A.-K. Seghouane

University of Melbourne, Melbourne, Victoria, Australia

Are you A.-K. Seghouane?

Claim your profile

Publications (43)33.84 Total impact

  • A.-K. Seghouane · A. Shah
    [Show abstract] [Hide abstract]
    ABSTRACT: Different approaches have been considered so far for non-parametric Hemodynamic Response Function (HRF) estimation in noisy functional Magnetic Resonance Imaging (fMRI). However, very few methods have considered the temporal correlation of the fMRI times series when estimating the HRF as most of these methods use a Gaussian white noise model. In this paper, this issue is addressed by modeling the noise in fMRI times series by an autoregressive model of order one (AR(1)). Making use of a semiparametric model to characterize the fMRI time series and the AR(1) to model the temporally correlated noise, a generalized least squares estimator for voxelwise consistent non-parametric HRF estimation is derived in this paper. The proposed error structure estimation method has the advantage of not involving any nonparametric estimation. The effectiveness of the proposed HRF estimation procedure is illustrated on both simulated and experimental fMRI data from a finger tapping experiment.
    No preview · Article · Jul 2015
  • M.U. Khalid · A.-K. Seghouane
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose an effective technique to analyze task-based functional connectivity across multiple subjects for functional magnetic resonance imaging (fMRI) data. Instead of applying the assumption of group-independence or multiset correlation maximization, an alternative approach is adopted based on a combined framework of sparse dictionary learning (SDL) and multi-set canonical correlation analysis (MCCA) to obtain connectivity maps. The proposed technique encapsulates commonality and uniqueness solely based on sparsity of cross dataset corresponding components. It is validated using real fMRI data and its superior performance is illustrated using a simulation study, which shows its better capability in obtaining connectivity maps that are more specific.
    No preview · Article · Jul 2015
  • M. Hanif · A.-K. Seghouane
    [Show abstract] [Hide abstract]
    ABSTRACT: Image restoration is a significant inverse problem in image processing community. We present an iterative alternating minimization of Kullback Leibler divergence (KLD) for an optimized image denoising. It is obtained by modeling the original image and the additive noise as multivariate Gaussian processes with unknown covariance matrices in wavelet domain. The original image and noise parameters are estimated by minimizing KLD between a model family of probability distributions defined using the linear image degradation model and a desired family of probability distributions constrained to be concentrated on the observed noisy image. The wavelet coefficients are modeled using the class of Gaussian Scale Mixture (GSM), which represents the heavy-tailed statistical distribution, suitable for natural images. The algorithm provides closed form expressions for the parameters updates and converge only in few iterations. The efficiency of proposed method is demonstrated through numerical simulations, both visually and in terms of signal to noise ratio.
    No preview · Article · Jan 2015
  • M. Hanif · A.-K. Seghouane
    [Show abstract] [Hide abstract]
    ABSTRACT: Blurring is a common source of image degradation in many applications. Blind image deblurring (BID) is an apposite approach for blur removal in real images. Being an ill-posed linear inverse problem, a regularized and well constrained approach is required for a credible solution of BID model. Recently sparse representation base modeling emerged as an efficacious tool in image processing community, with application as regularizer in inverse problems. In this work the sparsity constraint is fused with the non-negative matrix approximation to address the BID problem. An alternative-iterative frame work is developed to estimate the non-negative sparse approximation of the sharp image and blurring kernel. With sparsity constraint, an estimate of the sharp image is obtained without solving the ill-posed deconvolution model. Although similar formulation has been proposed but unlike other BID methods the proposed approach is parameter free and requires no prior statistics. The experimental results validate comparatively better performance of proposed method against the other methods.
    No preview · Article · Jan 2015
  • Adnan Shah · A.-K. Seghouane
    [Show abstract] [Hide abstract]
    ABSTRACT: Non-parametric hemodynamic response function (HRF) estimation in noisy functional near-infrared spectroscopy (fNIRS) plays an important role when investigating the temporal dynamics of a brain region response during activations. Assuming the drift Lipschitz continuous; a new algorithm for non-parametric HRF estimation from the oxygenated (HbO) and deoxygenated (HbR) fNIRS time-series is derived in this paper. The proposed algorithm estimates the HRF by applying a first order differencing to the fNIRS time series samples. It is shown that the proposed HRF estimator is √N consistent. Its performance is assessed using both simulated and a real fNIRS data set obtained from a motor activity experiment. The application results reveal that the proposed HRF estimation method is efficient both computationally and in terms of accuracy.
