References of "Schrouff, Jessica"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailCan we interpret linear kernel machine learning models using anatomically labelled regions?
Schrouff, Jessica ULg; Monteiro, Joao; Joao Rosa, Maria et al

Poster (2014, June)

Detailed reference viewed: 19 (1 ULg)
Full Text
Peer Reviewed
See detailBiased binomial assessment of cross-validated estimation of classification accuracies illustrated in diagnosis predictions
Noirhomme, Quentin ULg; Lesenfants, Damien ULg; Gomez, Francisco et al

in NeuroImage: Clinical (2014), 4

Multivariate classification is used in neuroimaging studies to infer brain activation or in medical applications to infer diagnosis. Their results are often assessed through either a binomial or a ... [more ▼]

Multivariate classification is used in neuroimaging studies to infer brain activation or in medical applications to infer diagnosis. Their results are often assessed through either a binomial or a permutation test. Here, we simulated classification results of generated random data to assess the influence of the cross-validation scheme on the significance of results. Distributions built from classification of random data with crossvalidation did not follow the binomial distribution. The binomial test is therefore not adapted. On the contrary, the permutation test was unaffected by the cross-validation scheme. The influence of the crossvalidation was further illustrated on real-data from a brain–computer interface experiment in patients with disorders of consciousness and from an fMRI study on patients with Parkinson disease. Three out of 16 patients with disorders of consciousness had significant accuracy on binomial testing, but only one showed significant accuracy using permutation testing. In the fMRI experiment, the mental imagery of gait could discriminate significantly between idiopathic Parkinson’s disease patients and healthy subjects according to the permutation test but not according to the binomial test. Hence, binomial testing could lead to biased estimation of significance and false positive or negative results. In our view, permutation testing is thus recommended for clinical application of classification with cross-validation. [less ▲]

Detailed reference viewed: 23 (3 ULg)
Full Text
Peer Reviewed
See detailAssessing the quality of Experimental Data with Gaussian Processes: Example with an Injection Scroll Compressor
Quoilin, Sylvain ULg; Schrouff, Jessica ULg

in Proceedings of the 2014 Purdue Conferences (2014)

This paper describes an experimental study carried out on a refrigeration scroll compressor with and without vapour injection. The test rig designed for that purposed allows evaluating the performance ... [more ▼]

This paper describes an experimental study carried out on a refrigeration scroll compressor with and without vapour injection. The test rig designed for that purposed allows evaluating the performance over a wide range of operating conditions, by varying the supply pressure, the injection pressure, the discharge pressure, the supply superheating and the injection superheating. 97 Steady-state points are measured, with a maximum isentropic efficiency of 64.1% and a maximum consumed electrical power of 13.1 kW. A critical analysis of the experimental results is then carried out to evaluate the quality of the data using a machine learning method. This method based on Gaussian Processes regression, is used to build a statistical operating map of the compressor as a function of the different inputs. This statistical operating map can then be compared to the experimental data points to evaluate their accuracy. [less ▲]

Detailed reference viewed: 16 (0 ULg)
Full Text
Peer Reviewed
See detailMultivariate pattern interpretation using PRoNTo
Schrouff, Jessica ULg; Rosa, Maria; Rondina, Jane et al

Poster (2013, June)

Recently, machine learning models have been applied to neuroimaging data, allowing to make predictions about a variable of interest based on the pattern of activation or anatomy over a set of voxels. In ... [more ▼]

Recently, machine learning models have been applied to neuroimaging data, allowing to make predictions about a variable of interest based on the pattern of activation or anatomy over a set of voxels. In addition, they might lead to an increased sensitivity to detect the presence of a particular mental representation compared to univariate methods such as the General Linear Model (GLM). Application of these methods made it possible to decode the category of a seen object or the orientation of a striped pattern seen by the subject. They also allowed classification of patients and healthy controls and could therefore be used as a diagnostic tool due to their ability to predict the class of an unseen sample. The main disadvantage of multivariate machine learning models is that local inference with respect to the brain neuroanatomy is complex: although linear models generate weights for each voxel, the model predictions are based on the whole pattern and therefore one cannot threshold the weights to make regional statistical inferences as in univariate analysis. In the present work, we developed a methodology based on a labelled anatomical template (e.g. AAL or Brodmann) to display a smoothed version of the model weights and compute a ranking of the regions according their contribution to the predictive model. This work is distributed in PRoNTo (Pattern Recognition for Neuroimaging Toolbox), a user-friendly toolbox, making machine learning models available to every neuroscientist. [less ▲]

