Dewen Hu

Identifying major depression using whole-brain functional connectivity: a multivariate pattern analysis

Recent resting-state functional connectivity magnetic resonance imaging studies have shown significant group differences in several regions and networks between patients with major depressive disorder and healthy controls. The objective of the present study was to investigate the whole-brain resting-state functional connectivity patterns of depressed patients, which can be used to test the feasibility of identifying major depressive individuals from healthy controls. Multivariate pattern analysis was employed to classify 24 depressed patients from 29 demographically matched healthy volunteers. Permutation tests were used to assess classifier performance. The experimental results demonstrate that 94.3% (P < 0.0001) of subjects were correctly classified by leave-one-out cross-validation, including 100% identification of all patients. The majority of the most discriminating functional connections were located within or across the default mode network, affective network, visual cortical areas and cerebellum, thereby indicating that the disease-related resting-state network alterations may give rise to a portion of the complex of emotional and cognitive disturbances in major depression. Moreover, the amygdala, anterior cingulate cortex, parahippocampal gyrus and hippocampus, which exhibit high discriminative power in classification, may play important roles in the pathophysiology of this disorder. The current study may shed new light on the pathological mechanism of major depression and suggests that whole-brain resting-state functional connectivity magnetic resonance imaging may provide potential effective biomarkers for its clinical diagnosis.

Discriminative analysis of resting-state functional connectivity patterns of schizophrenia using low dimensional embedding of fMRI

Recently, a functional disconnectivity hypothesis of schizophrenia has been proposed for the physiological explanation of behavioral syndromes of this complex mental disorder. In this paper, we aim at further examining whether syndromes of schizophrenia could be decoded by some special spatiotemporal patterns of resting-state functional connectivity. We designed a data-driven classifier based on machine learning to extract highly discriminative functional connectivity features and to discriminate schizophrenic patients from healthy controls. The proposed classifier consisted of two separate steps. First, we used feature selection based on a correlation coefficient method to extract highly discriminative regions and construct the optimal feature set for classification. Then, an unsupervised-learning classifier combining low-dimensional embedding and self-organized clustering of fMRI was trained to discriminate schizophrenic patients from healthy controls. The performance of the classifier was tested using a leave-one-out cross-validation strategy. The experimental results demonstrated not only high classification accuracy (93.75% for schizophrenic patients, 75.0% for healthy controls), but also good generalization and stability with respect to the number of extracted features. In addition, some functional connectivities between certain brain regions of the cerebellum and frontal cortex were found to exhibit the highest discriminative power, which might provide further evidence for the cognitive dysmetria hypothesis of schizophrenia. This primary study demonstrated that machine learning could extract exciting new information from the resting-state activity of a brain with schizophrenia, which might have potential ability to improve current diagnosis and treatment evaluation of schizophrenia.

Rapid and brief communication: Two-dimensional locality preserving projections (2DLPP) with its application to palmprint recognition

This paper proposes a novel algorithm for image feature extraction, namely, the two-dimensional locality preserving projections (2DLPP), which directly extracts the proper features from image matrices based on locality preserving criterion. Experimental results on the PolyU palmprint database show the effectiveness of the proposed algorithm.

Discussion: Comment on: Two-dimensional locality preserving projections (2DLPP) with its application to palmprint recognition

This paper proposes a novel algorithm for image feature extraction, namely, the two-dimensional locality preserving projections (2DLPP), which directly extracts the proper features from image matrices based on locality preserving criterion. Experimental results on the PolyU palmprint database show the effectiveness of the proposed algorithm.

A Numerical-Integration Perspective on Gaussian Filters

This paper proposes a numerical-integration perspective on the Gaussian filters. A Gaussian filter is approximation of the Bayesian inference with the Gaussian posterior probability density assumption being valid. There exists a variation of Gaussian filters in the literature that derived themselves from very different backgrounds. From the numerical-integration viewpoint, various versions of Gaussian filters are only distinctive from each other in their specific treatments of approximating the multiple statistical integrations. A common base is provided for the first time to analyze and compare Gaussian filters with respect to accuracy, efficiency and stability factor. This study is expected to facilitate the selection of appropriate Gaussian filters in practice and to help design more efficient filters by employing better numerical integration methods

A Treatment-Resistant Default Mode Subnetwork in Major Depression

BACKGROUND Previous studies have suggested that the default mode network (DMN) plays a central role in the physiopathology of major depressive disorder (MDD). However, the effect of antidepressant treatment on functional connectivity within the DMN has yet to be established. Considering the very high rates of relapse in recovered subjects, we hypothesized that abnormalities in DMN functional connectivity would persist in recovered MDD subjects. METHODS Resting state functional magnetic resonance imaging images were collected from 24 MDD patients and 29 healthy control subjects. After 12 weeks of antidepressant treatment, 18 recovered MDD subjects were scanned again. Group independent component analysis was performed to decompose the resting state images into spatially independent components. Default mode subnetworks were identified using a template based on previous studies. Group differences in the ensuing subnetworks were tested using two-sample t tests. RESULTS Two spatially independent default mode subnetworks were detected in all subjects: the anterior subnetwork and the posterior subnetwork. Both subnetworks showed increased functional connectivity in pretreatment MDD subjects, relative to control subjects. Differences in the posterior subnetwork were normalized after antidepressant treatment, while abnormal functional connectivity persisted within the anterior subnetwork. CONCLUSIONS Our findings suggest a dissociation of the DMN into subnetworks, where persistent abnormal functional connectivity within the anterior subnetwork in recovered MDD subjects may constitute a biomarker of asymptomatic depression and potential for relapse.

