Pub Date : 2015-12-15DOI: 10.1109/PRNI.2014.6858551
S. Weichwald, B. Scholkopf, T. Ball, M. Grosse-Wentrup
Pattern recognition in neuroimaging distinguishes between two types of models: encoding- and decoding models. This distinction is based on the insight that brain state features, that are found to be relevant in an experimental paradigm, carry a different meaning in encoding-than in decoding models. In this paper, we argue that this distinction is not sufficient: Relevant features in encoding- and decoding models carry a different meaning depending on whether they represent causal-or anti-causal relations. We provide a theoretical justification for this argument and conclude that causal inference is essential for interpretation in neuroimaging.
{"title":"Causal and anti-causal learning in pattern recognition for neuroimaging","authors":"S. Weichwald, B. Scholkopf, T. Ball, M. Grosse-Wentrup","doi":"10.1109/PRNI.2014.6858551","DOIUrl":"https://doi.org/10.1109/PRNI.2014.6858551","url":null,"abstract":"Pattern recognition in neuroimaging distinguishes between two types of models: encoding- and decoding models. This distinction is based on the insight that brain state features, that are found to be relevant in an experimental paradigm, carry a different meaning in encoding-than in decoding models. In this paper, we argue that this distinction is not sufficient: Relevant features in encoding- and decoding models carry a different meaning depending on whether they represent causal-or anti-causal relations. We provide a theoretical justification for this argument and conclude that causal inference is essential for interpretation in neuroimaging.","PeriodicalId":133286,"journal":{"name":"2014 International Workshop on Pattern Recognition in Neuroimaging","volume":"11 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123311018","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}
Pub Date : 2014-06-04DOI: 10.1109/PRNI.2014.6858528
Achim Leydecker, F. Biessmann, S. Fazli
Neurotechnology offers the potential to improve performance in cognitive tasks by tailoring the learning paradigm to the neurophysiological correlates of mental processes. Up to date, there are few studies that investigate the single trial performance of neural decoding in cognitive tasks. In this study we examine EEG data while a given subject is solving questions which are commonly used in intelligence quotient tests. Subjects are instructed to solve a number of visual template matching tasks. Our findings suggest that it is possible to decode the true answer from the subjects' ERP responses at the time of its presentation. These results indicate that neurophysiological markers could be useful for neurotechnology assisted learning paradigms.
{"title":"Single-trials ERPs predict correct answers to intelligence test questions","authors":"Achim Leydecker, F. Biessmann, S. Fazli","doi":"10.1109/PRNI.2014.6858528","DOIUrl":"https://doi.org/10.1109/PRNI.2014.6858528","url":null,"abstract":"Neurotechnology offers the potential to improve performance in cognitive tasks by tailoring the learning paradigm to the neurophysiological correlates of mental processes. Up to date, there are few studies that investigate the single trial performance of neural decoding in cognitive tasks. In this study we examine EEG data while a given subject is solving questions which are commonly used in intelligence quotient tests. Subjects are instructed to solve a number of visual template matching tasks. Our findings suggest that it is possible to decode the true answer from the subjects' ERP responses at the time of its presentation. These results indicate that neurophysiological markers could be useful for neurotechnology assisted learning paradigms.","PeriodicalId":133286,"journal":{"name":"2014 International Workshop on Pattern Recognition in Neuroimaging","volume":"116 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126398766","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}
Pub Date : 2014-06-04DOI: 10.1109/PRNI.2014.6858550
A. Vilamala, L. B. Muñoz, A. Vellido
Convex non-negative matrix factorization is a blind signal separation technique that has previously demonstrated to be well-suited for the task of human brain tumor diagnosis from magnetic resonance spectroscopy data. This is due to its ability to retrieve interpretable sources of mixed sign that highly correlate with tissue type prototypes. The current study provides a Bayesian formulation for such problem and derives a maximum a posteriori estimate based on a gradient descent algorithm specifically designed to deal with matrices with different sign restrictions. Its applicability to neuro-oncology diagnosis was experimentally assessed and the results were found to be comparable to those achieved by state of the art methods in tumor type discrimination and consistently better in source extraction.
