Model selection for hemodynamic brain parcellation in FMRI. Albughdadi, M., Chaari, L., Forbes, F., Tourneret, J., & Ciuciu, P. In 2014 22nd European Signal Processing Conference (EUSIPCO), pages 31-35, Sep., 2014. Paper abstract bibtex Brain parcellation into a number of hemodynamically homogeneous regions (parcels) is a challenging issue in fMRI analyses. This task has been recently integrated in the joint detection estimation [1] resulting in the so-called joint parcellation detection estimation (JPDE) model [2]. JPDE automatically estimates the parcels from the fMRI data but requires the desired number of parcels to be fixed. This is potentially critical in that the chosen number of parcels may influence detection-estimation performance. In this paper, we propose a model selection procedure to automatically set the number of parcels from the data. The selection procedure relies on the calculation of the free energy corresponding to each concurrent model, within the variational expectation maximization framework. Experiments on synthetic and real fMRI data demonstrate the ability of the proposed procedure to select the optimal number of parcels.
@InProceedings{6951965,
author = {M. Albughdadi and L. Chaari and F. Forbes and J. Tourneret and P. Ciuciu},
booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},
title = {Model selection for hemodynamic brain parcellation in FMRI},
year = {2014},
pages = {31-35},
abstract = {Brain parcellation into a number of hemodynamically homogeneous regions (parcels) is a challenging issue in fMRI analyses. This task has been recently integrated in the joint detection estimation [1] resulting in the so-called joint parcellation detection estimation (JPDE) model [2]. JPDE automatically estimates the parcels from the fMRI data but requires the desired number of parcels to be fixed. This is potentially critical in that the chosen number of parcels may influence detection-estimation performance. In this paper, we propose a model selection procedure to automatically set the number of parcels from the data. The selection procedure relies on the calculation of the free energy corresponding to each concurrent model, within the variational expectation maximization framework. Experiments on synthetic and real fMRI data demonstrate the ability of the proposed procedure to select the optimal number of parcels.},
keywords = {biomedical MRI;brain;expectation-maximisation algorithm;feature extraction;feature selection;free energy;haemodynamics;medical image processing;neurophysiology;optimisation;parameter estimation;variational techniques;optimal parcel number selection;variational expectation maximization framework;free energy calculation;automatic parcel number setting;detection-estimation performance;parcel number selection effect;constant desired parcel number;automatic parcel estimation;JPDE model;joint parcellation detection estimation model;joint detection estimation;hemodynamically homogeneous regions;FMRI analysis;hemodynamic brain parcellation;model selection;Data models;Brain modeling;Hemodynamics;Joints;Estimation;Bayes methods;Educational institutions;fMRI;JDE;JPDE;Parcellation;VEM},
issn = {2076-1465},
month = {Sep.},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569926613.pdf},
}
Downloads: 0
{"_id":"tLPQKXFDBcp2gjKYi","bibbaseid":"albughdadi-chaari-forbes-tourneret-ciuciu-modelselectionforhemodynamicbrainparcellationinfmri-2014","authorIDs":[],"author_short":["Albughdadi, M.","Chaari, L.","Forbes, F.","Tourneret, J.","Ciuciu, P."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["M."],"propositions":[],"lastnames":["Albughdadi"],"suffixes":[]},{"firstnames":["L."],"propositions":[],"lastnames":["Chaari"],"suffixes":[]},{"firstnames":["F."],"propositions":[],"lastnames":["Forbes"],"suffixes":[]},{"firstnames":["J."],"propositions":[],"lastnames":["Tourneret"],"suffixes":[]},{"firstnames":["P."],"propositions":[],"lastnames":["Ciuciu"],"suffixes":[]}],"booktitle":"2014 22nd European Signal Processing Conference (EUSIPCO)","title":"Model selection for hemodynamic brain parcellation in FMRI","year":"2014","pages":"31-35","abstract":"Brain parcellation into a number of hemodynamically homogeneous regions (parcels) is a challenging issue in fMRI analyses. This task has been recently integrated in the joint detection estimation [1] resulting in the so-called joint parcellation detection estimation (JPDE) model [2]. JPDE automatically estimates the parcels from the fMRI data but requires the desired number of parcels to be fixed. This is potentially critical in that the chosen number of parcels may influence detection-estimation performance. In this paper, we propose a model selection procedure to automatically set the number of parcels from the data. The selection procedure relies on the calculation of the free energy corresponding to each concurrent model, within the variational expectation maximization framework. Experiments on synthetic and real fMRI data demonstrate the ability of the proposed procedure to select the optimal number of parcels.","keywords":"biomedical MRI;brain;expectation-maximisation algorithm;feature extraction;feature