Detailed reference viewed: 42 (4 ULg)
Full Text
See detailPattern Recognition in NeuroImaging: What can machine learning classifiers bring to the analysis of functional brain imaging?
Schrouff, Jessica ULg

Doctoral thesis (2013)

The study of the brain development and functioning raises many question that are tracked using neuroimaging techniques such as positron emission tomography or (functional) magnetic resonance imaging ... [more ▼]

The study of the brain development and functioning raises many question that are tracked using neuroimaging techniques such as positron emission tomography or (functional) magnetic resonance imaging. During the last decades, various techniques have been developed to analyse neuroimaging data. These techniques brought valuable insight on neuroscientific questions, but encounter limitations which make them unsuitable to tackle more complex problems. More recently, machine learning based models, coming from the field of pattern recognition, have been promisingly applied to neuroimaging data. In this work, the assets and limitations of machine learning based models were investigated and compared to previously developed techniques. To this end, two applications involving challenging datasets were defined and the results from widespread methods were compared to the results obtained using machine learning based modelling. More specifically, the first application addressed a research question: Is it possible to detect and characterize mnemonic traces? The fMRI experiment comprised a learning and a control tasks, both flanked by rest sessions. From previous studies, patterns of brain activity generated during the learning task should be spontaneously repeated during the following rest session, while no difference should be observed between the pre- and post-task rest session in the control condition. Using univariate and multivariate feature selection steps before a Gaussian Processes classification, mnemonic traces could be detected and their spatio-temporal evolution characterized. On the contrary, an analysis of the rest sessions based on the detection of independent networks did not provide any results supporting the theory of memory consolidation. The second application tackled a clinical issue: Can a pattern of brain activation characteristic to idiopathic Parkinson’s disease be detected and localized? The dataset considered to address this question comprised the fMRI images of aged healthy subjects and Parkinsonian patients while they were performing a task of mental imagery of gait at three different paces. The signal comprised in a priori selected regions of interest allowed for the support vector machines classification of healthy and diseased volunteers with an accuracy of 86%. To localize the discriminating pattern, a methodology based on the weight in labelled regions (e.g. from the anatomical automatic labelling or Brodmann atlases) was developed, which enabled the comparison between univariate and multivariate results and showed a nice overlap between them. Furthermore, models could then be compared quantitatively in terms of pattern localization, using a specifically defined measure of distance. This measure could then be used to compare the patterns generated from different folds of a same model, from different feature sets, or from different modelling techniques. The present study concluded that machine learning models can clearly and fruitfully complement other analysis techniques to tackle challenging questions in neuroscience. On the other hand, more work is needed in order to render the methodology fully accessible to the neuroscientific community. [less ▲]

Detailed reference viewed: 228 (39 ULg)
Full Text
Peer Reviewed
See detailPRoNTo: Pattern Recognition for Neuroimaging Toolbox
Schrouff, Jessica ULg; Rosa, Maria Joao; Rondina, Jane et al

in Neuroinformatics (2013)

In the past years, mass univariate statistical analyses of neuroimaging data have been complemented by the use of multivariate pattern analyses, especially based on machine learning models. While these ... [more ▼]

In the past years, mass univariate statistical analyses of neuroimaging data have been complemented by the use of multivariate pattern analyses, especially based on machine learning models. While these allow an increased sensitivity for the detection of spatially distributed effects compared to univariate techniques, they lack an established and accessible software framework. The goal of this work was to build a toolbox comprising all the necessary functionalities formultivariate analyses of neuroimaging data, based on machine learning models. The “Pattern Recognition for Neuroimaging Toolbox” (PRoNTo) is open-source, cross-platform, MATLAB-based and SPM compatible, therefore being suitable for both cognitive and clinical neuroscience research. In addition, it is designed to facilitate novel contributions from developers, aiming to improve the interaction between the neuroimaging and machine learning communities. Here, we introduce PRoNTo by presenting examples of possible research questions that can be addressed with the machine learning framework implemented in PRoNTo, and cannot be easily investigated with mass univariate statistical analysis. [less ▲]

