Left ventricle segmentation in LGE-MRI using multiclass learning

Conference contribution


Publication Details

Author(s): Kurzendorfer T, Breininger K, Steidl S, Maier A, Fahrig R
Editor(s): Bennett A. Landman, Elsa D. Angelini, Elsa D. Angelini, Elsa D. Angelini
Publisher: SPIE
Publication year: 2019
Volume: 10949
Conference Proceedings Title: Progress in Biomedical Optics and Imaging - Proceedings of SPIE
ISBN: 9781510625457
ISSN: 1605-7422


Abstract

Cardiovascular diseases are the major cause of death worldwide. Magnetic resonance imaging (MRI) is often used for the diagnosis of cardiac diseases because of its good soft tissue contrast. Furthermore, the fibrosis characterization of the myocardium can be important for accurate diagnosis and treatment planning. The clinical gold standard to visualize myocardial scarring is late gadolinium enhanced (LGE) MRI. However, the challenge arises in the accurate segmentation of the endocardial and epicardial border because of the smooth transition between the blood pool and scarred myocardium, as contrast agent accumulates in the damaged tissue and leads to hyper-enhancements. An exact segmentation, is essential for the scar tissue quantification. We propose a deep learning-based method to segment the left ventricle's endocardium and epicardium in LGE-MRI. To this end, a multi-scale fully convolutional neural network with skip-connections (U-Net) and residual units is applied to solve the multiclass segmentation problem. As a loss function, weighted cross-entropy is used. The network is trained on 70 clinical LGE MRI sequences, validated with 5, and evaluated with 26 data sets. The approach yields a mean Dice coefficient of 0.90 for the endocard and 0.87 for the epicard. The proposed method segments the endocardium and epicardium of the left ventricle fully automatically with a high accuracy.


FAU Authors / FAU Editors

Breininger, Katharina
Lehrstuhl für Informatik 5 (Mustererkennung)
Fahrig, Rebecca Prof. Dr.
Technische Fakultät
Maier, Andreas Prof. Dr.-Ing.
Lehrstuhl für Informatik 5 (Mustererkennung)
Steidl, Stefan PD Dr.
Lehrstuhl für Informatik 5 (Mustererkennung)


How to cite

APA:
Kurzendorfer, T., Breininger, K., Steidl, S., Maier, A., & Fahrig, R. (2019). Left ventricle segmentation in LGE-MRI using multiclass learning. In Bennett A. Landman, Elsa D. Angelini, Elsa D. Angelini, Elsa D. Angelini (Eds.), Progress in Biomedical Optics and Imaging - Proceedings of SPIE. San Diego, CA, US: SPIE.

MLA:
Kurzendorfer, Tanja, et al. "Left ventricle segmentation in LGE-MRI using multiclass learning." Proceedings of the Medical Imaging 2019: Image Processing, San Diego, CA Ed. Bennett A. Landman, Elsa D. Angelini, Elsa D. Angelini, Elsa D. Angelini, SPIE, 2019.

BibTeX: 

Last updated on 2019-16-07 at 08:38