E. Duff, T. Makin, Sasidhar S. Madugula, Stephen M. Smith, M. Woolrich
Correlation and partial correlation are often used to provide a characterisation of the network properties of the human brain, based on functional brain imaging data. However, for partial correlation, the choice of network nodes (brain regions) and regularisation parameters is crucial and not yet well explored. Here we assess a number of approaches by calculating how each approach performs when used to discriminate different ongoing states of brain activity. We find evidence that partial correlation matrices, when estimated with appropriate regularisation, can provide a useful characterisation of brain functional connectivity.
{"title":"Utility of Partial Correlation for Characterising Brain Dynamics: MVPA-based Assessment of Regularisation and Network Selection","authors":"E. Duff, T. Makin, Sasidhar S. Madugula, Stephen M. Smith, M. Woolrich","doi":"10.1109/PRNI.2013.24","DOIUrl":"https://doi.org/10.1109/PRNI.2013.24","url":null,"abstract":"Correlation and partial correlation are often used to provide a characterisation of the network properties of the human brain, based on functional brain imaging data. However, for partial correlation, the choice of network nodes (brain regions) and regularisation parameters is crucial and not yet well explored. Here we assess a number of approaches by calculating how each approach performs when used to discriminate different ongoing states of brain activity. We find evidence that partial correlation matrices, when estimated with appropriate regularisation, can provide a useful characterisation of brain functional connectivity.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128577289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Schrouff, J. Crémers, G. Garraux, Luca Baldassarre, J. Miranda, C. Phillips
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.
{"title":"Localizing and Comparing Weight Maps Generated from Linear Kernel Machine Learning Models","authors":"J. Schrouff, J. Crémers, G. Garraux, Luca Baldassarre, J. Miranda, C. Phillips","doi":"10.1109/PRNI.2013.40","DOIUrl":"https://doi.org/10.1109/PRNI.2013.40","url":null,"abstract":"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.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127538511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Viktor Wottschel, O. Ciccarelli, D. Chard, David H. Miller, D. Alexander
The aim of this study is to predict the conversion from clinically isolated syndrome to clinically definite multiple sclerosis using support vector machines. The two groups of converters and non-converters are classified using features that were calculated from baseline data of 73 patients. The data consists of standard magnetic resonance images, binary lesion masks, and clinical and demographic information. 15 features were calculated and all combinations of them were iteratively tested for their predictive capacity using polynomial kernels and radial basis functions with leave-one-out cross-validation. The accuracy of this prediction is up to 86.4% with a sensitivity and specificity in the same range indicating that this is a feasible approach for the prediction of a second clinical attack in patients with clinically isolated syndromes, and that the chosen features are appropriate. The two features gender and location of onset lesions have been used in all feature combinations leading to a high accuracy suggesting that they are highly predictive. However, it is necessary to add supporting features to maximise the accuracy.
{"title":"Prediction of Second Neurological Attack in Patients with Clinically Isolated Syndrome Using Support Vector Machines","authors":"Viktor Wottschel, O. Ciccarelli, D. Chard, David H. Miller, D. Alexander","doi":"10.1109/PRNI.2013.30","DOIUrl":"https://doi.org/10.1109/PRNI.2013.30","url":null,"abstract":"The aim of this study is to predict the conversion from clinically isolated syndrome to clinically definite multiple sclerosis using support vector machines. The two groups of converters and non-converters are classified using features that were calculated from baseline data of 73 patients. The data consists of standard magnetic resonance images, binary lesion masks, and clinical and demographic information. 15 features were calculated and all combinations of them were iteratively tested for their predictive capacity using polynomial kernels and radial basis functions with leave-one-out cross-validation. The accuracy of this prediction is up to 86.4% with a sensitivity and specificity in the same range indicating that this is a feasible approach for the prediction of a second clinical attack in patients with clinically isolated syndromes, and that the chosen features are appropriate. The two features gender and location of onset lesions have been used in all feature combinations leading to a high accuracy suggesting that they are highly predictive. However, it is necessary to add supporting features to maximise the accuracy.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133807250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. Bzdok, R. Langner, S. Eickhoff, A. Laird, P. Fox
The right temporo-parietal junction (RTPJ) is consistently implicated in two cognitive domains - attention and social cognitions. We conducted multi-modal connectivity-based parcellation to investigate potentially separate functional modules within RTPJ implementing this cognitive dualism. Both task-constrained meta-analytic co activation mapping and task-free resting-state connectivity analysis independently identified two distinct clusters within RTPJ, subsequently characterized by network mapping and functional forward/reverse inference. The anterior cluster increased activity concomitantly with a midcingulate-motor-insular network, functionally associated with attention, and decreased activity with a parietal network, functionally associated with social cognition and introspection. The posterior cluster showed the exactly opposite association pattern. Our data thus suggest that RTPJ links two antagonistic brain networks processing external versus internal information.