Detailed reference viewed: 178 (44 ULg)
Full Text
Peer Reviewed
See detailMulticlass classification of FDG PET scans for the distinction between Parkinson's disease and atypical parkinsonian syndromes
Garraux, Gaëtan ULg; Phillips, Christophe ULg; Schrouff, Jessica ULg et al

in NeuroImage: Clinical (2013), 2

Most available pattern recognition methods in neuroimaging address binary classification problems. Here, we used relevance vector machine (RVM) in combination with booststrap resampling (‘bagging’) for ... [more ▼]

Most available pattern recognition methods in neuroimaging address binary classification problems. Here, we used relevance vector machine (RVM) in combination with booststrap resampling (‘bagging’) for non-hierarchical multiclass classification. The method was tested on 120 cerebral 18fluorodeoxyglucose (FDG) positron emission tomography (PET) scans performed in patients who exhibited parkinsonian clinical features for 3.5 years on average but that were outside the prevailing perception for Parkinson's disease (PD). A radiological diagnosis of PD was suggested for 30 patients at the time of PET imaging. However, at follow-up several years after PET imaging, 42 of them finally received a clinical diagnosis of PD. The remaining 78 APS patients were diagnosed with multiple system atrophy (MSA, N = 31), progressive supranuclear palsy (PSP, N = 26) and corticobasal syndrome (CBS, N = 21), respectively. With respect to this standard of truth, classification sensitivity, specificity, positive and negative predictive values for PD were 93% 83% 75% and 96%, respectively using binary RVM (PD vs. APS) and 90%, 87%, 79% and 94%, respectively, using multiclass RVM (PD vs. MSA vs. PSP vs. CBS). Multiclass RVM achieved 45%, 55% and 62% classification accuracy for, MSA, PSP and CBS, respectively. Finally, a majority confidence ratio was computed for each scan on the basis of class pairs that were the most frequently assigned by RVM. Altogether, the results suggest that automatic multiclass RVM classification of FDG PET scans achieves adequate performance for the early differentiation between PD and APS on the basis of cerebral FDG uptake patterns when the clinical diagnosis is felt uncertain. This approach cannot be recommended yet as an aid for distinction between the three APS classes under consideration. [less ▲]

Detailed reference viewed: 38 (11 ULg)
Full Text
Peer Reviewed
See detailConcurrent Synaptic and Systems Memory Consolidation during Sleep
Mascetti, Laura; Foret, Ariane; Schrouff, Jessica ULg et al

in Journal of Neuroscience (2013), 33(24), 10182-10190

Memories are consolidated during sleep by two apparently antagonistic processes: (1) reinforcement of memory-specific cortical interactions and (2) homeostatic reduction in synaptic efficiency. Using fMRI ... [more ▼]

Memories are consolidated during sleep by two apparently antagonistic processes: (1) reinforcement of memory-specific cortical interactions and (2) homeostatic reduction in synaptic efficiency. Using fMRI, we assessed whether episodic memories are processed during sleep by either or both mechanisms, by comparing recollection before and after sleep. We probed whether LTP influences these processes by contrasting two groups of individuals prospectively recruited based on BDNF rs6265 (Val66Met) polymorphism. Between immediate retrieval and delayed testing scheduled after sleep, responses to recollection increased significantly more in Val/Val individuals than in Met carriers in parietal and occipital areas not previously engaged in retrieval, consistent with “systems-level consolidation.” Responses also increased differentially between allelic groups in regions already activated before sleep but only in proportion to slow oscillation power, in keeping with “synaptic downscaling.” Episodic memories seem processed at both synaptic and systemic levels during sleep by mechanisms involving LTP. [less ▲]

Detailed reference viewed: 25 (4 ULg)
Full Text
Peer Reviewed
See detailLocalizing and comparing weight maps generated from linear kernel machine learning models
Schrouff, Jessica ULg; CREMERS, Julien ULg; GARRAUX, Gaëtan ULg et al

in 2013 Third International Workshop on Pattern Recognition in NeuroImaging (PRNI 2013): proceedings (2013)