    No preview · Conference Paper · Oct 2013
  • A. Shah · A.-K. Seghouane
    [Show abstract] [Hide abstract]
    ABSTRACT: Extracting region-specific hemodynamic response function (HRF) from overlapping ROIs of activated areas in the brain in noisy functional Magnetic Resonance Imaging (fMRI) data is essential when analyzing the temporal dynamics of a brain region response and its neuronal coupling for functional and effective connectivity. Based on the assumption of spatially sparse brain hemodynamics, HRFs from jointly activated overlapping regions are separated based on sparse dictionary learning. The proposed HRF estimation procedure is tested on both simulated and real fMRI data. The results reveal the efficiency of the proposed method in separating temporally-dependent inter-region HRFs from fMRI data.
    No preview · Conference Paper · Jan 2013
  • A.-K. Seghouane · A. Shah
    [Show abstract] [Hide abstract]
    ABSTRACT: Non-parametric hemodynamic response function (HRF) estimation in noisy functional Magnetic Resonance Imaging (fMRI) plays an important role when investigating the temporal dynamic of a brain region response during activations. Assuming the drift Lipschitz continuous; a new algorithm for non-parametric HRF estimation is derived in this paper. The proposed algorithm estimates the HRF by applying a first order differencing to the fMRI time series samples. It is shown that the proposed HRF estimator is √(N) consistent. Its performance is assessed using both simulated and a real fMRI data sets obtained from an event-related fMRI experiment. The application results reveal that the proposed HRF estimation method is efficient both computationally and in term of accuracy.
    No preview · Conference Paper · Jan 2013
  • A.-K. Seghouane
    [Show abstract] [Hide abstract]
    ABSTRACT: When neural activity increases in a region of the brain, the local magnetic resonance signal produced in that part of the brain increases by a small amount owing to changes in blood oxygenation. This blood oxygenation level dependent (BOLD) effect is the basis for most functional magnetic resonance imaging (fMRI) studies done today to map patterns of activation in the working human brain. In this tutorial we will review the main techniques used to analyze fMRI data.
    No preview · Conference Paper · Jan 2013
  • M.U. Khalid · A.-K. Seghouane
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper a novel framework that combines data-driven methods is proposed for functional connectivity analysis of functional magnetic resonance imaging (fMRI) data. The basic idea is to overcome the shortcomings of compressed sensing based data-driven method by incorporating canonical correlation analysis (CCA) to extract a more meaningful temporal profile that is based solely on underlying brain hemodynamics, which can be further investigated to detect functional connectivity using regression analysis. We apply our method on synthetic and task-related fMRI data to show that the combined framework which better adapts to individual variations of distinct activity patterns in the brain is an effective approach to reveal functionally connected brain regions.
    No preview · Conference Paper · Jan 2013
  • A. Shah · A.-K. Seghouane
    [Show abstract] [Hide abstract]
    ABSTRACT: Discriminating between active and non-active brain voxels in noisy functional magnetic resonance imaging (fMRI) data plays an important role when investigating task-related activations of the neuronal sites. A novel method for efficiently capturing drifts in the functional magnetic resonance imaging (fMRI) data is presented that leads to enhanced fMRI activation detection. The proposed algorithm apply a first order differencing to the fMRI time series samples in order to remove the drift effect. Using linear least-squares, a consistent hemodynamic response function (HRF) of the fMRI voxel is estimated as a first-step that leads to an optimal estimate of the drift based on a wavelet thresholding technique. The de-drifted fMRI voxel response is then obtained by removing the estimated drift from the fMRI time-series. Its performance is assessed using a visual task real fMRI data set. The application results reveal that the proposed method, which avoids the selection of a model to remove the drift component, leads to an improved activation detection performance in fMRI data.
    No preview · Conference Paper · Jan 2013
  • Muhammad Hanif · A.-K. Seghouane
    [Show abstract] [Hide abstract]
    ABSTRACT: Image restoration (deconvolution) is a basic step for image processing, analysis and computer vision. We addressed blurred image deconvolution problem using Expectation maximization (EM) based approach in the wavelet domain. The sparsity property of wavelet coefficients is modelled using the class of Gaussian Scale Mixture (GSM), which represents the heavy-tailed statistical distribution. The maximum a posterior (MAP) estimate is computed using EM, where scale factors of GSM plays the role of hidden variables. The estimated hidden scaling variables are then used to restore the original image. Although similar formulations have been proposed before but the resulting optimization problems have been computationally demanding and sometimes depends heavily on the initial values of parameters. We proposed an optimized Bayesian approach in wavelet domain to restore an image degraded by linear distortion (e.g., blur) and additive Gaussian noise. Simulation results are presented to demonstrate the quality of our method, over a wide range of blur and noise level, both visually and in terms of signal to noise ratio.