{"title":"A MAP approach for convex non-negative matrix factorization in the diagnosis of brain tumors","authors":"A. Vilamala, L. B. Muñoz, A. Vellido","doi":"10.1109/PRNI.2014.6858550","DOIUrl":"https://doi.org/10.1109/PRNI.2014.6858550","url":null,"abstract":"Convex non-negative matrix factorization is a blind signal separation technique that has previously demonstrated to be well-suited for the task of human brain tumor diagnosis from magnetic resonance spectroscopy data. This is due to its ability to retrieve interpretable sources of mixed sign that highly correlate with tissue type prototypes. The current study provides a Bayesian formulation for such problem and derives a maximum a posteriori estimate based on a gradient descent algorithm specifically designed to deal with matrices with different sign restrictions. Its applicability to neuro-oncology diagnosis was experimentally assessed and the results were found to be comparable to those achieved by state of the art methods in tumor type discrimination and consistently better in source extraction.","PeriodicalId":133286,"journal":{"name":"2014 International Workshop on Pattern Recognition in Neuroimaging","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125625171","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}
Pub Date : 2014-06-04DOI: 10.1109/PRNI.2014.6858511
F. Biessmann, Michael Gaebler, Jan-Peter Lamke, Uijong Ju, S. Hetzer, C. Wallraven, K. Müller
A central question in neuroscience is how the brain reacts to real world sensory stimuli. Naturalistic and complex (e.g. movie) stimuli are increasingly used in empirical research but their analysis often relies on considerable human efforts to label or extract stimulus features. Here we present data-driven analysis strategies that help to obtain interpretable results from multisubject neuroimaging data when complex movie stimuli are used. These analyses a) enable localization and visualization of brain activity using standard statistical parametric maps in the subspace of brain activity shared between subjects and b) facilitate interpretation of intersubject correlations. We show experimental results obtained from 50 subjects.
{"title":"Data-driven multisubject neuroimaging analyses for naturalistic stimuli","authors":"F. Biessmann, Michael Gaebler, Jan-Peter Lamke, Uijong Ju, S. Hetzer, C. Wallraven, K. Müller","doi":"10.1109/PRNI.2014.6858511","DOIUrl":"https://doi.org/10.1109/PRNI.2014.6858511","url":null,"abstract":"A central question in neuroscience is how the brain reacts to real world sensory stimuli. Naturalistic and complex (e.g. movie) stimuli are increasingly used in empirical research but their analysis often relies on considerable human efforts to label or extract stimulus features. Here we present data-driven analysis strategies that help to obtain interpretable results from multisubject neuroimaging data when complex movie stimuli are used. These analyses a) enable localization and visualization of brain activity using standard statistical parametric maps in the subspace of brain activity shared between subjects and b) facilitate interpretation of intersubject correlations. We show experimental results obtained from 50 subjects.","PeriodicalId":133286,"journal":{"name":"2014 International Workshop on Pattern Recognition in Neuroimaging","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130686720","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}
Pub Date : 2014-06-04DOI: 10.1109/PRNI.2014.6858548
S. Takerkart, L. Ralaivola
Multi-voxel pattern analysis has become an important tool for neuroimaging data analysis by allowing to predict a behavioral variable from the imaging patterns. However, standard models do not take into account the differences that can exist between subjects, so that they perform poorly in the inter-subject prediction task. We here introduce a model called Multiple Subject Learning (MSL) that is designed to effectively combine the information provided by fMRI data from several subjects; in a first stage, a weighting of single-subject kernels is learnt using multiple kernel learning to produce a classifier; then, a data shuffling procedure allows to build ensembles of such classifiers, which are then combined by a majority vote. We show that MSL outperforms other models in the inter-subject prediction task and we discuss the empirical behavior of this new model.