Recently, machine learning models have been applied to neuroimaging data, allowing to make predictions about a variable of interest based on the pattern of activation or anatomy over a set of voxels ... [more ▼]

Recently, machine learning models have been applied to neuroimaging data, allowing to make predictions about a variable of interest based on the pattern of activation or anatomy over a set of voxels. These pattern recognition based methods present undeniable assets over classical (univariate) techniques, by providing predictions for unseen data, as well as the weights of each voxel in the model. However, the obtained weight map cannot be thresholded to perform regionally specific inference, leading to a difficult localization of the variable of interest. In this work, we provide local averages of the weights according to regions defined by anatomical or functional atlases (e.g. Brodmann atlas). These averages can then be ranked, thereby providing a sorted list of regions that can be (to a certain extent) compared with univariate results. Furthermore, we defined a “ranking distance”, allowing for the quantitative comparison between localized patterns. These concepts are illustrated with two datasets. [less ▲]

Detailed reference viewed: 22 (4 ULg)
Full Text
Peer Reviewed
See detailPattern Recognition for Neuroimaging Toolbox
Schrouff, Jessica ULg; Rosa, Maria; Rondina, Jane et al

in Suykens, J.A.K.; Argyriou, A.; De Brabanter, K. (Eds.) et al International workshop on advances in Regularization, Optimization, Kernel Methods and Support Vector Machines: theory and applications (ROKS 2013), Book of Abstracts (2013)

In the past years, mass univariate statistical analyses of neuroimaging data have been complemented by the use of multivariate pattern analyses, especially based on machine learning models. While these ... [more ▼]

In the past years, mass univariate statistical analyses of neuroimaging data have been complemented by the use of multivariate pattern analyses, especially based on machine learning models. While these allow an increased sensitivity for the detection of spatially distributed e ffects compared to univariate techniques, they lack an established and accessible software framework. Here we introduce the \Pattern Recognition for Neuroimaging Toolbox" (PRoNTo), an open-source, cross-platform and MATLAB-based software comprising many necessary functionalities for machine learning modelling of neuroimaging data. [less ▲]

Detailed reference viewed: 36 (1 ULg)
Full Text
Peer Reviewed
See detailDiscriminant BOLD Activation Patterns during Mental Imagery in Parkinson’s Disease
Schrouff, Jessica ULg; Cremers, Julien ULg; D'Ostilio, Kevin ULg et al

in Proceedings of MLINI 2012 (2012, December 07)

Using machine learning based models in clinical applications has become current practice and can prove useful to provide information at the subject’s level, such as predicting an (early) diagnosis or ... [more ▼]

Using machine learning based models in clinical applications has become current practice and can prove useful to provide information at the subject’s level, such as predicting an (early) diagnosis or monitoring the evolution of a disease. However, the performance of these models depends on the choice of a biomarker to detect the presence or absence of a disease. Choosing a biomarker is not straightforward, especially in the case of Parkinson’s disease when compared to healthy subjects. In the present work, we investigated the mental imagery of gait as a biomarker of Parkinson’s disease and showed that the signal in the mesencephalic locomotor region during the mental imagery of gait at a comfortable pace can discriminate significantly between idiopathic Parkinson’s disease patients and healthy subjects. Although there is room for improvement, the results of this preliminary study are promising. [less ▲]

Detailed reference viewed: 107 (29 ULg)
Full Text
Peer Reviewed
See detailDecoding spontaneous brain activity from fMRI using Gaussian Processes: tracking brain reactivation
Schrouff, Jessica ULg; Kussé, Caroline ULg; Wehenkel, Louis ULg et al

in 2012 Second International Workshop on Pattern Recognition in NeuroImaging (PRNI 2012): proceedings (2012, July 03)

While Multi-Variate Pattern Analysis techniques based on machine learning have now been regularly applied to neuroimaging data, decoding brain activity is usually performed in highly controlled ... [more ▼]