    No preview · Conference Paper · Dec 2012
  • A.-K. Seghouane · Muhammad Usman Khalid
    [Show abstract] [Hide abstract]
    ABSTRACT: Brain networks explore the dependence relationships between brain regions under consideration through the estimation of the precision matrix. An approach based on linear regression is adopted here for estimating the partial correlation matrix from functional brain imaging data. Knowing that brain networks are sparse and hierarchical, the l1-norm penalized regression has been used to estimate sparse brain networks. Although capable of including the sparsity information, the l1-norm penalty alone doesn't incorporate the hierarchical structure prior information when estimating brain networks. In this paper, a new l1 regularization method that applies the sparsity constraint at hierarchical levels is proposed and its implementation described. This hierarchical sparsity approach has the advantage of generating brain networks that are sparse at all levels of the hierarchy. The performance of the proposed approach in comparison to other existing methods is illustrated on real fMRI data.
    No preview · Conference Paper · Sep 2012
  • A.-K. Seghouane
    [Show abstract] [Hide abstract]
    ABSTRACT: A fundamental question in functional MRI (fMRI) data analysis is to declare pixels either activated or non-activated with respect to the experimental design. A new statistical test for detecting activated pixels in fMRI data is proposed. The test is based on comparing the dimension of the parametric models fitted to the voxels fMRI time series data with and without controlled activation-baseline pattern. A corrected variant of the Akaike information criterion, is used for this comparison. This test has the advantage of not requiring any user-specified threshold to be estimated. The effectiveness of the proposed fMRI activation detection method is illustrated on real experimental data.
    No preview · Conference Paper · Jan 2012
  • A.-K. Seghouane · M. Hanif
    [Show abstract] [Hide abstract]
    ABSTRACT: A new algorithm for wavelet-based blind image restoration is presented in this paper. It is obtained by defining an intermediate variable to characterize the original image. Both the original image and the additive noise are modeled by multivariate Gaussian process. The blurring process is specified by its point spread function, which is unknown. The original image and the blur are estimated by alternating minimization of the KullbackLeibler divergence between a model family of probability distributions defined using a linear image model and a desired family of probability distributions constrained to be concentrated on the observed data. The intermediate variable is used to introduce regularization in the algorithm. The algorithm presents the advantage to provide closed form expressions for the parameters to be updated and to converge only after few iterations. A simulation example that illustrates the effectiveness of the proposed algorithm is presented.
    No preview · Conference Paper · Jan 2012
  • M.U. Khalid · A. Shah · A.-K. Seghouane
    [Show abstract] [Hide abstract]
    ABSTRACT: The univariate approach without a smoothing filter for detecting activation patterns in functional magnetic resonance imaging (fMRI) data suffers from a low sensitivity due to presence of high noise. The poor performance of univariate methods such as ordinary correlation is due to lack of their ability to take advantage of spatial correlation that exists in fMR images among group of neighboring voxels. To rectify this problem multivariate approaches such as canonical correlation analysis (CCA), adaptive canonical correlation analysis (ACCA) and spatial Gaussian smoothing accompanied with univariate correlation has already been applied to fMR images to improve both sensitivity and specificity. In this work idea of smoothing fMR images with ACCA has been extended to adaptive two-dimensional canonical correlation analysis (A2DCCA) to obtain improvements in detection performance in terms of specificity. It is shown on synthetic and real fMRI data that A2DCCA produces better specificity than ACCA and Gaussian smoothing.
    No preview · Conference Paper · Jan 2012
  • A.-K. Seghouane
    [Show abstract] [Hide abstract]
    ABSTRACT: Estimation of the expected Kullback-Leibler information is the basis for deriving the Akaike information criterion (AIC) and its corrected version AIC c . Both criteria were designed for selecting multivariate regression models with an appropriateness of AIC c for small sample cases. In the work presented here, two new small sample AIC corrections are derived for multivariate regression model selection. The proposed AIC corrections are based on asymptotic approximation of bootstrap-type estimates of Kullback-Leibler information. These new corrections are of particular interest when the use of bootstrap is not really justified in terms of the required calculations. As it is the case for AIC c , the new proposed criteria are asymptotically equivalent to AIC. Simulation results demonstrate that in small sample size settings, one of the proposed criterion provides better model choices than other available model selection criteria. As a result, this proposed criterion serves as an effective tool for selecting a model of appropriate order. Asymptotic justifications for the proposed criteria are provided in the Appendix.
