithms were derived in this paper using the fixed-point learning concept. A complete stability analysis was provided for the proposed methods, which also made a correction to the stability analysis given to OCICA. Variations for adding constraints either to the components or to the associated time courses were derived too. Using synthetic data, the proposed methods yielded a better stability and a better source separation quality in terms of higher signal-to-noise-ratio and smaller performance index than OCICA. For the artificially generated brain activations, the new CICAs demonstrated a better sensitivity/specificity performance than standard univariate general linear model (GLM) and standard ICA. Original CICA showed a similar sensitivity/specificity gain but failed to converge for several times. Using functional magnetic resonance imaging (fMRI) data acquired with a well-characterized sensorimotor task, the proposed CICAs yielded better sensitivity than OCICA, standard ICA and GLM in all the target functional regions in terms of either higher t values or larger suprathreshold cluster extensions using the same significance threshold. In addition, they were more stable than OCICA and standard ICA for analyzing the sensorimotor fMRI data.     

Realignment strategies for awake-monkey fMRI data

Functional magnetic resonance imaging (fMRI) experiments with awake nonhuman primates (NHPs) have recently seen a surge of applications. However, the standard fMRI analysis tools designed for human experiments are not optimal for NHP data collected at high fields. One major difference is the experimental setup. Although real head movement is impossible for NHPs, MRI image series often contain visible motion artifacts. Animal body movement results in image position changes and geometric distortions. Since conventional realignment methods are not appropriate to address such differences, algorithms tailored specifically for animal scanning become essential. We have implemented a series of high-field NHP specific methods in a software toolbox, fMRI Sandbox (http://kyb.tuebingen.mpg.de/~stoewer/), which allows us to use different realignment strategies. Here we demonstrate the effect of different realignment strategies on the analysis of awake-monkey fMRI data acquired at high field (7 T). We show that the advantage of using a nonstandard realignment algorithm depends on the amount of distortion in the dataset. While the benefits for less distorted datasets are minor, the improvement of statistical maps for heavily distorted datasets is significant.     

A simple technique for laser-induced ablation pressure measurement

A simple method for measuring laser-induced ablation pressure is described. The technique utilizes the well-known double foil concept. In the present experiment the impact times were estimated by monitoring the reflectivity of the impact foil rear. The measurements were performed using a glass laser (1·06 μm wavelength) in the 10¹¹−10¹³ W/cm² irradiance range. Experimental results showed good agreement with those obtained using other techniques as also those with the self-regulating ablation model prediction.     

Assessment of data acquisition parameters,and analysis techniques for noise reduction in spinal cord fMRI data

Purpose

The purpose of this work is to characterize the noise in spinal cord functional MRI, assess current methods aimed at reducing noise, and optimize imaging parameters.

Methods

Functional MRI data were acquired at multiple echo times and the contrast-to-noise ratio (CNR) was calculated. Independently, the repetition time was systematically varied with and without parallel imaging, to maximize BOLD sensitivity and minimize type I errors. Noise in the images was characterized by examining the frequency spectrum, and investigating whether autocorrelations exist. The efficacy of several physiological noise reduction methods in both null (no stimuli) and task (thermal pain paradigm) data was also assessed. Finally, our previous normalization methods were extended.

Results

The echo time with the highest functional CNR at 3 Tesla is at roughly 75 msec. Parallel imaging reduced the variance and the presence of autocorrelations, however the BOLD response in task data was more robust in data acquired without parallel imaging. Model-free based approaches further increased the detection of active voxels in the task data. Finally, inter-subject registration was improved.

Conclusions

Results from this study provide a rigorous characterization of the properties of the noise and assessment of data acquisition and analysis methods for spinal cord and brainstem fMRI.     

Ellipsometric data analysis used in on-line metal passivation monitoring

Metal oxide thin films, suitable for use on solar energy converters and photocatalitic applications, have been characterized on-line by ellipsometric monitoring system. Ellipsometry is a powerful and non-invasive technique of film analysis but it is indirect tool. The most interesting parameters such as film thickness and complex refractive indices can be determined only by computer sample modelling. The complex reflection coefficients obtained from model calculation were compared with ellipsometric measurements. We discuss composition of multilayer film structure using various models and fittings method. The implementation of effective medium approximation procedure enables to interpret multilayer oxides structure formation during passivation process. It is shown that an accurate model fitting was obtained using Levenberg-Marquardt optimization algorithm and multidimensional mean square error.     

A novel approach for fMRI data analysis based on the combination of sparse approximation and affinity propagation clustering

Clustering analysis has been widely used to detect the functional connectivity from functional magnetic resonance imaging (fMRI) data. However, it has some limitations such as enormous computer memory requirement, and difficulty in estimating the number of clusters. In this study, in order to effectually resolve the deficiencies mentioned above, we have proposed a novel approach (SAAPC) for fMRI data analysis, which combines sparsity, an effective assumption for analyzing fMRI signal, with affinity propagation clustering (APC).     