While Multi-Variate Pattern Analysis techniques based on machine learning have now been regularly applied to neuroimaging data, decoding brain activity is usually performed in highly controlled experimental paradigms. In more realistic conditions, the number, sequence and duration of mental states are unpredictably generated by the individual, resulting in complex and imbalanced fMRI data sets. Moreover, in the case of spontaneous brain activity, the mental states can not be linked to any external or internal stimulation, which makes it a highly difficult condition to decode. This study tests the classification of brain activity, acquired on 14 volunteers using fMRI, during mental imagery, a condition in which the number and duration of mental events were not externally imposed but self-generated. Application of the obtained model on rest sessions allowed classifying spontaneous brain activity linked to the task which, overall, correlated with their behavioural performance to the task. [less ▲]

Detailed reference viewed: 31 (13 ULg)
Full Text
Peer Reviewed
See detailPRoNTo: Pattern Recognition for Neuroimaging Toolbox
Schrouff, Jessica ULg; Rosa, Maria J; Rondina, Jane et al

Poster (2012, June 12)

Detailed reference viewed: 77 (10 ULg)
Full Text
Peer Reviewed
See detailAutomatic multiclass classification of 18FDG-PET scans for the distinction between Parkinson’s disease and atypical parkinsonian syndromes
Phillips, Christophe ULg; Schrouff, Jessica ULg; Luxen, André ULg et al

Poster (2012, June 10)

Part of the difficulty in the early diagnosis of Parkinson’s disease (PD) is in differentiating it from atypical parkinsonian disorders (APS) that have a poorer prognosis such as multiple system atrophy ... [more ▼]

Part of the difficulty in the early diagnosis of Parkinson’s disease (PD) is in differentiating it from atypical parkinsonian disorders (APS) that have a poorer prognosis such as multiple system atrophy (MSA), progressive supranuclear palsy (PSP) and corticobasal syndrome (CBS). 18flurodeoxyglucose (FDG) positron emission tomography (PET) has been recommended for the early differentiation between PD and APS [1]. Here, 120 FDG PET scans (42, 31, 26 and 21 for the PD, MSA, PSP and CBS resp.) were acquired on average 3.5 years after symptoms onset (because the initial clinical features were outside the prevailing perception for PD) to look, without any a priori assumption, for cerebral FDG uptake patterns that discriminate either between the PD and APS classes, or between the four PD, MSA, PSP and CBS classes. The diagnostic used to label the scans was defined by clinical criteria on average 4.5 years after PET assessment. [less ▲]

Detailed reference viewed: 59 (3 ULg)
See detailPRoNTo: Pattern Recognition for Neuroimaging Toolbox
Schrouff, Jessica ULg; Rosa, Maria Joao; Rondina, Jane et al

Software (2012)

PRoNTo (Pattern Recognition for Neuroimaging Toolbox) is a software toolbox based on pattern recognition techniques for the analysis of neuroimaging data. Statistical pattern recognition is a field within ... [more ▼]

PRoNTo (Pattern Recognition for Neuroimaging Toolbox) is a software toolbox based on pattern recognition techniques for the analysis of neuroimaging data. Statistical pattern recognition is a field within the area of machine learning which is concerned with automatic discovery of regularities in data through the use of computer algorithms, and with the use of these regularities to take actions such as classifying the data into different categories. In PRoNTo, brain scans are treated as spatial patterns and statistical learning models are used to identify statistical properties of the data that can be used to discriminate between experimental conditions or groups of subjects (classification models) or to predict a continuous measure (regression models). PRoNTo aims to facilitate the interaction between machine learning and neuroimaging communities. On one hand, the machine learning community can contribute to the toolbox with novel machine learning models. On the other hand, the toolbox provides a variety of tools for the neuroscience and clinical neuroscience communities, enabling them to ask new questions that cannot be easily investigated using existing software and analysis tools. PRoNTo is distributed for free as copyright software under the terms of the GNU General Public License as published by the Free Software Foundation. The development of the toolbox has been supported by the PASCAL Harvest framework and The Wellcome Trust. [less ▲]

Detailed reference viewed: 11 (3 ULg)
Full Text
Peer Reviewed
See detailDecoding Semi-Constrained Brain Activity from fMRI Using Support Vector Machines and Gaussian Processes
Schrouff, Jessica ULg; Kussé, Caroline ULg; Wehenkel, Louis ULg et al

in PLoS ONE (2012), 7(4),

Predicting a particular cognitive state from a specific pattern of fMRI voxel values is still a methodological challenge. Decoding brain activity is usually performed in highly controlled experimental ... [more ▼]

