A Multiple Kernel Learning Framework to Investigate the Relationship Between Ventricular Fibrillation and First Myocardial Infarction

Maciej Marciniak; Hermenegild Arevalo; Jacob Tfelt-Hansen; Kiril A. Ahtarovski; Thomas Jespersen; Reza Jabbari; Charlotte Glinge; Niels Vejlstrup; Thomas Engstrom; Mary M. Maleckar; Kristin McLeod

doi:10.1007/978-3-319-59448-4_16

A Multiple Kernel Learning Framework to Investigate the Relationship Between Ventricular Fibrillation and First Myocardial Infarction

Maciej Marciniak^*, Hermenegild Arevalo, Jacob Tfelt-Hansen, Kiril A. Ahtarovski, Thomas Jespersen, Reza Jabbari, Charlotte Glinge, Niels Vejlstrup, Thomas Engstrom, Mary M. Maleckar, Kristin McLeod

^*Corresponding author for this work

1 Citation (Scopus)

Abstract

Myocardial infarction results in changes in the structure and tissue deformation of the ventricles. In some cases, the development of the disease may trigger an arrhythmic event, which is a major cause of death within the first twenty four hours after the infarction. Advanced analysis methods are increasingly used in order to discover particular characteristics of the myocardial infarction development that lead to the occurrence of arrhythmias. However, such methods usually consider only a single feature or combine separate analyses from multiple features in the analytical process. In an attempt to address this, we propose to use cardiac magnetic resonance imaging to extract data on the shape of the ventricles and volume and location of the infarct zone, and to combine them within one analytical model through a multiple kernel learning framework. The proposed method was applied to a cohort of 46 myocardial infarction patients. The location, rather than the volume, of the infarct region was found to be correlated with arrhythmic events and the proposed combination of kernels yielded excellent accuracy (100%) in distinguishing between patients that did and did not present at the hospital with ventricular fibrillation.

Original language	English
Title of host publication	Functional Imaging and Modelling of the Heart : 9th International Conference, FIMH 2017, Toronto, ON, Canada, June 11-13, 2017, Proceedings
Number of pages	11
Publisher	Springer
Publication date	1 Jan 2017
Pages	161-171
ISBN (Print)	9783319594477
DOIs	https://doi.org/10.1007/978-3-319-59448-4_16
Publication status	Published - 1 Jan 2017
Event	9th International Conference on Functional Imaging and Modelling of the Heart, FIMH 2017 - Toronto, Canada Duration: 11 Jun 2017 → 13 Jun 2017

Conference

Conference	9th International Conference on Functional Imaging and Modelling of the Heart, FIMH 2017
Country/Territory	Canada
City	Toronto
Period	11/06/2017 → 13/06/2017
Sponsor	et al., GE HealthCare, Imricor, Inria, SciMedia Ltd, Shelly Medical Imaging Technologies

Series	Lecture Notes in Computer Science
Volume	10263 LNCS
ISSN	0302-9743

Access to Document

10.1007/978-3-319-59448-4_16

Cite this

Marciniak, M., Arevalo, H., Tfelt-Hansen, J., Ahtarovski, K. A., Jespersen, T., Jabbari, R., Glinge, C., Vejlstrup, N., Engstrom, T., Maleckar, M. M., & McLeod, K. (2017). A Multiple Kernel Learning Framework to Investigate the Relationship Between Ventricular Fibrillation and First Myocardial Infarction. In Functional Imaging and Modelling of the Heart: 9th International Conference, FIMH 2017, Toronto, ON, Canada, June 11-13, 2017, Proceedings (pp. 161-171). Springer. https://doi.org/10.1007/978-3-319-59448-4_16

A Multiple Kernel Learning Framework to Investigate the Relationship Between Ventricular Fibrillation and First Myocardial Infarction. / Marciniak, Maciej; Arevalo, Hermenegild; Tfelt-Hansen, Jacob et al.
Functional Imaging and Modelling of the Heart: 9th International Conference, FIMH 2017, Toronto, ON, Canada, June 11-13, 2017, Proceedings. Springer, 2017. p. 161-171 (Lecture Notes in Computer Science, Vol. 10263 LNCS).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Marciniak, M, Arevalo, H, Tfelt-Hansen, J, Ahtarovski, KA, Jespersen, T, Jabbari, R, Glinge, C, Vejlstrup, N, Engstrom, T, Maleckar, MM & McLeod, K 2017, A Multiple Kernel Learning Framework to Investigate the Relationship Between Ventricular Fibrillation and First Myocardial Infarction. in Functional Imaging and Modelling of the Heart: 9th International Conference, FIMH 2017, Toronto, ON, Canada, June 11-13, 2017, Proceedings. Springer, Lecture Notes in Computer Science, vol. 10263 LNCS, pp. 161-171, 9th International Conference on Functional Imaging and Modelling of the Heart, FIMH 2017, Toronto, Canada, 11/06/2017. https://doi.org/10.1007/978-3-319-59448-4_16

Marciniak M, Arevalo H, Tfelt-Hansen J, Ahtarovski KA, Jespersen T, Jabbari R et al. A Multiple Kernel Learning Framework to Investigate the Relationship Between Ventricular Fibrillation and First Myocardial Infarction. In Functional Imaging and Modelling of the Heart: 9th International Conference, FIMH 2017, Toronto, ON, Canada, June 11-13, 2017, Proceedings. Springer. 2017. p. 161-171. (Lecture Notes in Computer Science, Vol. 10263 LNCS). doi: 10.1007/978-3-319-59448-4_16

Marciniak, Maciej ; Arevalo, Hermenegild ; Tfelt-Hansen, Jacob et al. / A Multiple Kernel Learning Framework to Investigate the Relationship Between Ventricular Fibrillation and First Myocardial Infarction. Functional Imaging and Modelling of the Heart: 9th International Conference, FIMH 2017, Toronto, ON, Canada, June 11-13, 2017, Proceedings. Springer, 2017. pp. 161-171 (Lecture Notes in Computer Science, Vol. 10263 LNCS).

