An nnU-Net Model to Enhance Segmentation of Cardiac Cine DENSE-MRI Using Phase Information
Authors:
- 3 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 670-673
Abstract
This study explores the application of deep learning to the segmentation of DENSE cardiovascular magnetic resonance (CMR) images, which is an important step in the analysis of cardiac deformation and may help in the diagnosis of heart conditions. A self-adapting method based on the nnU-Net framework is introduced to enhance the accuracy of DENSE-MR image segmentation, with a particular focus on the left ventricle myocardium (LVM) and left ventricle cavity (LVC), by leveraging the phase information in the cine DENSE-MR images. Two models are built and compared: 1) $\text{Model}_{\mathrm{M}}$ , which uses only the magnitude of the DENSE-MR images; and 2) $\text{Model}_{\text{MP}}$ , which incorporates magnitude and phase images. DENSE-MR images from 10 human volunteers processed using the DENSE-Analysis MATLAB toolbox were included in this study. The two models were trained using a 2D UNet-based architecture with a loss function combining the Dice similarity coefficient (DSC) and cross-entropy. The findings show the effectiveness of leveraging the phase information with $\text{Model}_{\text{MP}}$ resulting in a higher DSC and improved image segmentation, especially in challenging cases, e.g., at early systole and with basal and apical slices.
Keywords
Funding Information
- National Science Foundation (2205043)
This publication has 9 references indexed in Scilit:
- Medical image analysis using deep learning algorithmsFrontiers in Public Health, 2023
- Automated segmentation of long and short axis DENSE cardiovascular magnetic resonance for myocardial strain analysis using spatio-temporal convolutional neural networksJournal of Cardiovascular Magnetic Resonance, 2023
- Automated segmentation of biventricular contours in tissue phase mapping using deep learningNMR in Biomedicine, 2021
- A Multi-step Machine Learning Approach for Short Axis MR Images Segmentation2021
- Fully-automated global and segmental strain analysis of DENSE cardiovascular magnetic resonance using deep learning for segmentation and phase unwrappingJournal of Cardiovascular Magnetic Resonance, 2021
- Fast and Automated Segmentation for the Three-Directional Multi-Slice Cine Myocardial Velocity MappingDiagnostics, 2021
- nnU-Net: a self-configuring method for deep learning-based biomedical image segmentationNature Methods, 2020
- Machine learning in cardiovascular magnetic resonance: basic concepts and applicationsJournal of Cardiovascular Magnetic Resonance, 2019
- Tracking Myocardial Motion From Cine DENSE Images Using Spatiotemporal Phase Unwrapping and Temporal FittingIEEE Transactions on Medical Imaging, 2007