{"title":"Multiple subject learning for inter-subject prediction","authors":"S. Takerkart, L. Ralaivola","doi":"10.1109/PRNI.2014.6858548","DOIUrl":"https://doi.org/10.1109/PRNI.2014.6858548","url":null,"abstract":"Multi-voxel pattern analysis has become an important tool for neuroimaging data analysis by allowing to predict a behavioral variable from the imaging patterns. However, standard models do not take into account the differences that can exist between subjects, so that they perform poorly in the inter-subject prediction task. We here introduce a model called Multiple Subject Learning (MSL) that is designed to effectively combine the information provided by fMRI data from several subjects; in a first stage, a weighting of single-subject kernels is learnt using multiple kernel learning to produce a classifier; then, a data shuffling procedure allows to build ensembles of such classifiers, which are then combined by a majority vote. We show that MSL outperforms other models in the inter-subject prediction task and we discuss the empirical behavior of this new model.","PeriodicalId":133286,"journal":{"name":"2014 International Workshop on Pattern Recognition in Neuroimaging","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133175931","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}
Pub Date : 2014-06-04DOI: 10.1109/PRNI.2014.6858513
J. Bulthé, J. V. D. Hurk, Nicky Daniels, B. Smedt, H. O. D. Beeck
Most fMRI studies using Multi-Voxel Pattern Analysis (MVPA) restrict these analyses to merely one spatial scale. However, recently [1] used a multi-spatial scale method combining three levels of MVPA analysis on fMRI data from 16 subjects who performed a number comparison task: whole-brain MVPA, Regions Of Interest (ROI) based MVPA, and a small radius searchlight. The results of [1] clearly demonstrated the necessity of incorporating different spatial scales in MVPA analysis to draw conclusions on how the neural representations of the effects are distributed across the brain. We tested the validity of the method used in this empirical study by using three simulated fMRI datasets. Both simulated data and the real data [1] confirmed the relevance of analyzing data with MVPA on different spatial scales.
{"title":"A validation of a multi-spatialscale method for multivariate pattern analysis","authors":"J. Bulthé, J. V. D. Hurk, Nicky Daniels, B. Smedt, H. O. D. Beeck","doi":"10.1109/PRNI.2014.6858513","DOIUrl":"https://doi.org/10.1109/PRNI.2014.6858513","url":null,"abstract":"Most fMRI studies using Multi-Voxel Pattern Analysis (MVPA) restrict these analyses to merely one spatial scale. However, recently [1] used a multi-spatial scale method combining three levels of MVPA analysis on fMRI data from 16 subjects who performed a number comparison task: whole-brain MVPA, Regions Of Interest (ROI) based MVPA, and a small radius searchlight. The results of [1] clearly demonstrated the necessity of incorporating different spatial scales in MVPA analysis to draw conclusions on how the neural representations of the effects are distributed across the brain. We tested the validity of the method used in this empirical study by using three simulated fMRI datasets. Both simulated data and the real data [1] confirmed the relevance of analyzing data with MVPA on different spatial scales.","PeriodicalId":133286,"journal":{"name":"2014 International Workshop on Pattern Recognition in Neuroimaging","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132092892","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}
Pub Date : 2014-06-04DOI: 10.1109/PRNI.2014.6858546
Alejandro Tabas-Diaz, E. Balaguer-Ballester, L. Igual
Resting-State fMRI (RS-fMRI) is a brain imaging technique useful for exploring functional connectivity. A major point of interest in RS-fMRI analysis is to isolate connectivity patterns characterising disorders such as for instance ADHD. Such characterisation is usually performed in two steps: first, all connectivity patterns in the data are extracted by means of Independent Component Analysis (ICA); second, standard statistical tests are performed over the extracted patterns to find differences between control and clinical groups. In this work we introduce a novel, single-step, approach for this problem termed Spatial Discriminant ICA. The algorithm can efficiently isolate networks of functional connectivity characterising a clinical group by combining ICA and a new variant of the Fisher's Linear Discriminant also introduced in this work. As the characterisation is carried out in a single step, it potentially provides for a richer characterisation of inter-class differences. The algorithm is tested using synthetic and real fMRI data, showing promising results in both experiments.