@inproceedings{4c93058efd584f3089da025fc46fb6e2,

title = "A Multiple Kernel Learning Framework to Investigate the Relationship Between Ventricular Fibrillation and First Myocardial Infarction",

abstract = "Myocardial infarction results in changes in the structure and tissue deformation of the ventricles. In some cases, the development of the disease may trigger an arrhythmic event, which is a major cause of death within the first twenty four hours after the infarction. Advanced analysis methods are increasingly used in order to discover particular characteristics of the myocardial infarction development that lead to the occurrence of arrhythmias. However, such methods usually consider only a single feature or combine separate analyses from multiple features in the analytical process. In an attempt to address this, we propose to use cardiac magnetic resonance imaging to extract data on the shape of the ventricles and volume and location of the infarct zone, and to combine them within one analytical model through a multiple kernel learning framework. The proposed method was applied to a cohort of 46 myocardial infarction patients. The location, rather than the volume, of the infarct region was found to be correlated with arrhythmic events and the proposed combination of kernels yielded excellent accuracy (100%) in distinguishing between patients that did and did not present at the hospital with ventricular fibrillation.",

author = "Maciej Marciniak and Hermenegild Arevalo and Jacob Tfelt-Hansen and Ahtarovski, {Kiril A.} and Thomas Jespersen and Reza Jabbari and Charlotte Glinge and Niels Vejlstrup and Thomas Engstrom and Maleckar, {Mary M.} and Kristin McLeod",

year = "2017",

month = jan,

day = "1",

doi = "10.1007/978-3-319-59448-4_16",

language = "English",

isbn = "9783319594477",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "161--171",

booktitle = "Functional Imaging and Modelling of the Heart",

note = "9th International Conference on Functional Imaging and Modelling of the Heart, FIMH 2017 ; Conference date: 11-06-2017 Through 13-06-2017",

}

TY - GEN

T1 - A Multiple Kernel Learning Framework to Investigate the Relationship Between Ventricular Fibrillation and First Myocardial Infarction

AU - Marciniak, Maciej

AU - Arevalo, Hermenegild

AU - Tfelt-Hansen, Jacob

AU - Ahtarovski, Kiril A.

AU - Jespersen, Thomas

AU - Jabbari, Reza

AU - Glinge, Charlotte

AU - Vejlstrup, Niels

AU - Engstrom, Thomas

AU - Maleckar, Mary M.

AU - McLeod, Kristin

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Myocardial infarction results in changes in the structure and tissue deformation of the ventricles. In some cases, the development of the disease may trigger an arrhythmic event, which is a major cause of death within the first twenty four hours after the infarction. Advanced analysis methods are increasingly used in order to discover particular characteristics of the myocardial infarction development that lead to the occurrence of arrhythmias. However, such methods usually consider only a single feature or combine separate analyses from multiple features in the analytical process. In an attempt to address this, we propose to use cardiac magnetic resonance imaging to extract data on the shape of the ventricles and volume and location of the infarct zone, and to combine them within one analytical model through a multiple kernel learning framework. The proposed method was applied to a cohort of 46 myocardial infarction patients. The location, rather than the volume, of the infarct region was found to be correlated with arrhythmic events and the proposed combination of kernels yielded excellent accuracy (100%) in distinguishing between patients that did and did not present at the hospital with ventricular fibrillation.

AB - Myocardial infarction results in changes in the structure and tissue deformation of the ventricles. In some cases, the development of the disease may trigger an arrhythmic event, which is a major cause of death within the first twenty four hours after the infarction. Advanced analysis methods are increasingly used in order to discover particular characteristics of the myocardial infarction development that lead to the occurrence of arrhythmias. However, such methods usually consider only a single feature or combine separate analyses from multiple features in the analytical process. In an attempt to address this, we propose to use cardiac magnetic resonance imaging to extract data on the shape of the ventricles and volume and location of the infarct zone, and to combine them within one analytical model through a multiple kernel learning framework. The proposed method was applied to a cohort of 46 myocardial infarction patients. The location, rather than the volume, of the infarct region was found to be correlated with arrhythmic events and the proposed combination of kernels yielded excellent accuracy (100%) in distinguishing between patients that did and did not present at the hospital with ventricular fibrillation.

U2 - 10.1007/978-3-319-59448-4_16

DO - 10.1007/978-3-319-59448-4_16

M3 - Article in proceedings

AN - SCOPUS:85020473723

SN - 9783319594477

T3 - Lecture Notes in Computer Science

SP - 161

EP - 171

BT - Functional Imaging and Modelling of the Heart

PB - Springer

T2 - 9th International Conference on Functional Imaging and Modelling of the Heart, FIMH 2017

Y2 - 11 June 2017 through 13 June 2017

ER -

A Multiple Kernel Learning Framework to Investigate the Relationship Between Ventricular Fibrillation and First Myocardial Infarction

Abstract

Conference

Access to Document

Fingerprint

Cite this