Segmentation of the left ventricle in cardiac MRI using an ELM model

Y. Luo, B. Yang, L. Xu, L. Hao, J. Liu, Y. Yao, F.N. van de Vosse

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureHoofdstukAcademicpeer review

9 Citaties (Scopus)

Uittreksel

In this paper, an automatic left ventricle (LV) segmentation method based on an Extreme Learning Machine (ELM) is presented. Firstly, according to background and foreground, all sample pixels of Magnetic Resonance Imaging (MRI) images are divided into two types, and then 23-dimensional features of each pixel are extracted to generate a feature matrix. Secondly, the feature matrix is input into the ELM to train the ELM. Finally, the LV is segmented by the trained ELM. Experimental results show that the mean speed of LV segmentation based on the ELM is about 25 times faster than that of the level set, about 7 times faster than that of the SVM. The mean values of mad and maxd of image segmentation based on the ELM is about 80 and 83.1 % of that of the level set and the SVM, respectively. The mean value of dice of image segmentation based on the ELM is about 8 and 2 % higher than that of the level set and the SVM, respectively. The standard deviation of the proposed method is the lowest among all three methods. The results prove that the proposed method is efficient and satisfactory for the LV segmentation.
Originele taal-2Engels
TitelProceedings of ELM-2015, Vol. 1: Theory, Algorithms and Applications (I)
RedacteurenJ. Cao, K. Mao, J. Wu, A. Lendasse
Plaats van productieDordrecht
UitgeverijSpringer
Pagina's147-157
Aantal pagina's11
ISBN van geprinte versie978-3-319-28396-8
DOI's
StatusGepubliceerd - 2016

Publicatie series

NaamProceedings in Adaptation Learning and Optimization

Citeer dit

Luo, Y., Yang, B., Xu, L., Hao, L., Liu, J., Yao, Y., & van de Vosse, F. N. (2016). Segmentation of the left ventricle in cardiac MRI using an ELM model. In J. Cao, K. Mao, J. Wu, & A. Lendasse (editors), Proceedings of ELM-2015, Vol. 1: Theory, Algorithms and Applications (I) (blz. 147-157). (Proceedings in Adaptation Learning and Optimization). Dordrecht: Springer. https://doi.org/10.1007/978-3-319-28397-5_12
Luo, Y. ; Yang, B. ; Xu, L. ; Hao, L. ; Liu, J. ; Yao, Y. ; van de Vosse, F.N. / Segmentation of the left ventricle in cardiac MRI using an ELM model. Proceedings of ELM-2015, Vol. 1: Theory, Algorithms and Applications (I). redacteur / J. Cao ; K. Mao ; J. Wu ; A. Lendasse. Dordrecht : Springer, 2016. blz. 147-157 (Proceedings in Adaptation Learning and Optimization).
@inbook{6ea6bda3cf674a3494c64c3fe34152c5,
title = "Segmentation of the left ventricle in cardiac MRI using an ELM model",
abstract = "In this paper, an automatic left ventricle (LV) segmentation method based on an Extreme Learning Machine (ELM) is presented. Firstly, according to background and foreground, all sample pixels of Magnetic Resonance Imaging (MRI) images are divided into two types, and then 23-dimensional features of each pixel are extracted to generate a feature matrix. Secondly, the feature matrix is input into the ELM to train the ELM. Finally, the LV is segmented by the trained ELM. Experimental results show that the mean speed of LV segmentation based on the ELM is about 25 times faster than that of the level set, about 7 times faster than that of the SVM. The mean values of mad and maxd of image segmentation based on the ELM is about 80 and 83.1 {\%} of that of the level set and the SVM, respectively. The mean value of dice of image segmentation based on the ELM is about 8 and 2 {\%} higher than that of the level set and the SVM, respectively. The standard deviation of the proposed method is the lowest among all three methods. The results prove that the proposed method is efficient and satisfactory for the LV segmentation.",
keywords = "Extreme learning machine, Image segmentation, Left ventricle, Magnetic resonance imaging",
author = "Y. Luo and B. Yang and L. Xu and L. Hao and J. Liu and Y. Yao and {van de Vosse}, F.N.",
year = "2016",
doi = "10.1007/978-3-319-28397-5_12",
language = "English",
isbn = "978-3-319-28396-8",
series = "Proceedings in Adaptation Learning and Optimization",
publisher = "Springer",
pages = "147--157",
editor = "J. Cao and K. Mao and J. Wu and A. Lendasse",
booktitle = "Proceedings of ELM-2015, Vol. 1: Theory, Algorithms and Applications (I)",
address = "Germany",

