Cardiac MR Image Segmentation and Quality Control in the Presence of Respiratory Motion Artifacts Using Simulated Data

Sina Amirrajab; Yasmina Al Khalil; Josien Pluim; Marcel Breeuwer; Cian M. Scannell

doi:10.1007/978-3-031-23443-9_44

Cardiac MR Image Segmentation and Quality Control in the Presence of Respiratory Motion Artifacts Using Simulated Data

Sina Amirrajab, Yasmina Al Khalil, Josien Pluim, Marcel Breeuwer, Cian M. Scannell

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

Abstract

In this work, we propose solutions for the two tasks of the CMRxMotion challenge; 1) quality control and 2) image segmentation in the presence of respiratory motion artifacts. We develop a k-space based motion simulation approach to generate cardiac MR images with respiratory motion artifacts on open-source artifact-free data to handle data scarcity. For task 1, a motion-denoising auto-encoder is trained to reconstruct motion-free images from the pairs of images with and without simulated motion. The encoder part of the auto-encoder is used as a feature extractor for a fully-connected classifier. For task 2, an ensemble of modified 2D nn-Unet models is proposed to tackle different aspects of variations in the data with the purpose of improving the robustness of the model to images hampered by respiratory motion artifacts. All proposed models in this paper are trained using the images with simulated motion artifacts. The proposed quality control model achieves a classification accuracy of 0.75 with the Cohen’s kappa coefficient of 0.64 and the ensemble model obtains the mean Dice scores of 0.922, 0.829, and 0.910 respectively for the left ventricle, myocardium, and right ventricle segmentation on the validation set of the CMRxMotion challenge.

Original language	English
Title of host publication	Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers
Subtitle of host publication	13th International Workshop, STACOM 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Revised Selected Papers
Editors	Oscar Camara, Esther Puyol-Antón, Avan Suinesiaputra, Alistair Young, Chen Qin, Maxime Sermesant, Shuo Wang
Place of Publication	Cham
Publisher	Springer
Chapter	44
Pages	466-475
Number of pages	10
ISBN (Electronic)	978-3-031-23443-9
ISBN (Print)	978-3-031-23442-2
DOIs	https://doi.org/10.1007/978-3-031-23443-9_44
Publication status	Published - 2022
Event	13th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2022, held in conjunction with the 25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022 - Singapore, Singapore Duration: 18 Sept 2022 → 18 Sept 2022

Publication series

Name	Lecture Notes in Computer Science (LNCS)
Volume	13593
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	13th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2022, held in conjunction with the 25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022
Country/Territory	Singapore
City	Singapore
Period	18/09/22 → 18/09/22

Bibliographical note

Funding Information:
Acknowledgments. This research is a part of the openGTN project, supported by the European Union in the Marie Curie Innovative Training Networks (ITN) fellowship program under project No. 764465.

Funding

Acknowledgments. This research is a part of the openGTN project, supported by the European Union in the Marie Curie Innovative Training Networks (ITN) fellowship program under project No. 764465.

Keywords

Cardiac image segmentation
Motion artifact simulation
Quality control
Respiratory motion artifacts

Access to Document

10.1007/978-3-031-23443-9_44

Cite this

Amirrajab, S., Al Khalil, Y., Pluim, J., Breeuwer, M., & Scannell, C. M. (2022). Cardiac MR Image Segmentation and Quality Control in the Presence of Respiratory Motion Artifacts Using Simulated Data. In O. Camara, E. Puyol-Antón, A. Suinesiaputra, A. Young, C. Qin, M. Sermesant, & S. Wang (Eds.), Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers : 13th International Workshop, STACOM 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Revised Selected Papers (pp. 466-475). (Lecture Notes in Computer Science (LNCS); Vol. 13593). Springer. https://doi.org/10.1007/978-3-031-23443-9_44

Amirrajab, Sina ; Al Khalil, Yasmina ; Pluim, Josien et al. / Cardiac MR Image Segmentation and Quality Control in the Presence of Respiratory Motion Artifacts Using Simulated Data. Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers : 13th International Workshop, STACOM 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Revised Selected Papers. editor / Oscar Camara ; Esther Puyol-Antón ; Avan Suinesiaputra ; Alistair Young ; Chen Qin ; Maxime Sermesant ; Shuo Wang. Cham : Springer, 2022. pp. 466-475 (Lecture Notes in Computer Science (LNCS)).

