Fully Automatic Segmentation of the Right Ventricle Via Multi-Task Deep Neural Networks

Liang Zhang; Georgios Vasileios Karanikolas; Mehmet Akcakaya; Georgios B. Giannakis

doi:10.1109/ICASSP.2018.8461556

Fully Automatic Segmentation of the Right Ventricle Via Multi-Task Deep Neural Networks

Liang Zhang, Georgios Vasileios Karanikolas, Mehmet Akcakaya, Georgios B. Giannakis

Electrical and Computer Engineering

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

20 Scopus citations

Abstract

Segmentation of ventricles from cardiac magnetic resonance (MR) images is a key step to obtaining clinical parameters useful for prognosis of cardiac pathologies. To improve upon the performance of existing fully convolutional network (FCN) based automatic right ventricle (RV) segmentation approaches, a multi-task deep neural network (DNN) architecture is proposed. The multi-task model can employ any FCN as a building block, allows for leveraging shared features between different tasks, and can be efficiently trained end-to-end. Specifically, a multi-task U-net is developed and implemented using the Tensorflow framework. Numerical tests on real datasets showcase the merits of the proposed approach and in particular its ability to offer improved segmentation performance for small-size RVs.

Original language	English (US)
Title of host publication	2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	6677-6681
Number of pages	5
ISBN (Print)	9781538646588
DOIs	https://doi.org/10.1109/ICASSP.2018.8461556
State	Published - Sep 10 2018
Event	2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Calgary, Canada Duration: Apr 15 2018 → Apr 20 2018

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2018-April
ISSN (Print)	1520-6149

Other

Other	2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
Country/Territory	Canada
City	Calgary
Period	4/15/18 → 4/20/18

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

Keywords

Convolutional neural networks
Multi-task learning
Right ventricle segmentation
U-net

Publisher link

10.1109/ICASSP.2018.8461556

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6938227

Find It

Find It at U of M Libraries

Cite this

Zhang, L., Karanikolas, G. V., Akcakaya, M., & Giannakis, G. B. (2018). Fully Automatic Segmentation of the Right Ventricle Via Multi-Task Deep Neural Networks. In 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings (pp. 6677-6681). Article 8461556 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2018-April). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2018.8461556

Fully Automatic Segmentation of the Right Ventricle Via Multi-Task Deep Neural Networks. / Zhang, Liang; Karanikolas, Georgios Vasileios; Akcakaya, Mehmet et al.
2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 6677-6681 8461556 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2018-April).

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

Zhang, L, Karanikolas, GV, Akcakaya, M & Giannakis, GB 2018, Fully Automatic Segmentation of the Right Ventricle Via Multi-Task Deep Neural Networks. in 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings., 8461556, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2018-April, Institute of Electrical and Electronics Engineers Inc., pp. 6677-6681, 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018, Calgary, Canada, 4/15/18. https://doi.org/10.1109/ICASSP.2018.8461556

Zhang L, Karanikolas GV, Akcakaya M , Giannakis GB. Fully Automatic Segmentation of the Right Ventricle Via Multi-Task Deep Neural Networks. In 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 6677-6681. 8461556. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2018.8461556

Zhang, Liang ; Karanikolas, Georgios Vasileios ; Akcakaya, Mehmet et al. / Fully Automatic Segmentation of the Right Ventricle Via Multi-Task Deep Neural Networks. 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 6677-6681 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{3eb57720bd4a4a4887dcd6ebe8d54490,

title = "Fully Automatic Segmentation of the Right Ventricle Via Multi-Task Deep Neural Networks",

abstract = "Segmentation of ventricles from cardiac magnetic resonance (MR) images is a key step to obtaining clinical parameters useful for prognosis of cardiac pathologies. To improve upon the performance of existing fully convolutional network (FCN) based automatic right ventricle (RV) segmentation approaches, a multi-task deep neural network (DNN) architecture is proposed. The multi-task model can employ any FCN as a building block, allows for leveraging shared features between different tasks, and can be efficiently trained end-to-end. Specifically, a multi-task U-net is developed and implemented using the Tensorflow framework. Numerical tests on real datasets showcase the merits of the proposed approach and in particular its ability to offer improved segmentation performance for small-size RVs.",

keywords = "Convolutional neural networks, Multi-task learning, Right ventricle segmentation, U-net",

author = "Liang Zhang and Karanikolas, {Georgios Vasileios} and Mehmet Akcakaya and Giannakis, {Georgios B.}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 ; Conference date: 15-04-2018 Through 20-04-2018",

year = "2018",

month = sep,

day = "10",

doi = "10.1109/ICASSP.2018.8461556",

language = "English (US)",

isbn = "9781538646588",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "6677--6681",

booktitle = "2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings",

}

TY - GEN

T1 - Fully Automatic Segmentation of the Right Ventricle Via Multi-Task Deep Neural Networks

AU - Zhang, Liang

AU - Karanikolas, Georgios Vasileios

AU - Akcakaya, Mehmet

AU - Giannakis, Georgios B.

PY - 2018/9/10

Y1 - 2018/9/10

N2 - Segmentation of ventricles from cardiac magnetic resonance (MR) images is a key step to obtaining clinical parameters useful for prognosis of cardiac pathologies. To improve upon the performance of existing fully convolutional network (FCN) based automatic right ventricle (RV) segmentation approaches, a multi-task deep neural network (DNN) architecture is proposed. The multi-task model can employ any FCN as a building block, allows for leveraging shared features between different tasks, and can be efficiently trained end-to-end. Specifically, a multi-task U-net is developed and implemented using the Tensorflow framework. Numerical tests on real datasets showcase the merits of the proposed approach and in particular its ability to offer improved segmentation performance for small-size RVs.

AB - Segmentation of ventricles from cardiac magnetic resonance (MR) images is a key step to obtaining clinical parameters useful for prognosis of cardiac pathologies. To improve upon the performance of existing fully convolutional network (FCN) based automatic right ventricle (RV) segmentation approaches, a multi-task deep neural network (DNN) architecture is proposed. The multi-task model can employ any FCN as a building block, allows for leveraging shared features between different tasks, and can be efficiently trained end-to-end. Specifically, a multi-task U-net is developed and implemented using the Tensorflow framework. Numerical tests on real datasets showcase the merits of the proposed approach and in particular its ability to offer improved segmentation performance for small-size RVs.

KW - Convolutional neural networks

KW - Multi-task learning

KW - Right ventricle segmentation

KW - U-net

UR - http://www.scopus.com/inward/record.url?scp=85054265023&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054265023&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2018.8461556

DO - 10.1109/ICASSP.2018.8461556

M3 - Conference contribution

AN - SCOPUS:85054265023

SN - 9781538646588

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 6677

EP - 6681

BT - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018

Y2 - 15 April 2018 through 20 April 2018

ER -

Fully Automatic Segmentation of the Right Ventricle Via Multi-Task Deep Neural Networks

Abstract

Publication series

Other

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this