selection;free energy;haemodynamics;medical image processing;neurophysiology;optimisation;parameter estimation;variational techniques;optimal parcel number selection;variational expectation maximization framework;free energy calculation;automatic parcel number setting;detection-estimation performance;parcel number selection effect;constant desired parcel number;automatic parcel estimation;JPDE model;joint parcellation detection estimation model;joint detection estimation;hemodynamically homogeneous regions;FMRI analysis;hemodynamic brain parcellation;model selection;Data models;Brain modeling;Hemodynamics;Joints;Estimation;Bayes methods;Educational institutions;fMRI;JDE;JPDE;Parcellation;VEM","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569926613.pdf","bibtex":"@InProceedings{6951965,\n author = {M. Albughdadi and L. Chaari and F. Forbes and J. Tourneret and P. Ciuciu},\n booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},\n title = {Model selection for hemodynamic brain parcellation in FMRI},\n year = {2014},\n pages = {31-35},\n abstract = {Brain parcellation into a number of hemodynamically homogeneous regions (parcels) is a challenging issue in fMRI analyses. This task has been recently integrated in the joint detection estimation [1] resulting in the so-called joint parcellation detection estimation (JPDE) model [2]. JPDE automatically estimates the parcels from the fMRI data but requires the desired number of parcels to be fixed. This is potentially critical in that the chosen number of parcels may influence detection-estimation performance. In this paper, we propose a model selection procedure to automatically set the number of parcels from the data. The selection procedure relies on the calculation of the free energy corresponding to each concurrent model, within the variational expectation maximization framework. Experiments on synthetic and real fMRI data demonstrate the ability of the proposed procedure to select the optimal number of parcels.},\n keywords = {biomedical MRI;brain;expectation-maximisation algorithm;feature extraction;feature selection;free energy;haemodynamics;medical image processing;neurophysiology;optimisation;parameter estimation;variational techniques;optimal parcel number selection;variational expectation maximization framework;free energy calculation;automatic parcel number setting;detection-estimation performance;parcel number selection effect;constant desired parcel number;automatic parcel estimation;JPDE model;joint parcellation detection estimation model;joint detection estimation;hemodynamically homogeneous regions;FMRI analysis;hemodynamic brain parcellation;model selection;Data models;Brain modeling;Hemodynamics;Joints;Estimation;Bayes methods;Educational institutions;fMRI;JDE;JPDE;Parcellation;VEM},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569926613.pdf},\n}\n\n","author_short":["Albughdadi, M.","Chaari, L.","Forbes, F.","Tourneret, J.","Ciuciu, P."],"key":"6951965","id":"6951965","bibbaseid":"albughdadi-chaari-forbes-tourneret-ciuciu-modelselectionforhemodynamicbrainparcellationinfmri-2014","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569926613.pdf"},"keyword":["biomedical MRI;brain;expectation-maximisation algorithm;feature extraction;feature selection;free energy;haemodynamics;medical image processing;neurophysiology;optimisation;parameter estimation;variational techniques;optimal parcel number selection;variational expectation maximization framework;free energy calculation;automatic parcel number setting;detection-estimation performance;parcel number selection effect;constant desired parcel number;automatic parcel estimation;JPDE model;joint parcellation detection estimation model;joint detection estimation;hemodynamically homogeneous regions;FMRI analysis;hemodynamic brain parcellation;model selection;Data models;Brain modeling;Hemodynamics;Joints;Estimation;Bayes methods;Educational institutions;fMRI;JDE;JPDE;Parcellation;VEM"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2014url.bib","creationDate":"2021-02-13T17:43:41.572Z","downloads":0,"keywords":["biomedical mri;brain;expectation-maximisation algorithm;feature extraction;feature selection;free energy;haemodynamics;medical image processing;neurophysiology;optimisation;parameter estimation;variational techniques;optimal parcel number selection;variational expectation maximization framework;free energy calculation;automatic parcel number setting;detection-estimation performance;parcel number selection effect;constant desired parcel number;automatic parcel estimation;jpde model;joint parcellation detection estimation model;joint detection estimation;hemodynamically homogeneous regions;fmri analysis;hemodynamic brain parcellation;model selection;data models;brain modeling;hemodynamics;joints;estimation;bayes methods;educational institutions;fmri;jde;jpde;parcellation;vem"],"search_terms":["model","selection","hemodynamic","brain","parcellation","fmri","albughdadi","chaari","forbes","tourneret","ciuciu"],"title":"Model selection for hemodynamic brain parcellation in FMRI","year":2014,"dataSources":["A2ezyFL6GG6na7bbs","oZFG3eQZPXnykPgnE"]}