Predicting a particular cognitive state from a specific pattern of fMRI voxel values is still a methodological challenge. Decoding brain activity is usually performed in highly controlled experimental paradigms characterized by a series of distinct states induced by a temporally constrained experimental design. In more realistic conditions, the number, sequence and duration of mental states are unpredictably generated by the individual, resulting in complex and imbalanced fMRI data sets. This study tests the classification of brain activity, acquired on 16 volunteers using fMRI, during mental imagery, a condition in which the number and duration of mental events were not externally imposed but self-generated. To deal with these issues, two classification techniques were considered (Support Vector Machines, SVM, and Gaussian Processes, GP), as well as different feature extraction methods (General Linear Model, GLM and SVM). These techniques were combined in order to identify the procedures leading to the highest accuracy measures. Our results showed that 12 data sets out of 16 could be significantly modeled by either SVM or GP. Model accuracies tended to be related to the degree of imbalance between classes and to task performance of the volunteers. We also conclude that the GP technique tends to be more robust than SVM to model unbalanced data sets. [less ▲]

Detailed reference viewed: 48 (16 ULg)
Full Text
See detailMultivariate pattern analysis: brain decoding
Schrouff, Jessica ULg; Phillips, Christophe ULg

in Schnakers, Caroline; Laureys, Steven (Eds.) Coma and altered states of consciousness (2012)

Two of the most fundamental questions in the field of neurosciences are how information is represented in different brain structures, and how this information evolves over time. Various tools, such as ... [more ▼]

Two of the most fundamental questions in the field of neurosciences are how information is represented in different brain structures, and how this information evolves over time. Various tools, such as Magnetic Resonance (MRI) and Positron Emission Tomography (PET) have been developed over the last few decades to record brain activity and investigate these questions. In particular, functional MRI (fMRI) tracks changes of the Blood Oxygenation Level-Dependent (BOLD) signal, which is a good indicator of brain activity, with a spatial resolution of a few cubic millimeters and a typical temporal resolution in the order of 1 or 2 seconds. Until recently, the methods used to analyze such data focused on characterizing the individual relationship between a cognitive or perceptual state and each image voxel, i.e. following a massively univariate approach. A well-known univariate technique is Statistical Parametric Mapping (SPM) . SPM relies on the General Linear Model to detect which voxels show a statistically significant response to the (combination of) experimental conditions of interest. However, there are limitations on what can be learned about the representation of information by examining voxels in a univariate fashion. For instance, spatially distributed sets of voxels considered as non-significant by a SPM analysis of one experimental condition might still carry information about the presence or absence of that condition. Furthermore, classic voxel-based analytic techniques are agnostic of any a priori information, for example disease-specific information. They are also mainly designed to perform group-wise comparisons and would therefore be unsuitable to evaluate the state of the disease of each individual. On the other hand, Multi-Voxel Pattern Analyses (MVPA) allow an increased sensitivity to detect the presence of a particular mental representation. These multivariate methods, also known as brain decoding or mind reading, attempt to link a particular cognitive, behavioral or perceptual state to specific patterns of voxels’ activity. Application of these methods made it possible to decode the category of a seen object or the orientation of a stripped pattern seen by the subject from the brain activation of the imaged subject. Advances in pattern-classification algorithms also allowed the decoding of less-controlled conditions such as memory retrieval tasks. Advanced mathematical tools are still under development to allow the classification of more complicated experimental data sets, such as examining the content of mind wandering or detecting the state of consciousness of a patient showing no response to a command. [less ▲]

Detailed reference viewed: 74 (11 ULg)
See detailDecoding semi-constrained brain activity from fMRI using SVM and GP
Schrouff, Jessica ULg; Kussé, Caroline ULg; Wehenkel, Louis ULg et al

Scientific conference (2011, November 22)

Predicting a particular cognitive state from a specific pattern of fMRI voxel values is still a methodological challenge. Decoding brain activity is usually performed in highly controlled experimental ... [more ▼]

