A graph-based brain parcellation method extracting sparse networks

Nicolas Honnorat, Harini Eavani, Theodore D. Satterthwaite, Christos Davatzikos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

FMRI is a powerful tool for assessing the functioning of the brain. The analysis of resting-state fMRI allows to describe the functional relationship between the cortical areas. Since most connectivity analysis methods suffer from the curse of dimensionality, the cortex needs to be first partitioned into regions of coherent activation patterns. Once the signals of these regions of interest have been extracted, estimating a sparse approximation of the inverse of their correlation matrix is a classical way to robustly describe their functional interactions. In this paper, we address both objectives with a novel parcellation method based on Markov Random Fields that favors the extraction of sparse networks of regions. Our method relies on state of the art rsfMRI models, naturally adapts the number of parcels to the data and is guaranteed to provide connected regions due to the use of shape priors. The second contribution of this paper resides in two novel sparsity enforcing potentials. Our approach is validated with a publicly available dataset.

Original languageEnglish (US)
Title of host publicationProceedings - 2013 3rd International Workshop on Pattern Recognition in Neuroimaging, PRNI 2013
Pages157-160
Number of pages4
DOIs
StatePublished - 2013
Externally publishedYes
Event2013 3rd International Workshop on Pattern Recognition in Neuroimaging, PRNI 2013 - Philadelphia, PA, United States
Duration: Jun 22 2013Jun 24 2013

Other

Other2013 3rd International Workshop on Pattern Recognition in Neuroimaging, PRNI 2013
CountryUnited States
CityPhiladelphia, PA
Period6/22/136/24/13

Fingerprint

Brain
Chemical activation
Magnetic Resonance Imaging

Keywords

  • fMRI
  • Markov Random Fields
  • parcellation
  • sparsity
  • star convexity

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Biomedical Engineering

Cite this

Honnorat, N., Eavani, H., Satterthwaite, T. D., & Davatzikos, C. (2013). A graph-based brain parcellation method extracting sparse networks. In Proceedings - 2013 3rd International Workshop on Pattern Recognition in Neuroimaging, PRNI 2013 (pp. 157-160). [6603580] https://doi.org/10.1109/PRNI.2013.48

A graph-based brain parcellation method extracting sparse networks. / Honnorat, Nicolas; Eavani, Harini; Satterthwaite, Theodore D.; Davatzikos, Christos.

Proceedings - 2013 3rd International Workshop on Pattern Recognition in Neuroimaging, PRNI 2013. 2013. p. 157-160 6603580.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Honnorat, N, Eavani, H, Satterthwaite, TD & Davatzikos, C 2013, A graph-based brain parcellation method extracting sparse networks. in Proceedings - 2013 3rd International Workshop on Pattern Recognition in Neuroimaging, PRNI 2013., 6603580, pp. 157-160, 2013 3rd International Workshop on Pattern Recognition in Neuroimaging, PRNI 2013, Philadelphia, PA, United States, 6/22/13. https://doi.org/10.1109/PRNI.2013.48
Honnorat N, Eavani H, Satterthwaite TD, Davatzikos C. A graph-based brain parcellation method extracting sparse networks. In Proceedings - 2013 3rd International Workshop on Pattern Recognition in Neuroimaging, PRNI 2013. 2013. p. 157-160. 6603580 https://doi.org/10.1109/PRNI.2013.48
Honnorat, Nicolas ; Eavani, Harini ; Satterthwaite, Theodore D. ; Davatzikos, Christos. / A graph-based brain parcellation method extracting sparse networks. Proceedings - 2013 3rd International Workshop on Pattern Recognition in Neuroimaging, PRNI 2013. 2013. pp. 157-160
@inproceedings{e6f71c31e4cc4eef9afbf58e001bbb60,
title = "A graph-based brain parcellation method extracting sparse networks",
abstract = "FMRI is a powerful tool for assessing the functioning of the brain. The analysis of resting-state fMRI allows to describe the functional relationship between the cortical areas. Since most connectivity analysis methods suffer from the curse of dimensionality, the cortex needs to be first partitioned into regions of coherent activation patterns. Once the signals of these regions of interest have been extracted, estimating a sparse approximation of the inverse of their correlation matrix is a classical way to robustly describe their functional interactions. In this paper, we address both objectives with a novel parcellation method based on Markov Random Fields that favors the extraction of sparse networks of regions. Our method relies on state of the art rsfMRI models, naturally adapts the number of parcels to the data and is guaranteed to provide connected regions due to the use of shape priors. The second contribution of this paper resides in two novel sparsity enforcing potentials. Our approach is validated with a publicly available dataset.",
keywords = "fMRI, Markov Random Fields, parcellation, sparsity, star convexity",
author = "Nicolas Honnorat and Harini Eavani and Satterthwaite, {Theodore D.} and Christos Davatzikos",
year = "2013",
doi = "10.1109/PRNI.2013.48",
language = "English (US)",
isbn = "9780769550619",
pages = "157--160",
booktitle = "Proceedings - 2013 3rd International Workshop on Pattern Recognition in Neuroimaging, PRNI 2013",

}

TY - GEN

T1 - A graph-based brain parcellation method extracting sparse networks

AU - Honnorat, Nicolas

AU - Eavani, Harini

AU - Satterthwaite, Theodore D.

AU - Davatzikos, Christos

PY - 2013

Y1 - 2013

N2 - FMRI is a powerful tool for assessing the functioning of the brain. The analysis of resting-state fMRI allows to describe the functional relationship between the cortical areas. Since most connectivity analysis methods suffer from the curse of dimensionality, the cortex needs to be first partitioned into regions of coherent activation patterns. Once the signals of these regions of interest have been extracted, estimating a sparse approximation of the inverse of their correlation matrix is a classical way to robustly describe their functional interactions. In this paper, we address both objectives with a novel parcellation method based on Markov Random Fields that favors the extraction of sparse networks of regions. Our method relies on state of the art rsfMRI models, naturally adapts the number of parcels to the data and is guaranteed to provide connected regions due to the use of shape priors. The second contribution of this paper resides in two novel sparsity enforcing potentials. Our approach is validated with a publicly available dataset.

AB - FMRI is a powerful tool for assessing the functioning of the brain. The analysis of resting-state fMRI allows to describe the functional relationship between the cortical areas. Since most connectivity analysis methods suffer from the curse of dimensionality, the cortex needs to be first partitioned into regions of coherent activation patterns. Once the signals of these regions of interest have been extracted, estimating a sparse approximation of the inverse of their correlation matrix is a classical way to robustly describe their functional interactions. In this paper, we address both objectives with a novel parcellation method based on Markov Random Fields that favors the extraction of sparse networks of regions. Our method relies on state of the art rsfMRI models, naturally adapts the number of parcels to the data and is guaranteed to provide connected regions due to the use of shape priors. The second contribution of this paper resides in two novel sparsity enforcing potentials. Our approach is validated with a publicly available dataset.

KW - fMRI

KW - Markov Random Fields

KW - parcellation

KW - sparsity

KW - star convexity

UR - http://www.scopus.com/inward/record.url?scp=84885200220&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885200220&partnerID=8YFLogxK

U2 - 10.1109/PRNI.2013.48

DO - 10.1109/PRNI.2013.48

M3 - Conference contribution

SN - 9780769550619

SP - 157

EP - 160

BT - Proceedings - 2013 3rd International Workshop on Pattern Recognition in Neuroimaging, PRNI 2013

ER -