{"title":"Antagonistic Activation Patterns Underlie Multi-functionality of the Right Temporo-Parietal Junction","authors":"D. Bzdok, R. Langner, S. Eickhoff, A. Laird, P. Fox","doi":"10.1109/PRNI.2013.25","DOIUrl":"https://doi.org/10.1109/PRNI.2013.25","url":null,"abstract":"The right temporo-parietal junction (RTPJ) is consistently implicated in two cognitive domains - attention and social cognitions. We conducted multi-modal connectivity-based parcellation to investigate potentially separate functional modules within RTPJ implementing this cognitive dualism. Both task-constrained meta-analytic co activation mapping and task-free resting-state connectivity analysis independently identified two distinct clusters within RTPJ, subsequently characterized by network mapping and functional forward/reverse inference. The anterior cluster increased activity concomitantly with a midcingulate-motor-insular network, functionally associated with attention, and decreased activity with a parietal network, functionally associated with social cognition and introspection. The posterior cluster showed the exactly opposite association pattern. Our data thus suggest that RTPJ links two antagonistic brain networks processing external versus internal information.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"164 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132727031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
An emergent trend in data analysis of functional brain recordings is based on multivariate pattern recognition. Unlike univariate approaches, it is designed as a prediction task by decoding the brain state. fMRI brain decoding is a challenging classification problem due to the noisy, redundant and spatio-temporal correlated data, where there are generally much more features than samples. The use of a classifier requires that raw data is mapped into n-dimensional real vectors where the structural information of the data is not taken into account. Alternative methods propose a different data representation based on a graph encoding. While graphs provide a more powerful representation, machine learning algorithms for this type of encoding become computationally intensive. The contribution of this paper is the introduction of a graph kernel with a lower computational complexity that allows taking advantage from both the representative power of graphs and the discrimination power of kernel-based classifiers such as Support Vector Machines. We provide experimental results for a discrimination task between faces and houses on a fMRI dataset. We also investigate on synthetic data, how the brain decoding task differs according to the different encodings: vectorial and graph-based. A remarkable feature of the graph approach is its capability to handle data from different subjects, without the need of any intersubject alignment. An intersubject decoding experiment is also performed for the faces versus houses problem.
{"title":"Brain Decoding via Graph Kernels","authors":"Sandro Vega-Pons, P. Avesani","doi":"10.1109/PRNI.2013.43","DOIUrl":"https://doi.org/10.1109/PRNI.2013.43","url":null,"abstract":"An emergent trend in data analysis of functional brain recordings is based on multivariate pattern recognition. Unlike univariate approaches, it is designed as a prediction task by decoding the brain state. fMRI brain decoding is a challenging classification problem due to the noisy, redundant and spatio-temporal correlated data, where there are generally much more features than samples. The use of a classifier requires that raw data is mapped into n-dimensional real vectors where the structural information of the data is not taken into account. Alternative methods propose a different data representation based on a graph encoding. While graphs provide a more powerful representation, machine learning algorithms for this type of encoding become computationally intensive. The contribution of this paper is the introduction of a graph kernel with a lower computational complexity that allows taking advantage from both the representative power of graphs and the discrimination power of kernel-based classifiers such as Support Vector Machines. We provide experimental results for a discrimination task between faces and houses on a fMRI dataset. We also investigate on synthetic data, how the brain decoding task differs according to the different encodings: vectorial and graph-based. A remarkable feature of the graph approach is its capability to handle data from different subjects, without the need of any intersubject alignment. An intersubject decoding experiment is also performed for the faces versus houses problem.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116145735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Francisco Pereira, J. M. Walz, H. E. Çetingül, S. Sudarsky, M. Nadar, R. Prakash
In this paper we introduce a method to produce a subdivision of an anatomical atlas by taking into account the similarity of resting state functional MRI time series within anatomically-defined regions of interest. This method differs from others in that the resulting atlases are comparable across subjects, making group analyses possible. Finally, we show that the functional connectivity matrices obtained with this method can be used in a diagnostic classification task and that they enhance a classifier's ability to extract relevant information from the data, leading to more interpretable prediction models in the process.