Predicting a particular cognitive state from a specific pattern of fMRI voxel values is still a methodological challenge. Decoding brain activity is usually performed in highly controlled experimental paradigms characterized by a series of distinct states induced by a temporally constrained experimental design. In more realistic conditions, the number, sequence and duration of mental states are unpredictably generated by the individual, resulting in complex and imbalanced fMRI data sets. This study tests the classification of brain activity, acquired on 16 volunteers using fMRI, during mental imagery, a condition in which the number and duration of mental events were not externally imposed but self-generated. To deal with these issues, two classification techniques were considered (Support Vector Machines, SVM, and Gaussian Processes, GP), as well as different feature extraction methods (General Linear Model, GLM and SVM). These techniques were combined in order to identify the procedures leading to the highest accuracy measures. Our results showed that 12 data sets out of 16 could be significantly modeled by either SVM or GP. Model accuracies tended to be related to the degree of imbalance between classes and to task performance of the volunteers. We also conclude that the GP technique tends to be more robust than SVM to model unbalanced data sets. [less ▲]

Detailed reference viewed: 50 (5 ULg)
Peer Reviewed
See detailFASST- a FMRI Artefact rejection and Sleep Scoring Toolbox
Schrouff, Jessica ULg; Leclercq, Yves ULg; Noirhomme, Quentin ULg et al

Poster (2011, June 28)

We started writing the “fMRI artefact rejection and sleep scoring toolbox”, or “FASST”, to process our sleep EEG-fMRI data, that is, the simultaneous recording of electroencephalographic and functional ... [more ▼]

We started writing the “fMRI artefact rejection and sleep scoring toolbox”, or “FASST”, to process our sleep EEG-fMRI data, that is, the simultaneous recording of electroencephalographic and functional magnetic resonance imaging data acquired while a subject is asleep. FAST tackles three crucial issues typical of this kind of data: (1) data manipulation (viewing, comparing, chunking, etc.) of long continuous M/EEG recordings, (2) rejection of the fMRI-induced artefact in the EEG signal, and (3)manual sleep-scoring of the M/EEG recording. Currently, the toolbox can efficiently deal with these issues via a GUI, SPM8 batching system or handwritten script. The tools developed are, of course, also useful for other EEG applications, for example, involving simultaneous EEG-fMRI acquisition, continuous EEG eye-balling, and manipulation. Even though the toolbox was originally devised for EEG data, it will also gracefully handle MEG data without any problem. “FAST” is developed in Matlab as an add-on toolbox for SPM8 and, therefore, internally uses its SPM8-meeg data format. “FAST” is available for free, under the GNU-GPL. [less ▲]

Detailed reference viewed: 12 (1 ULg)
Full Text
Peer Reviewed
See detailDecoding Directed Brain Activity in fMRI using Support Vector Machines and Gaussian Processes
Schrouff, Jessica ULg; Kussé, Caroline ULg; Wehenkel, Louis ULg et al

Poster (2011, June 26)

Predicting a particular cognitive state from a specific pattern of fMRI voxel values is still a methodological challenge. Decoding brain activity is usually performed in highly controlled experimental ... [more ▼]

Predicting a particular cognitive state from a specific pattern of fMRI voxel values is still a methodological challenge. Decoding brain activity is usually performed in highly controlled experimental paradigms characterized by a series of distinct states induced by a temporally constrained experimental design. In more realistic conditions, the number, sequence and duration of mental states are unpredictably generated by the individual, resulting in complex and imbalanced fMRI data sets. This study tests the classification of brain activity, acquired on 16 volunteers using fMRI, during mental imagery, a condition in which the number and duration of mental events were not externally imposed but self-generated. To deal with these issues, two classification techniques were considered (Support Vector Machines, SVM, and Gaussian Processes, GP), as well as different feature extraction methods (General Linear Model, GLM and SVM). These techniques were combined in order to identify the procedures leading to the highest accuracy measures. Our results showed that 12 data sets out of 16 could be significantly modeled by either SVM or GP. Model accuracies tended to be related to the degree of imbalance between classes and to task performance of the volunteers. We also conclude that the GP technique tends to be more robust than SVM to model unbalanced data sets. [less ▲]

Detailed reference viewed: 27 (5 ULg)