{"title":"Spatial discriminant ICA for RS-fMRI characterisation","authors":"Alejandro Tabas-Diaz, E. Balaguer-Ballester, L. Igual","doi":"10.1109/PRNI.2014.6858546","DOIUrl":"https://doi.org/10.1109/PRNI.2014.6858546","url":null,"abstract":"Resting-State fMRI (RS-fMRI) is a brain imaging technique useful for exploring functional connectivity. A major point of interest in RS-fMRI analysis is to isolate connectivity patterns characterising disorders such as for instance ADHD. Such characterisation is usually performed in two steps: first, all connectivity patterns in the data are extracted by means of Independent Component Analysis (ICA); second, standard statistical tests are performed over the extracted patterns to find differences between control and clinical groups. In this work we introduce a novel, single-step, approach for this problem termed Spatial Discriminant ICA. The algorithm can efficiently isolate networks of functional connectivity characterising a clinical group by combining ICA and a new variant of the Fisher's Linear Discriminant also introduced in this work. As the characterisation is carried out in a single step, it potentially provides for a richer characterisation of inter-class differences. The algorithm is tested using synthetic and real fMRI data, showing promising results in both experiments.","PeriodicalId":133286,"journal":{"name":"2014 International Workshop on Pattern Recognition in Neuroimaging","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132629681","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}
Pub Date : 2014-06-04DOI: 10.1109/PRNI.2014.6858533
A. Marquand, Steven C. R. Williams, O. Doyle, M. J. Rosa
Multi-task learning (MTL) has recently been demonstrated to be highly promising for decoding multiple target variables from neuroimaging data. Its primary advantage is that it makes more efficient use of the data than existing decoding models, leading to improved accuracy. In this work, we propose a novel Bayesian MTL approach, motivated by problems such as clinical applications where accurate quantification of uncertainty is crucial. We present a Markov chain Monte Carlo approach to perform inference in the model and demonstrate the approach using a publicly available neuroimaging dataset. We study the conditions where MTL is likely to improve performance: we first evaluate MTL as an approach for accommodating missing data, which is an important problem that has received little attention from the neuroimaging community. We then examine whether it is beneficial to include classification and regression tasks in the same model. We relate our conclusions to results from geostatistics, where MTL methods were pioneered, and make recommendations for neuroimaging practitioners using MTL.
{"title":"Full Bayesian multi-task learning for multi-output brain decoding and accommodating missing data","authors":"A. Marquand, Steven C. R. Williams, O. Doyle, M. J. Rosa","doi":"10.1109/PRNI.2014.6858533","DOIUrl":"https://doi.org/10.1109/PRNI.2014.6858533","url":null,"abstract":"Multi-task learning (MTL) has recently been demonstrated to be highly promising for decoding multiple target variables from neuroimaging data. Its primary advantage is that it makes more efficient use of the data than existing decoding models, leading to improved accuracy. In this work, we propose a novel Bayesian MTL approach, motivated by problems such as clinical applications where accurate quantification of uncertainty is crucial. We present a Markov chain Monte Carlo approach to perform inference in the model and demonstrate the approach using a publicly available neuroimaging dataset. We study the conditions where MTL is likely to improve performance: we first evaluate MTL as an approach for accommodating missing data, which is an important problem that has received little attention from the neuroimaging community. We then examine whether it is beneficial to include classification and regression tasks in the same model. We relate our conclusions to results from geostatistics, where MTL methods were pioneered, and make recommendations for neuroimaging practitioners using MTL.","PeriodicalId":133286,"journal":{"name":"2014 International Workshop on Pattern Recognition in Neuroimaging","volume":"13 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131437291","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}
Pub Date : 2014-06-04DOI: 10.1109/PRNI.2014.6858531
Loizos Markides, D. Gillies
Among the long-term goals of the fairly new area of brain decoding is the exploitation of the results for the creation of advanced brain-computer interfaces, which can potentially establish a solid communication channel with people in vegetative state. Recent attempts for large-scale brain decoding form a both powerful and promising foundation towards that goal, since they aim to extract accurate representations of certain stimuli within the human brain, given a large number of different studies. An inherent problem with across-study brain decoding is that the classification algorithms end up discriminating among studies instead among stimuli. This is due to study-specific nuisance effects, which cannot be removed by standard preprocessing methodologies, and which may cause two volumes representing different stimuli within a single study to be closer to one another than two volumes representing similar stimuli across different studies. Considering that a large number of previous studies suggest that across-subject and across-session decoding works, we have come to believe that the problem of degraded across-study accuracy is introduced by differing stimuli activation values across studies, originating from study-specific and not subject-specific idiosyncrasies. Therefore, the problem of correct stimuli classification across studies is reduced to the one of consistent intensity normalisation across studies, in order to provide persistent representations of stimuli in the brain. In this work, we provide a thorough discussion on the performance of four different intensity normalisation techniques, in order to evaluate their applicability as a pre-processing step for large-scale brain decoding.