A simple correction technique for positron annihilation lineshape measurements

A simple correction technique for positron annihilation photon lineshape measurements which can significantly decrease systematic errors arising from resolution changes is described.     

A simple positive-step alignment technique for a ring resonator

A quick and simple technique is presented for the alignment of a ring resonator of any configuration and any number of mirrors, given that a laser power source of variable gain is available. The method used ensures that the resonator is known to be aligned—a distinct advantage over former techniques.     

Multivariate analysis of fMRI data by oriented partial least squares

Partial least squares (PLS) has been used in multivariate analysis of functional magnetic resonance imaging (fMRI) data as a way of incorporating information about the underlying experimental paradigm. In comparison, principal component analysis (PCA) extracts structure merely by summarizing variance and with no assurance that individual component structures are directly interpretable or that they represent salient and useful features. Oriented partial least squares (OrPLS) is a new PLS-like analysis paradigm in which extracted components can be oriented away from undesirable noise or confounds in the data and toward a desired targeted structure reflecting the fMRI experiment.     

介绍一种简单的光学模糊成像技术

本文介绍了一种光学成像技术,采用这种技术可以得到一张面目全非的照片。这张面目全非的照片经过处理后,又可恢复成原来的照片。这种技术具有一把钥匙开一把锁的特性,在某些场合具有特殊的用途。     

Maximum likelihood estimation for second level fMRI data analysis with expectation trust region algorithm

The trust region method which originated from the Levenberg–Marquardt (LM) algorithm for mixed effect model estimation are considered in the context of second level functional magnetic resonance imaging (fMRI) data analysis. We first present the mathematical and optimization details of the method for the mixed effect model analysis, then we compare the proposed methods with the conventional expectation-maximization (EM) algorithm based on a series of datasets (synthetic and real human fMRI datasets). From simulation studies, we found a higher damping factor for the LM algorithm is better than lower damping factor for the fMRI data analysis. More importantly, in most cases, the expectation trust region algorithm is superior to the EM algorithm in terms of accuracy if the random effect variance is large. We also compare these algorithms on real human datasets which comprise repeated measures of fMRI in phased-encoded and random block experiment designs. We observed that the proposed method is faster in computation and robust to Gaussian noise for the fMRI analysis. The advantages and limitations of the suggested methods are discussed.     

A simple and fast method for computing the relativistic Compton scattering kernel for radiative transfer

The Klein-Nishina differential cross section averaged over a relativistic Maxwellian electron distribution is analytically reduced to a single integral, which can then be rapidly evaluated in a variety of ways. A particularly fast method for numerically computing this single integral is presented. This is, to our knowledge, the first correct computation of the Compton scattering kernel.     

A variant of logistic transfer function in Infomax and a postprocessing procedure for independent component analysis applied to fMRI data

Independent component analysis with Infomax algorithm can separate functional magnetic resonance imaging (fMRI) data into independent spatial components (brain activation maps) and their associated time courses. In the current study, we propose a variant of the logistic transfer function in Infomax, referred to as a-logistic Infomax, and a postprocessing procedure to combine a consistently task-related (CTR) component with transiently task-related (TTR) components for a better definition of brain functional localization. This a-logistic Infomax introduced parameter a into the standard logistic transfer function of conventional Infomax algorithm. For postprocessing method, we suggest the use of a stepwise linear regression of CTR and TTR components to fit reference function and then to sum up with different weights only those with significant contributions to the reference function in order to obtain a task component activation map. The effectiveness of both approaches on separating components and functional localization was evaluated with simulated and real fMRI data.     

A method for comparing group fMRI data using independent component analysis: application to visual, motor and visuomotor tasks

Independent component analysis (ICA) is an approach for decomposing fMRI data into spatially independent maps and time courses. We have recently proposed a method for ICA of multisubject data; in the current paper, an extension is proposed for allowing ICA group comparisons. This method is applied to data from experiments designed to stimulate visual cortex, motor cortex or both visual and motor cortices. Several intergroup and intragroup metrics are proposed for assessing the utility of the components for comparisons of group ICA data. The proposed method may prove to be useful in answering questions requiring multigroup comparisons when a flexible modeling approach is desired.     

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.     

Comparison of two exploratory data analysis methods for fMRI: fuzzy clustering vs. principal component analysis

Exploratory data-driven methods such as Fuzzy clustering analysis (FCA) and Principal component analysis (PCA) may be considered as hypothesis-generating procedures that are complementary to the hypothesis-led statistical inferential methods in functional magnetic resonance imaging (fMRI). Here, a comparison between FCA and PCA is presented in a systematic fMRI study, with MR data acquired under the null condition, i.e., no activation, with different noise contributions and simulated, varying "activation." The contrast-to-noise (CNR) ratio ranged between 1-10. We found that if fMRI data are corrupted by scanner noise only, FCA and PCA show comparable performance. In the presence of other sources of signal variation (e.g., physiological noise), FCA outperforms PCA in the entire CNR range of interest in fMRI, particularly for low CNR values. The comparison method that we introduced may be used to assess other exploratory approaches such as independent component analysis or neural network-based techniques.