{"title":"Creating Group-Level Functionally-Defined Atlases for Diagnostic Classification","authors":"Francisco Pereira, J. M. Walz, H. E. Çetingül, S. Sudarsky, M. Nadar, R. Prakash","doi":"10.1109/PRNI.2013.17","DOIUrl":"https://doi.org/10.1109/PRNI.2013.17","url":null,"abstract":"In this paper we introduce a method to produce a subdivision of an anatomical atlas by taking into account the similarity of resting state functional MRI time series within anatomically-defined regions of interest. This method differs from others in that the resulting atlases are comparable across subjects, making group analyses possible. Finally, we show that the functional connectivity matrices obtained with this method can be used in a diagnostic classification task and that they enhance a classifier's ability to extract relevant information from the data, leading to more interpretable prediction models in the process.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121996273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
G. Stetten, Cindy Wong, Vikas Shivaprabhu, Ada Zhang, S. Horvath, Jihang Wang, J. Galeotti, V. Gorantla, H. Aizenstein
We present a novel and relatively simple method for clustering pixels into homogeneous patches using a directed graph of edges between neighboring pixels. For a 2D image, the mean and variance of image intensity is computed within a circular region centered at each pixel. Each pixel stores its circle's mean and variance, and forms the node in a graph, with possible edges to its 4 immediate neighbors. If at least one of those neighbors has a lower variance than itself, a directed edge is formed, pointing to the neighbor with the lowest variance. Local minima in variance thus form the roots of disjoint trees, representing patches of relative homogeneity. The method works in n-dimensions and requires only a single parameter: the radius of the circular (spherical, or hyper spherical) regions used to compute variance around each pixel. Setting the intensity of all pixels within a given patch to the mean at its root pixel significantly reduces image noise while preserving anatomical structure, including location of boundaries. The patches may themselves be clustered using techniques that would be computationally too expensive if applied to the raw pixels. We demonstrate such clustering to identify fascicles in the median nerve in high-resolution 2D ultrasound images, as well as white matter hyper intensities in 3D magnetic resonance images.
{"title":"Descending Variance Graphs for Segmenting Neurological Structures","authors":"G. Stetten, Cindy Wong, Vikas Shivaprabhu, Ada Zhang, S. Horvath, Jihang Wang, J. Galeotti, V. Gorantla, H. Aizenstein","doi":"10.1109/PRNI.2013.52","DOIUrl":"https://doi.org/10.1109/PRNI.2013.52","url":null,"abstract":"We present a novel and relatively simple method for clustering pixels into homogeneous patches using a directed graph of edges between neighboring pixels. For a 2D image, the mean and variance of image intensity is computed within a circular region centered at each pixel. Each pixel stores its circle's mean and variance, and forms the node in a graph, with possible edges to its 4 immediate neighbors. If at least one of those neighbors has a lower variance than itself, a directed edge is formed, pointing to the neighbor with the lowest variance. Local minima in variance thus form the roots of disjoint trees, representing patches of relative homogeneity. The method works in n-dimensions and requires only a single parameter: the radius of the circular (spherical, or hyper spherical) regions used to compute variance around each pixel. Setting the intensity of all pixels within a given patch to the mean at its root pixel significantly reduces image noise while preserving anatomical structure, including location of boundaries. The patches may themselves be clustered using techniques that would be computationally too expensive if applied to the raw pixels. We demonstrate such clustering to identify fascicles in the median nerve in high-resolution 2D ultrasound images, as well as white matter hyper intensities in 3D magnetic resonance images.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"28 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132532742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Comparing and combining data from different brain imaging and non-imaging modalities is challenging, in particular due to the different dimensionalities and resolutions of the modalities. Using an abstract and expressive enough representation for the data, such as graphs, enables gainful inference of relationship between biological scales and mechanisms. Here, we propose a test for the significance of groups of graph vertices in a modality when the grouping is defined in another modality. We define test statistics that can be used to explore sub graphs of interest, and a permutation-based test. We evaluate sensitivity and specificity on synthetic graphs and a co-authorship graph. We then report neuroimaging results on functional, structural, and morphological connectivity graphs, by testing whether a gross anatomical partition yields significant communities. We also exemplify a hypothesis-driven use of the method by showing that elements of the visual system likely covary in cortical thickness and are well connected structurally.
