Deep independence network analysis of structural brain imaging: A simulation study

Eduardo Castro; Devon Hjelm; Sergey Plis; Laurent Dinh; Jessica Turner; Vince Calhoun

doi:10.1109/MLSP.2015.7324318

Deep independence network analysis of structural brain imaging: A simulation study

Eduardo Castro, Devon Hjelm, Sergey Plis, Laurent Dinh, Jessica Turner, Vince Calhoun

School of Medicine

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

The objective of this paper is to further validate theoretically and empirically a nonlinear independent component analysis (ICA) algorithm implemented with a deep learning architecture. We first revisited its formulation to verify its consistency with the criterion of minimization of mutual information. Then, we applied the nonlinear independent component estimation algorithm (NICE) to synthetic 2D images that resemble structural magnetic resonance imaging (sMRI) data. This data was generated by mixing spatial components that represent axial slices of sMRI tissue concentration images. Next, we generated the images under linear and mildly nonlinear mixtures, being able to show that NICE matches ICA when the data is generated by using the conventional linear mixture and outperforms ICA for the nonlinear mixture of components. The obtained results are promising and suggest that NICE has potential to find richer brain networks if applied to real sMRI data, provided that small conditioning adjustments are performed along with this approach.

Original language	English (US)
Title of host publication	2015 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2015
Editors	Deniz Erdogmus, Serdar Kozat, Jan Larsen, Murat Akcakaya
Publisher	IEEE Computer Society
ISBN (Electronic)	9781467374545
DOIs	https://doi.org/10.1109/MLSP.2015.7324318
State	Published - Nov 10 2015
Event	25th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2015 - Boston, United States Duration: Sep 17 2015 → Sep 20 2015

Publication series

Name	IEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume	2015-November
ISSN (Print)	2161-0363
ISSN (Electronic)	2161-0371

Other

Other	25th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2015
Country/Territory	United States
City	Boston
Period	9/17/15 → 9/20/15

Keywords

NICE
Nonlinear ICA
deep learning
simulation
structural MRI

ASJC Scopus subject areas

Human-Computer Interaction
Signal Processing

Access to Document

10.1109/MLSP.2015.7324318

Cite this

Castro, E., Hjelm, D., Plis, S., Dinh, L., Turner, J., & Calhoun, V. (2015). Deep independence network analysis of structural brain imaging: A simulation study. In D. Erdogmus, S. Kozat, J. Larsen, & M. Akcakaya (Eds.), 2015 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2015 Article 7324318 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2015-November). IEEE Computer Society. https://doi.org/10.1109/MLSP.2015.7324318

Deep independence network analysis of structural brain imaging: A simulation study. / Castro, Eduardo; Hjelm, Devon; Plis, Sergey et al.
2015 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2015. ed. / Deniz Erdogmus; Serdar Kozat; Jan Larsen; Murat Akcakaya. IEEE Computer Society, 2015. 7324318 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2015-November).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Castro, E, Hjelm, D, Plis, S, Dinh, L, Turner, J & Calhoun, V 2015, Deep independence network analysis of structural brain imaging: A simulation study. in D Erdogmus, S Kozat, J Larsen & M Akcakaya (eds), 2015 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2015., 7324318, IEEE International Workshop on Machine Learning for Signal Processing, MLSP, vol. 2015-November, IEEE Computer Society, 25th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2015, Boston, United States, 9/17/15. https://doi.org/10.1109/MLSP.2015.7324318

Castro E, Hjelm D, Plis S, Dinh L, Turner J, Calhoun V. Deep independence network analysis of structural brain imaging: A simulation study. In Erdogmus D, Kozat S, Larsen J, Akcakaya M, editors, 2015 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2015. IEEE Computer Society. 2015. 7324318. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP). doi: 10.1109/MLSP.2015.7324318

Castro, Eduardo ; Hjelm, Devon ; Plis, Sergey et al. / Deep independence network analysis of structural brain imaging : A simulation study. 2015 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2015. editor / Deniz Erdogmus ; Serdar Kozat ; Jan Larsen ; Murat Akcakaya. IEEE Computer Society, 2015. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP).