@inproceedings{21d7ff1f0896447da6a2b72d6556ebdf,

title = "Cardiac MR Image Segmentation and Quality Control in the Presence of Respiratory Motion Artifacts Using Simulated Data",

abstract = "In this work, we propose solutions for the two tasks of the CMRxMotion challenge; 1) quality control and 2) image segmentation in the presence of respiratory motion artifacts. We develop a k-space based motion simulation approach to generate cardiac MR images with respiratory motion artifacts on open-source artifact-free data to handle data scarcity. For task 1, a motion-denoising auto-encoder is trained to reconstruct motion-free images from the pairs of images with and without simulated motion. The encoder part of the auto-encoder is used as a feature extractor for a fully-connected classifier. For task 2, an ensemble of modified 2D nn-Unet models is proposed to tackle different aspects of variations in the data with the purpose of improving the robustness of the model to images hampered by respiratory motion artifacts. All proposed models in this paper are trained using the images with simulated motion artifacts. The proposed quality control model achieves a classification accuracy of 0.75 with the Cohen{\textquoteright}s kappa coefficient of 0.64 and the ensemble model obtains the mean Dice scores of 0.922, 0.829, and 0.910 respectively for the left ventricle, myocardium, and right ventricle segmentation on the validation set of the CMRxMotion challenge.",

keywords = "Cardiac image segmentation, Motion artifact simulation, Quality control, Respiratory motion artifacts",

author = "Sina Amirrajab and {Al Khalil}, Yasmina and Josien Pluim and Marcel Breeuwer and Scannell, {Cian M.}",

note = "Funding Information: Acknowledgments. This research is a part of the openGTN project, supported by the European Union in the Marie Curie Innovative Training Networks (ITN) fellowship program under project No. 764465. ; 13th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2022, held in conjunction with the 25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022 ; Conference date: 18-09-2022 Through 18-09-2022",

year = "2022",

doi = "10.1007/978-3-031-23443-9_44",

language = "English",

isbn = "978-3-031-23442-2",

series = "Lecture Notes in Computer Science (LNCS)",

publisher = "Springer",

pages = "466--475",

editor = "Oscar Camara and Esther Puyol-Ant{\'o}n and Avan Suinesiaputra and Alistair Young and Chen Qin and Maxime Sermesant and Shuo Wang",

booktitle = "Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers",

address = "Germany",

}

Amirrajab, S , Al Khalil, Y , Pluim, J , Breeuwer, M & Scannell, CM 2022, Cardiac MR Image Segmentation and Quality Control in the Presence of Respiratory Motion Artifacts Using Simulated Data. in O Camara, E Puyol-Antón, A Suinesiaputra, A Young, C Qin, M Sermesant & S Wang (eds), Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers : 13th International Workshop, STACOM 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Revised Selected Papers. Lecture Notes in Computer Science (LNCS), vol. 13593, Springer, Cham, pp. 466-475, 13th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2022, held in conjunction with the 25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022, Singapore, Singapore, 18/09/22. https://doi.org/10.1007/978-3-031-23443-9_44

Cardiac MR Image Segmentation and Quality Control in the Presence of Respiratory Motion Artifacts Using Simulated Data. / Amirrajab, Sina ; Al Khalil, Yasmina ; Pluim, Josien et al.
Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers : 13th International Workshop, STACOM 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Revised Selected Papers. ed. / Oscar Camara; Esther Puyol-Antón; Avan Suinesiaputra; Alistair Young; Chen Qin; Maxime Sermesant; Shuo Wang. Cham: Springer, 2022. p. 466-475 (Lecture Notes in Computer Science (LNCS); Vol. 13593).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Cardiac MR Image Segmentation and Quality Control in the Presence of Respiratory Motion Artifacts Using Simulated Data

AU - Amirrajab, Sina

AU - Al Khalil, Yasmina

AU - Pluim, Josien

AU - Breeuwer, Marcel

AU - Scannell, Cian M.