{"title":"Two Test Statistics for Cross-Modal Graph Community Significance","authors":"J. Richiardi, A. Altmann, M. Greicius","doi":"10.1109/PRNI.2013.27","DOIUrl":"https://doi.org/10.1109/PRNI.2013.27","url":null,"abstract":"Comparing and combining data from different brain imaging and non-imaging modalities is challenging, in particular due to the different dimensionalities and resolutions of the modalities. Using an abstract and expressive enough representation for the data, such as graphs, enables gainful inference of relationship between biological scales and mechanisms. Here, we propose a test for the significance of groups of graph vertices in a modality when the grouping is defined in another modality. We define test statistics that can be used to explore sub graphs of interest, and a permutation-based test. We evaluate sensitivity and specificity on synthetic graphs and a co-authorship graph. We then report neuroimaging results on functional, structural, and morphological connectivity graphs, by testing whether a gross anatomical partition yields significant communities. We also exemplify a hypothesis-driven use of the method by showing that elements of the visual system likely covary in cortical thickness and are well connected structurally.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":" 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113951300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Michael Eickenberg, Fabian Pedregosa, M. Senoussi, Alexandre Gramfort, B. Thirion
Second layer scattering descriptors are known to provide good classification performance on natural quasi-stationary processes such as visual textures due to their sensitivity to higher order moments and continuity with respect to small deformations. In a functional Magnetic Resonance Imaging (fMRI) experiment we present visual textures to subjects and evaluate the predictive power of these descriptors with respect to the predictive power of simple contour energy - the first scattering layer. We are able to conclude not only that invariant second layer scattering coefficients better encode voxel activity, but also that well predicted voxels need not necessarily lie in known retinotopic regions.
{"title":"Second Order Scattering Descriptors Predict fMRI Activity Due to Visual Textures","authors":"Michael Eickenberg, Fabian Pedregosa, M. Senoussi, Alexandre Gramfort, B. Thirion","doi":"10.1109/PRNI.2013.11","DOIUrl":"https://doi.org/10.1109/PRNI.2013.11","url":null,"abstract":"Second layer scattering descriptors are known to provide good classification performance on natural quasi-stationary processes such as visual textures due to their sensitivity to higher order moments and continuity with respect to small deformations. In a functional Magnetic Resonance Imaging (fMRI) experiment we present visual textures to subjects and evaluate the predictive power of these descriptors with respect to the predictive power of simple contour energy - the first scattering layer. We are able to conclude not only that invariant second layer scattering coefficients better encode voxel activity, but also that well predicted voxels need not necessarily lie in known retinotopic regions.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129293804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fabian Pedregosa, Michael Eickenberg, B. Thirion, Alexandre Gramfort
Extracting activation patterns from functional Magnetic Resonance Images (fMRI) datasets remains challenging in rapid-event designs due to the inherent delay of blood oxygen level-dependent (BOLD) signal. The general linear model (GLM) allows to estimate the activation from a design matrix and a fixed hemodynamic response function (HRF). However, the HRF is known to vary substantially between subjects and brain regions. In this paper, we propose a model for jointly estimating the hemodynamic response function (HRF) and the activation patterns via a low-rank representation of task effects. This model is based on the linearity assumption behind the GLM and can be computed using standard gradient-based solvers. We use the activation patterns computed by our model as input data for encoding and decoding studies and report performance improvement in both settings.
{"title":"HRF Estimation Improves Sensitivity of fMRI Encoding and Decoding Models","authors":"Fabian Pedregosa, Michael Eickenberg, B. Thirion, Alexandre Gramfort","doi":"10.1109/PRNI.2013.50","DOIUrl":"https://doi.org/10.1109/PRNI.2013.50","url":null,"abstract":"Extracting activation patterns from functional Magnetic Resonance Images (fMRI) datasets remains challenging in rapid-event designs due to the inherent delay of blood oxygen level-dependent (BOLD) signal. The general linear model (GLM) allows to estimate the activation from a design matrix and a fixed hemodynamic response function (HRF). However, the HRF is known to vary substantially between subjects and brain regions. In this paper, we propose a model for jointly estimating the hemodynamic response function (HRF) and the activation patterns via a low-rank representation of task effects. This model is based on the linearity assumption behind the GLM and can be computed using standard gradient-based solvers. We use the activation patterns computed by our model as input data for encoding and decoding studies and report performance improvement in both settings.","PeriodicalId":144007,"journal":{"name":"2013 International Workshop on Pattern Recognition in Neuroimaging","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130205737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：