}

Luo, Y, Yang, B, Xu, L, Hao, L, Liu, J, Yao, Y & van de Vosse, FN 2016, Segmentation of the left ventricle in cardiac MRI using an ELM model. in J Cao, K Mao, J Wu & A Lendasse (redactie), Proceedings of ELM-2015, Vol. 1: Theory, Algorithms and Applications (I). Proceedings in Adaptation Learning and Optimization, Springer, Dordrecht, blz. 147-157. https://doi.org/10.1007/978-3-319-28397-5_12

Segmentation of the left ventricle in cardiac MRI using an ELM model. / Luo, Y.; Yang, B.; Xu, L.; Hao, L.; Liu, J.; Yao, Y.; van de Vosse, F.N.

Proceedings of ELM-2015, Vol. 1: Theory, Algorithms and Applications (I). redactie / J. Cao; K. Mao; J. Wu; A. Lendasse. Dordrecht : Springer, 2016. blz. 147-157 (Proceedings in Adaptation Learning and Optimization).

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureHoofdstukAcademicpeer review

TY - CHAP

T1 - Segmentation of the left ventricle in cardiac MRI using an ELM model

AU - Luo, Y.

AU - Yang, B.

AU - Xu, L.

AU - Hao, L.

AU - Liu, J.

AU - Yao, Y.

AU - van de Vosse, F.N.

PY - 2016

Y1 - 2016

N2 - In this paper, an automatic left ventricle (LV) segmentation method based on an Extreme Learning Machine (ELM) is presented. Firstly, according to background and foreground, all sample pixels of Magnetic Resonance Imaging (MRI) images are divided into two types, and then 23-dimensional features of each pixel are extracted to generate a feature matrix. Secondly, the feature matrix is input into the ELM to train the ELM. Finally, the LV is segmented by the trained ELM. Experimental results show that the mean speed of LV segmentation based on the ELM is about 25 times faster than that of the level set, about 7 times faster than that of the SVM. The mean values of mad and maxd of image segmentation based on the ELM is about 80 and 83.1 % of that of the level set and the SVM, respectively. The mean value of dice of image segmentation based on the ELM is about 8 and 2 % higher than that of the level set and the SVM, respectively. The standard deviation of the proposed method is the lowest among all three methods. The results prove that the proposed method is efficient and satisfactory for the LV segmentation.

AB - In this paper, an automatic left ventricle (LV) segmentation method based on an Extreme Learning Machine (ELM) is presented. Firstly, according to background and foreground, all sample pixels of Magnetic Resonance Imaging (MRI) images are divided into two types, and then 23-dimensional features of each pixel are extracted to generate a feature matrix. Secondly, the feature matrix is input into the ELM to train the ELM. Finally, the LV is segmented by the trained ELM. Experimental results show that the mean speed of LV segmentation based on the ELM is about 25 times faster than that of the level set, about 7 times faster than that of the SVM. The mean values of mad and maxd of image segmentation based on the ELM is about 80 and 83.1 % of that of the level set and the SVM, respectively. The mean value of dice of image segmentation based on the ELM is about 8 and 2 % higher than that of the level set and the SVM, respectively. The standard deviation of the proposed method is the lowest among all three methods. The results prove that the proposed method is efficient and satisfactory for the LV segmentation.

KW - Extreme learning machine

KW - Image segmentation

KW - Left ventricle

KW - Magnetic resonance imaging

U2 - 10.1007/978-3-319-28397-5_12

DO - 10.1007/978-3-319-28397-5_12

M3 - Chapter

SN - 978-3-319-28396-8

T3 - Proceedings in Adaptation Learning and Optimization

SP - 147

EP - 157

BT - Proceedings of ELM-2015, Vol. 1: Theory, Algorithms and Applications (I)

A2 - Cao, J.

A2 - Mao, K.

A2 - Wu, J.

A2 - Lendasse, A.

PB - Springer

CY - Dordrecht

ER -

Luo Y, Yang B, Xu L, Hao L, Liu J, Yao Y et al. Segmentation of the left ventricle in cardiac MRI using an ELM model. In Cao J, Mao K, Wu J, Lendasse A, redacteurs, Proceedings of ELM-2015, Vol. 1: Theory, Algorithms and Applications (I). Dordrecht: Springer. 2016. blz. 147-157. (Proceedings in Adaptation Learning and Optimization). https://doi.org/10.1007/978-3-319-28397-5_12