Reliable segmentation of 2D cardiac magnetic resonance perfusion image sequences using time as the 3rd dimension
- PDF / 2,251,864 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 92 Downloads / 243 Views
CARDIAC
Reliable segmentation of 2D cardiac magnetic resonance perfusion image sequences using time as the 3rd dimension Veit Sandfort 1,2
&
Matthew Jacobs 2,3 & Andrew E. Arai 2 & Li-Yueh Hsu 2,4
Received: 19 May 2020 / Revised: 17 August 2020 / Accepted: 5 November 2020 # This is a U.S. government work and not under copyright protection in the U.S.; foreign copyright protection may apply 2020
Abstract Objectives Cardiac magnetic resonance (CMR) first-pass perfusion is an established noninvasive diagnostic imaging modality for detecting myocardial ischemia. A CMR perfusion sequence provides a time series of 2D images for dynamic contrast enhancement of the heart. Accurate myocardial segmentation of the perfusion images is essential for quantitative analysis and it can facilitate automated pixel-wise myocardial perfusion quantification. Methods In this study, we compared different deep learning methodologies for CMR perfusion image segmentation. We evaluated the performance of several image segmentation methods using convolutional neural networks, such as the U-Net in 2D and 3D (2D plus time) implementations, with and without additional motion correction image processing step. We also present a modified U-Net architecture with a novel type of temporal pooling layer which results in improved performance. Results The best DICE scores were 0.86 and 0.90 for LV myocardium and LV cavity, while the best Hausdorff distances were 2.3 and 2.1 pixels for LV myocardium and LV cavity using 5-fold cross-validation. The methods were corroborated in a second independent test set of 20 patients with similar performance (best DICE scores 0.84 for LV myocardium). Conclusions Our results showed that the LV myocardial segmentation of CMR perfusion images is best performed using a combination of motion correction and 3D convolutional networks which significantly outperformed all tested 2D approaches. Reliable frame-by-frame segmentation will facilitate new and improved quantification methods for CMR perfusion imaging. Key Points • Reliable segmentation of the myocardium offers the potential to perform pixel level perfusion assessment. • A deep learning approach in combination with motion correction, 3D (2D + time) methods, and a deep temporal connection module produced reliable segmentation results. Keywords Deep learning . Image segmentation . Cardiac magnetic resonance imaging . Myocardial perfusion
Abbreviations CMR Cardiac magnetic resonance imaging DTC Deeply temporally connected pooling layer GPU Graphics processing unit
LV MOCO
Left ventricle Motion corrected
Introduction * Veit Sandfort [email protected] 1
Stanford Medicine, Pasteur Drive 300, Stanford, CA 94305, USA
2
National Heart Lung and Blood Institute, National Institutes of Health, Bethesda, MD, USA
3
Department of Electrical Engineering and Computer Science, The Catholic University of America, Washington, DC, USA
4
Clinical Center, National Institutes of Health, Bethesda, MD, USA
Cardiac magnetic resonance (CMR) is an established noninvasive diag
Data Loading...