@inproceedings{7bbe7304c0b346bc8cbd8e1a604da6c3,

title = "Deep independence network analysis of structural brain imaging: A simulation study",

abstract = "The objective of this paper is to further validate theoretically and empirically a nonlinear independent component analysis (ICA) algorithm implemented with a deep learning architecture. We first revisited its formulation to verify its consistency with the criterion of minimization of mutual information. Then, we applied the nonlinear independent component estimation algorithm (NICE) to synthetic 2D images that resemble structural magnetic resonance imaging (sMRI) data. This data was generated by mixing spatial components that represent axial slices of sMRI tissue concentration images. Next, we generated the images under linear and mildly nonlinear mixtures, being able to show that NICE matches ICA when the data is generated by using the conventional linear mixture and outperforms ICA for the nonlinear mixture of components. The obtained results are promising and suggest that NICE has potential to find richer brain networks if applied to real sMRI data, provided that small conditioning adjustments are performed along with this approach.",

keywords = "NICE, Nonlinear ICA, deep learning, simulation, structural MRI",

author = "Eduardo Castro and Devon Hjelm and Sergey Plis and Laurent Dinh and Jessica Turner and Vince Calhoun",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.; 25th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2015 ; Conference date: 17-09-2015 Through 20-09-2015",

year = "2015",

month = nov,

day = "10",

doi = "10.1109/MLSP.2015.7324318",

language = "English (US)",

series = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",

publisher = "IEEE Computer Society",

editor = "Deniz Erdogmus and Serdar Kozat and Jan Larsen and Murat Akcakaya",

booktitle = "2015 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2015",

}

TY - GEN

T1 - Deep independence network analysis of structural brain imaging

T2 - 25th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2015

AU - Castro, Eduardo

AU - Hjelm, Devon

AU - Plis, Sergey

AU - Dinh, Laurent

AU - Turner, Jessica

AU - Calhoun, Vince

PY - 2015/11/10

Y1 - 2015/11/10

N2 - The objective of this paper is to further validate theoretically and empirically a nonlinear independent component analysis (ICA) algorithm implemented with a deep learning architecture. We first revisited its formulation to verify its consistency with the criterion of minimization of mutual information. Then, we applied the nonlinear independent component estimation algorithm (NICE) to synthetic 2D images that resemble structural magnetic resonance imaging (sMRI) data. This data was generated by mixing spatial components that represent axial slices of sMRI tissue concentration images. Next, we generated the images under linear and mildly nonlinear mixtures, being able to show that NICE matches ICA when the data is generated by using the conventional linear mixture and outperforms ICA for the nonlinear mixture of components. The obtained results are promising and suggest that NICE has potential to find richer brain networks if applied to real sMRI data, provided that small conditioning adjustments are performed along with this approach.

AB - The objective of this paper is to further validate theoretically and empirically a nonlinear independent component analysis (ICA) algorithm implemented with a deep learning architecture. We first revisited its formulation to verify its consistency with the criterion of minimization of mutual information. Then, we applied the nonlinear independent component estimation algorithm (NICE) to synthetic 2D images that resemble structural magnetic resonance imaging (sMRI) data. This data was generated by mixing spatial components that represent axial slices of sMRI tissue concentration images. Next, we generated the images under linear and mildly nonlinear mixtures, being able to show that NICE matches ICA when the data is generated by using the conventional linear mixture and outperforms ICA for the nonlinear mixture of components. The obtained results are promising and suggest that NICE has potential to find richer brain networks if applied to real sMRI data, provided that small conditioning adjustments are performed along with this approach.

KW - NICE

KW - Nonlinear ICA

KW - deep learning

KW - simulation

KW - structural MRI

UR - http://www.scopus.com/inward/record.url?scp=84960928316&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960928316&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2015.7324318

DO - 10.1109/MLSP.2015.7324318

M3 - Conference contribution

AN - SCOPUS:84960928316

T3 - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

BT - 2015 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2015

A2 - Erdogmus, Deniz

A2 - Kozat, Serdar

A2 - Larsen, Jan

A2 - Akcakaya, Murat

PB - IEEE Computer Society

Y2 - 17 September 2015 through 20 September 2015

ER -

Deep independence network analysis of structural brain imaging: A simulation study

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this