Lichen Liang

Connection between SVM+ and multi-task learning

Exploiting additional information to improve traditional inductive learning is an active research in machine learning. When data are naturally separated into groups, SVM+[7] can effectively utilize this structure information to improve generalization. Alternatively, we can view learning based on data from each group as an individual task, but all these tasks are somehow related; so the same problem can also be formulated as a multi-task learning problem. Following the SVM+ approach, we propose a new multi-task learning algorithm called svm+MTL, which can be thought as an adaptation of SVM+ for solving MTL problem. The connections between SVM+ and svm+MTL are discussed and their performance is compared using synthetic data sets.

Evaluation and optimization of fMRI single-subject processing pipelines with NPAIRS and second-level CVA

In functional magnetic resonance imaging (fMRI) analysis, although the univariate general linear model (GLM) is currently the dominant approach to brain activation detection, there is growing interest in multivariate approaches such as principal component analysis, canonical variate analysis (CVA), independent component analysis and cluster analysis, which have the potential to reveal neural networks and functional connectivity in the brain. To understand the effect of processing options on performance of multivariate model-based fMRI processing pipelines with real fMRI data, we investigated the impact of commonly used fMRI preprocessing steps and optimized the associated multivariate CVA-based, single-subject processing pipelines with the NPAIRS (nonparametric prediction, activation, influence and reproducibility resampling) performance metrics [prediction accuracy and statistical parametric image (SPI) reproducibility] on the Fiswidgets platform. We also compared the single-subject SPIs of univariate GLM with multivariate CVA-based processing pipelines from SPM, FSL.FEAT, NPAIRS.GLM and NPAIRS.CVA software packages (or modules) using a novel second-level CVA. We found that for the block-design data, (a) slice timing correction and global intensity normalization have little consistent impact on the fMRI processing pipeline, but spatial smoothing, temporal detrending or high-pass filtering, and motion correction significantly improved pipeline performance across all subjects; (b) the combined optimization of spatial smoothing, temporal detrending and CVA model parameters on average improved between-subject reproducibility; and (c) the most important pipeline choices include univariate or multivariate statistical models and spatial smoothing. This study suggests that considering options other than simply using GLM with a fixed spatial filter may be of critical importance in determining activation patterns in BOLD fMRI studies.

Spatial SVM for feature selection and fMRI activation detection

This paper describes application of support vector machines (SVM) methodology for fMRI activation detection. Whereas SVM methods have been successfully used for standard predictive learning settings (i.e., classification and regression), the goal of activation detection, strictly speaking, is not achieving improved prediction accuracy. We relate the problem of activation detection in fMRI to the problem feature selection in machine learning, and describe various multivariate supervised-learning formulations for this application. Due to extreme ill-posedness of typical fMRI data sets, the quality of activation detection will be greatly affected by (a) incorporating a priori knowledge into SVM formulations, and (b) using proper encoding for training data. We analyze these issues separately, and introduce (a) novel spatial SVM formulation (reflecting a priori knowledge about local spatial correlations in fMRI data) and (b) two new encoding schemes for fMRI data that incorporate the effects of the brain dynamics (i.e., its hemodynamic response function, or HRF). The effectiveness of these modifications is clearly demonstrated using benchmark simulated and real-life fMRI data sets.

Learning Using Structured Data: Application to fMRI Data Analysis

This paper investigates a new learning setting recently introduced by Vapnik (2006) that takes into account a known structure of the training data to improve generalization performance. This setting is a special case of a new inference technology known as learning with hidden information(Vapnik, 2006) suitable for many real-life applications with sparse high-dimensional data. We first briefly describe an extension of SVM called SVMgamma+ (Vapnik, 2006) that is associated with this new learning setting, and verify its effectiveness using a synthetic data set. Then we demonstrate the effectiveness of SVMgamma+ on a difficult real-life problem: detection of cognitive states from fMRI images obtained from different subjects. These empirical results show that the SVMgamma+ approach achieves improved inter-subject generalization vs standard SVM technology.

A Java-based fMRI Processing Pipeline Evaluation System for Assessment of Univariate General Linear Model and Multivariate Canonical Variate Analysis-based Pipelines

As functional magnetic resonance imaging (fMRI) becomes widely used, the demands for evaluation of fMRI processing pipelines and validation of fMRI analysis results is increasing rapidly. The current NPAIRS package, an IDL-based fMRI processing pipeline evaluation framework, lacks system interoperability and the ability to evaluate general linear model (GLM)-based pipelines using prediction metrics. Thus, it can not fully evaluate fMRI analytical software modules such as FSL.FEAT and NPAIRS.GLM. In order to overcome these limitations, a Java-based fMRI processing pipeline evaluation system was developed. It integrated YALE (a machine learning environment) into Fiswidgets (a fMRI software environment) to obtain system interoperability and applied an algorithm to measure GLM prediction accuracy. The results demonstrated that the system can evaluate fMRI processing pipelines with univariate GLM and multivariate canonical variates analysis (CVA)-based models on real fMRI data based on prediction accuracy (classification accuracy) and statistical parametric image (SPI) reproducibility. In addition, a preliminary study was performed where four fMRI processing pipelines with GLM and CVA modules such as FSL.FEAT and NPAIRS.CVA were evaluated with the system. The results indicated that (1) the system can compare different fMRI processing pipelines with heterogeneous models (NPAIRS.GLM, NPAIRS.CVA and FSL.FEAT) and rank their performance by automatic performance scoring, and (2) the rank of pipeline performance is highly dependent on the preprocessing operations. These results suggest that the system will be of value for the comparison, validation, standardization and optimization of functional neuroimaging software packages and fMRI processing pipelines.

Evaluation and comparison of GLM- and CVA-based fMRI processing pipelines with Java-based fMRI processing pipeline evaluation system.

Activation patterns identified by fMRI processing pipelines or fMRI software packages are usually determined by the preprocessing options, parameters, and statistical models used. Previous studies that evaluated options of GLM (general linear model)--based fMRI processing pipelines are mainly based on simulated data with receiver operating characteristics (ROC) analysis, but evaluation of such fMRI processing pipelines on real fMRI data is rare. To understand the effect of processing options on performance of GLM-based fMRI processing pipelines with real fMRI data, we investigated the impact of commonly-used fMRI preprocessing steps; optimized the associated GLM-based single-subject processing pipelines; and quantitatively compared univariate GLM (in FSL.FEAT and NPAIRS.GLM) and multivariate CVA (canonical variates analysis) (in NPAIRS.CVA)-based analytic models in single-subject analysis with a recently developed fMRI processing pipeline evaluation system based on prediction accuracy (classification accuracy) and reproducibility performance metrics. For block-design data, we found that with GLM analysis (1) slice timing correction and global intensity normalization have little consistent impact on fMRI processing pipelines, spatial smoothing and high-pass filtering or temporal detrending significantly increases pipeline performance and thus are essential for robust fMRI statistical analysis; (2) combined optimization of spatial smoothing and temporal detrending improves pipeline performance; and (3) in general, the prediction performance of multivariate CVA is higher than that of the univariate GLM, while univariate GLM is more reproducible than multivariate CVA. Because of the different bias-variance trade-offs of univariate and multivariate models, it may be necessary to consider a consensus approach to obtain more accurate activation patterns in fMRI data.