N1 - Funding Information: Acknowledgments. This research is a part of the openGTN project, supported by the European Union in the Marie Curie Innovative Training Networks (ITN) fellowship program under project No. 764465.

PY - 2022

Y1 - 2022

N2 - In this work, we propose solutions for the two tasks of the CMRxMotion challenge; 1) quality control and 2) image segmentation in the presence of respiratory motion artifacts. We develop a k-space based motion simulation approach to generate cardiac MR images with respiratory motion artifacts on open-source artifact-free data to handle data scarcity. For task 1, a motion-denoising auto-encoder is trained to reconstruct motion-free images from the pairs of images with and without simulated motion. The encoder part of the auto-encoder is used as a feature extractor for a fully-connected classifier. For task 2, an ensemble of modified 2D nn-Unet models is proposed to tackle different aspects of variations in the data with the purpose of improving the robustness of the model to images hampered by respiratory motion artifacts. All proposed models in this paper are trained using the images with simulated motion artifacts. The proposed quality control model achieves a classification accuracy of 0.75 with the Cohen’s kappa coefficient of 0.64 and the ensemble model obtains the mean Dice scores of 0.922, 0.829, and 0.910 respectively for the left ventricle, myocardium, and right ventricle segmentation on the validation set of the CMRxMotion challenge.

AB - In this work, we propose solutions for the two tasks of the CMRxMotion challenge; 1) quality control and 2) image segmentation in the presence of respiratory motion artifacts. We develop a k-space based motion simulation approach to generate cardiac MR images with respiratory motion artifacts on open-source artifact-free data to handle data scarcity. For task 1, a motion-denoising auto-encoder is trained to reconstruct motion-free images from the pairs of images with and without simulated motion. The encoder part of the auto-encoder is used as a feature extractor for a fully-connected classifier. For task 2, an ensemble of modified 2D nn-Unet models is proposed to tackle different aspects of variations in the data with the purpose of improving the robustness of the model to images hampered by respiratory motion artifacts. All proposed models in this paper are trained using the images with simulated motion artifacts. The proposed quality control model achieves a classification accuracy of 0.75 with the Cohen’s kappa coefficient of 0.64 and the ensemble model obtains the mean Dice scores of 0.922, 0.829, and 0.910 respectively for the left ventricle, myocardium, and right ventricle segmentation on the validation set of the CMRxMotion challenge.

KW - Cardiac image segmentation

KW - Motion artifact simulation

KW - Quality control

KW - Respiratory motion artifacts

UR - http://www.scopus.com/inward/record.url?scp=85148045577&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-23443-9_44

DO - 10.1007/978-3-031-23443-9_44

M3 - Conference contribution

AN - SCOPUS:85148045577

SN - 978-3-031-23442-2

T3 - Lecture Notes in Computer Science (LNCS)

SP - 466

EP - 475

BT - Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers

A2 - Camara, Oscar

A2 - Puyol-Antón, Esther

A2 - Suinesiaputra, Avan

A2 - Young, Alistair

A2 - Qin, Chen

A2 - Sermesant, Maxime

A2 - Wang, Shuo

PB - Springer

CY - Cham

T2 - 13th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2022, held in conjunction with the 25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022

Y2 - 18 September 2022 through 18 September 2022

ER -

Amirrajab S , Al Khalil Y , Pluim J , Breeuwer M , Scannell CM. Cardiac MR Image Segmentation and Quality Control in the Presence of Respiratory Motion Artifacts Using Simulated Data. In Camara O, Puyol-Antón E, Suinesiaputra A, Young A, Qin C, Sermesant M, Wang S, editors, Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers : 13th International Workshop, STACOM 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, Revised Selected Papers. Cham: Springer. 2022. p. 466-475. (Lecture Notes in Computer Science (LNCS)). doi: 10.1007/978-3-031-23443-9_44