Testing Multimodal Integration Hypotheses with Application to Schizophrenia Data

Martin Christian Axelsen, Nikolaj Bak, Lars Kai Hansen

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

104 Downloads (Pure)

Abstract

Multimodal data sets are getting more and more common. Integrating these data sets, the information from each modality can be combined to improve performance in classification problems. Fusion/integration of modalities can be done at several levels. The most appropriate fusion level is related to the conditional dependency between modalities. A varying degree of inter-modality dependency can be present across the modalities. A method for assessing the conditional dependency structure of the modalities and their relationship to intra-modality dependencies in each modality is therefore needed. The aim of the present paper is to propose a method for assessing these inter-modality dependencies. The approach is based on two permutations of an analyzed data set, each exploring different dependencies between and within modalities. The method was tested on the Kaggle MLSP 2014 Schizophrenia Classification Challenge data set which is composed of features from functional magnetic resonance imaging (MRI) and structural MRI. The results support the use of a permutation strategy for testing conditional dependencies between modalities in a multimodal classification problem.
Original languageEnglish
Title of host publicationProceedings of the 5th International Workshop on Pattern Recognition in NeuroImaging (PRNI 2015)
PublisherIEEE
Publication date2015
Pages37-40
ISBN (Print)978-1-4673-7145-2
DOIs
Publication statusPublished - 2015
Event5th International Workshop on Pattern Recognition in Neuroimaging - Stanford University, Palo Alto, United States
Duration: 10 Jun 201512 Jun 2015
Conference number: 5
https://sites.google.com/site/prni2015/

Workshop

Workshop5th International Workshop on Pattern Recognition in Neuroimaging
Number5
LocationStanford University
CountryUnited States
CityPalo Alto
Period10/06/201512/06/2015
Internet address

Cite this

Axelsen, M. C., Bak, N., & Hansen, L. K. (2015). Testing Multimodal Integration Hypotheses with Application to Schizophrenia Data. In Proceedings of the 5th International Workshop on Pattern Recognition in NeuroImaging (PRNI 2015) (pp. 37-40). IEEE. https://doi.org/10.1109/PRNI.2015.20
Axelsen, Martin Christian ; Bak, Nikolaj ; Hansen, Lars Kai. / Testing Multimodal Integration Hypotheses with Application to Schizophrenia Data. Proceedings of the 5th International Workshop on Pattern Recognition in NeuroImaging (PRNI 2015). IEEE, 2015. pp. 37-40
@inproceedings{3e84c499a8ec4a1a9e7ba9e0a8a9ab6f,
title = "Testing Multimodal Integration Hypotheses with Application to Schizophrenia Data",
abstract = "Multimodal data sets are getting more and more common. Integrating these data sets, the information from each modality can be combined to improve performance in classification problems. Fusion/integration of modalities can be done at several levels. The most appropriate fusion level is related to the conditional dependency between modalities. A varying degree of inter-modality dependency can be present across the modalities. A method for assessing the conditional dependency structure of the modalities and their relationship to intra-modality dependencies in each modality is therefore needed. The aim of the present paper is to propose a method for assessing these inter-modality dependencies. The approach is based on two permutations of an analyzed data set, each exploring different dependencies between and within modalities. The method was tested on the Kaggle MLSP 2014 Schizophrenia Classification Challenge data set which is composed of features from functional magnetic resonance imaging (MRI) and structural MRI. The results support the use of a permutation strategy for testing conditional dependencies between modalities in a multimodal classification problem.",
author = "Axelsen, {Martin Christian} and Nikolaj Bak and Hansen, {Lars Kai}",
year = "2015",
doi = "10.1109/PRNI.2015.20",
language = "English",
isbn = "978-1-4673-7145-2",
pages = "37--40",
booktitle = "Proceedings of the 5th International Workshop on Pattern Recognition in NeuroImaging (PRNI 2015)",
publisher = "IEEE",
address = "United States",

}

Axelsen, MC, Bak, N & Hansen, LK 2015, Testing Multimodal Integration Hypotheses with Application to Schizophrenia Data. in Proceedings of the 5th International Workshop on Pattern Recognition in NeuroImaging (PRNI 2015). IEEE, pp. 37-40, 5th International Workshop on Pattern Recognition in Neuroimaging, Palo Alto, United States, 10/06/2015. https://doi.org/10.1109/PRNI.2015.20

Testing Multimodal Integration Hypotheses with Application to Schizophrenia Data. / Axelsen, Martin Christian; Bak, Nikolaj; Hansen, Lars Kai.

Proceedings of the 5th International Workshop on Pattern Recognition in NeuroImaging (PRNI 2015). IEEE, 2015. p. 37-40.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Testing Multimodal Integration Hypotheses with Application to Schizophrenia Data

AU - Axelsen, Martin Christian

AU - Bak, Nikolaj

AU - Hansen, Lars Kai

PY - 2015

Y1 - 2015

N2 - Multimodal data sets are getting more and more common. Integrating these data sets, the information from each modality can be combined to improve performance in classification problems. Fusion/integration of modalities can be done at several levels. The most appropriate fusion level is related to the conditional dependency between modalities. A varying degree of inter-modality dependency can be present across the modalities. A method for assessing the conditional dependency structure of the modalities and their relationship to intra-modality dependencies in each modality is therefore needed. The aim of the present paper is to propose a method for assessing these inter-modality dependencies. The approach is based on two permutations of an analyzed data set, each exploring different dependencies between and within modalities. The method was tested on the Kaggle MLSP 2014 Schizophrenia Classification Challenge data set which is composed of features from functional magnetic resonance imaging (MRI) and structural MRI. The results support the use of a permutation strategy for testing conditional dependencies between modalities in a multimodal classification problem.

AB - Multimodal data sets are getting more and more common. Integrating these data sets, the information from each modality can be combined to improve performance in classification problems. Fusion/integration of modalities can be done at several levels. The most appropriate fusion level is related to the conditional dependency between modalities. A varying degree of inter-modality dependency can be present across the modalities. A method for assessing the conditional dependency structure of the modalities and their relationship to intra-modality dependencies in each modality is therefore needed. The aim of the present paper is to propose a method for assessing these inter-modality dependencies. The approach is based on two permutations of an analyzed data set, each exploring different dependencies between and within modalities. The method was tested on the Kaggle MLSP 2014 Schizophrenia Classification Challenge data set which is composed of features from functional magnetic resonance imaging (MRI) and structural MRI. The results support the use of a permutation strategy for testing conditional dependencies between modalities in a multimodal classification problem.

U2 - 10.1109/PRNI.2015.20

DO - 10.1109/PRNI.2015.20

M3 - Article in proceedings

SN - 978-1-4673-7145-2

SP - 37

EP - 40

BT - Proceedings of the 5th International Workshop on Pattern Recognition in NeuroImaging (PRNI 2015)

PB - IEEE

ER -

Axelsen MC, Bak N, Hansen LK. Testing Multimodal Integration Hypotheses with Application to Schizophrenia Data. In Proceedings of the 5th International Workshop on Pattern Recognition in NeuroImaging (PRNI 2015). IEEE. 2015. p. 37-40 https://doi.org/10.1109/PRNI.2015.20