Strapdown inertial navigation system algorithms based on dual quaternions

The design of strapdown inertial navigation system (INS) algorithms based on dual quaternions is addressed. Dual quaternion is a most concise and efficient mathematical tool to represent rotation and translation simultaneously, i.e., the general displacement of a rigid body. The principle of strapdown inertial navigation is represented using the tool of dual quaternion. It is shown that the principle can be expressed by three continuous kinematic equations in dual quaternion. These equations take the same form as the attitude quaternion rate equation. Subsequently, one new numerical integration algorithm is structured to solve the three kinematic equations, utilizing the traditional two-speed approach originally developed in attitude integration. The duality between the coning and sculling corrections, raised in the recent literature, can be essentially explained by splitting the new algorithm into the corresponding rotational and translational parts. The superiority of the new algorithm over conventional ones in accuracy is analytically derived. A variety of simulations are carried out to support the analytic results. The numerical results agree well with the analyses. The new algorithm turns out to be a better choice than any conventional algorithm for high-precision navigation systems and high-maneuver applications. Several guidelines in choosing a suitable navigation algorithm are also provided.

A novel hybrid BCI speller based on the incorporation of SSVEP into the P300 paradigm

OBJECTIVE Although extensive studies have shown improvement in spelling accuracy, the conventional P300 speller often exhibits errors, which occur in almost the same row or column relative to the target. To address this issue, we propose a novel hybrid brain-computer interface (BCI) approach by incorporating the steady-state visual evoked potential (SSVEP) into the conventional P300 paradigm. APPROACH We designed a periodic stimuli mechanism and superimposed it onto the P300 stimuli to increase the difference between the symbols in the same row or column. Furthermore, we integrated the random flashings and periodic flickers to simultaneously evoke the P300 and SSVEP, respectively. Finally, we developed a hybrid detection mechanism based on the P300 and SSVEP in which the target symbols are detected by the fusion of three-dimensional, time-frequency features. MAIN RESULTS The results obtained from 12 healthy subjects show that an online classification accuracy of 93.85% and information transfer rate of 56.44 bit/min were achieved using the proposed BCI speller in only a single trial. Specifically, 5 of the 12 subjects exhibited an information transfer rate of 63.56 bit/min with an accuracy of 100%. SIGNIFICANCE The pilot studies suggested that the proposed BCI speller could achieve a better and more stable system performance compared with the conventional P300 speller, and it is promising for achieving quick spelling in stimulus-driven BCI applications.

Generalised filtering and stochastic DCM for fMRI.

This paper is about the fitting or inversion of dynamic causal models (DCMs) of fMRI time series. It tries to establish the validity of stochastic DCMs that accommodate random fluctuations in hidden neuronal and physiological states. We compare and contrast deterministic and stochastic DCMs, which do and do not ignore random fluctuations or noise on hidden states. We then compare stochastic DCMs, which do and do not ignore conditional dependence between hidden states and model parameters (generalised filtering and dynamic expectation maximisation, respectively). We first characterise state-noise by comparing the log evidence of models with different a priori assumptions about its amplitude, form and smoothness. Face validity of the inversion scheme is then established using data simulated with and without state-noise to ensure that DCM can identify the parameters and model that generated the data. Finally, we address construct validity using real data from an fMRI study of internet addiction. Our analyses suggest the following. (i) The inversion of stochastic causal models is feasible, given typical fMRI data. (ii) State-noise has nontrivial amplitude and smoothness. (iii) Stochastic DCM has face validity, in the sense that Bayesian model comparison can distinguish between data that have been generated with high and low levels of physiological noise and model inversion provides veridical estimates of effective connectivity. (iv) Relaxing conditional independence assumptions can have greater construct validity, in terms of revealing group differences not disclosed by variational schemes. Finally, we note that the ability to model endogenous or random fluctuations on hidden neuronal (and physiological) states provides a new and possibly more plausible perspective on how regionally specific signals in fMRI are generated.

Unscented Kalman filtering for additive noise case: augmented versus nonaugmented

This paper concerns the unscented Kalman filtering (UKF) for the nonlinear dynamic systems with additive process and measurement noises. It is widely accepted for such a case that the system state needs not to be augmented with noise vectors and the resultant nonaugmented UKF yields similar, if not the same, results to the augmented UKF. In this letter, we find that under the condition of n+/spl kappa/=const, the basic difference between them is that the augmented UKF draws a sigma set only once within a filtering recursion, while the nonaugmented UKF has to redraw a new set of sigma points to incorporate the effect of additive process noise. This difference generally favors the augmented UKF in that the odd-order moment information is partly captured by the nonlinearly transformed sigma points and propagated throughout the recursion. The simulation results agree well with the analyses.