{"title":"Intensity normalisation for large-scale fMRI brain decoding","authors":"Loizos Markides, D. Gillies","doi":"10.1109/PRNI.2014.6858531","DOIUrl":"https://doi.org/10.1109/PRNI.2014.6858531","url":null,"abstract":"Among the long-term goals of the fairly new area of brain decoding is the exploitation of the results for the creation of advanced brain-computer interfaces, which can potentially establish a solid communication channel with people in vegetative state. Recent attempts for large-scale brain decoding form a both powerful and promising foundation towards that goal, since they aim to extract accurate representations of certain stimuli within the human brain, given a large number of different studies. An inherent problem with across-study brain decoding is that the classification algorithms end up discriminating among studies instead among stimuli. This is due to study-specific nuisance effects, which cannot be removed by standard preprocessing methodologies, and which may cause two volumes representing different stimuli within a single study to be closer to one another than two volumes representing similar stimuli across different studies. Considering that a large number of previous studies suggest that across-subject and across-session decoding works, we have come to believe that the problem of degraded across-study accuracy is introduced by differing stimuli activation values across studies, originating from study-specific and not subject-specific idiosyncrasies. Therefore, the problem of correct stimuli classification across studies is reduced to the one of consistent intensity normalisation across studies, in order to provide persistent representations of stimuli in the brain. In this work, we provide a thorough discussion on the performance of four different intensity normalisation techniques, in order to evaluate their applicability as a pre-processing step for large-scale brain decoding.","PeriodicalId":133286,"journal":{"name":"2014 International Workshop on Pattern Recognition in Neuroimaging","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128019021","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}
Pub Date : 2014-06-04DOI: 10.1109/PRNI.2014.6858508
S. Badillo, S. Desmidt, Chantal Ginisty, P. Ciuciu
Modern cognitive experiments in functional Magnetic Resonance Imaging (fMRI) rely on a cohort of subjects sampled from a population of interest to study characteristics of the healthy brain or to identify biomarkers on a specific pathology (e.g., Alzheimer's disease) or disorder (e.g., ageing). Group-level studies usually proceed in two steps by making random-effect analysis on top of intra-subject analyses, to localize activated regions in response to stimulations or to estimate brain dynamics. Here, we focus on improving the accuracy of group-level inference of the hemodynamic response function (HRF). We rest on a existing Joint Detection-Estimation (JDE) framework which aims at detecting evoked activity and estimating HRF shapes jointly. So far, region-specific group-level HRFs have been captured by averaging intra-subject HRF profiles. Here, our approach extends the JDE formalism to the multi-subject context by proposing a hierarchical Bayesian modeling that includes an additional layer for describing the link between subject-specific and group-level HRFs. This extension outperforms the original approach both on artificial and real multi-subject datasets.
{"title":"Multi-subject Bayesian Joint Detection and Estimation in fMRI","authors":"S. Badillo, S. Desmidt, Chantal Ginisty, P. Ciuciu","doi":"10.1109/PRNI.2014.6858508","DOIUrl":"https://doi.org/10.1109/PRNI.2014.6858508","url":null,"abstract":"Modern cognitive experiments in functional Magnetic Resonance Imaging (fMRI) rely on a cohort of subjects sampled from a population of interest to study characteristics of the healthy brain or to identify biomarkers on a specific pathology (e.g., Alzheimer's disease) or disorder (e.g., ageing). Group-level studies usually proceed in two steps by making random-effect analysis on top of intra-subject analyses, to localize activated regions in response to stimulations or to estimate brain dynamics. Here, we focus on improving the accuracy of group-level inference of the hemodynamic response function (HRF). We rest on a existing Joint Detection-Estimation (JDE) framework which aims at detecting evoked activity and estimating HRF shapes jointly. So far, region-specific group-level HRFs have been captured by averaging intra-subject HRF profiles. Here, our approach extends the JDE formalism to the multi-subject context by proposing a hierarchical Bayesian modeling that includes an additional layer for describing the link between subject-specific and group-level HRFs. This extension outperforms the original approach both on artificial and real multi-subject datasets.","PeriodicalId":133286,"journal":{"name":"2014 International Workshop on Pattern Recognition in Neuroimaging","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117165589","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：