    No preview · Article · May 2011 · IEEE Transactions on Aerospace and Electronic Systems
  • A.-K. Seghouane
    [Show abstract] [Hide abstract]
    ABSTRACT: A new algorithm for Maximum likelihood blind image restoration is presented in this paper. It is obtained by modeling the original image and the additive noise as multivariate Gaussian processes with unknown covariance matrices. The blurring process is specified by its point spread function, which is also unknown. Estimations of the original image and the blur are derived by alternating minimization of the Kullback-Leibler divergence. The algorithm presents the advantage to provide closed form expressions for the parameters to be updated and to converge only after few iterations. A simulation example that illustrates the effectiveness of the proposed algorithm is presented.
    No preview · Conference Paper · Oct 2010
  • A.-K. Seghouane · Ju Lynn Ong
    [Show abstract] [Hide abstract]
    ABSTRACT: Existing polyp detection methods rely heavily on curvature-based characteristics to differentiate between lesions. However, as curvature is a local feature and a second order differential quantity, simply inspecting the curvature at a point is not sufficient. In this paper, we propose to inspect a local neighbourhood around a candidate point using curvature maps. This candidate point is pre-identified using the geodesic centroid of a surface patch containing vertices with positive point curvature values corresponding to convex shaped protrusions. Geodesic rings are then constructed around this candidate point and point curvatures around these rings are accumulated to produce curvature maps. From this, a cumulative shape property, S for a given neighbourhood radius can be computed and used for identifying bulbous polyps which typically have a high S value, and its corresponding 'neck' region. We show that a threshold value of S > 0.48 is sufficient to discriminate between polyps and non polyps with 100% sensitivity and specificity for bulbous polyps > 10mm.
    No preview · Conference Paper · Oct 2010
  • A.-K. Seghouane · Ju Lynn Ong
    [Show abstract] [Hide abstract]
    ABSTRACT: Computed tomographic colonography (CTC) is a promising alternative to traditional invasive colonoscopic methods used in the detection and removal of cancerous growths, or polyps in the colon. Existing algorithms for CTC typically use a classifier to discriminate between true and false positives generated by a polyp candidate detection system. However, these classifiers often suffer from a phenomenon termed the curse of dimensionality, whereby there is a marked degradation in the performance of a classifier as the number of features used in the classifier is increased. In addition an increase in the number of features used also contributes to an increase in computational complexity and demands on storage space. This paper demonstrates the benefits of feature selection with the aim at increasing specificity while preserving sensitivity in a polyp detection system. It also compares the performances of an individual (F-score) and mutual information (MI) method for feature selection on a polyp candidate database, in order to select a subset of features for optimum CAD performance. Experimental results show that the performance of SVM+MI seems to be better for a small number of features used, but the SVM+Fscore method seems to dominate when using the 30-50 best ranked features. On the whole, the AUC measures are able to reach 0.8-0.85 for the top ranked 20-40 features using MI or F-score methods compared with 0.65-0.7 when using all 100 features in the worst-case scenario.
    No preview · Conference Paper · Oct 2010
  • A.-K. Seghouane · Ju Lynn Ong
    [Show abstract] [Hide abstract]
    ABSTRACT: The description of lesion shapes with curvature-based features is a widespread approach in polyp detection methods. These methods are motivated by the need to compactly and accurately encode the different existing shape forms on the colon wall. However, the colon wall presents a number of small convex shape that resemble polyps which increases drastically the number of false positive (FP) detected. In this paper a method based on multiresolution shape processing using the spherical wavelet transform is proposed. The method aims to reduce the number of FPs detected while preserving true positives. Simulation results illustrating the effectiveness of the method are presented.
    No preview · Conference Paper · Aug 2009

Publication Stats

270 Citations
33.84 Total Impact Points

Institutions

  • 2013
    • University of Melbourne
      Melbourne, Victoria, Australia
  • 2006-2012
    • Australian National University
      • College of Engineering & Computer Science
      Canberra, Australian Capital Territory, Australia
  • 2007-2010
    • National ICT Australia Ltd
      Sydney, New South Wales, Australia
  • 2004-2005
    • National Institute for Research in Computer Science and Control
      Le Chesney, Île-de-France, France
  • 2001-2004
    • École Supérieure d'Electricité
      Gif, Île-de-France, France