Fully Automated Myocardial Strain Estimation from Cardiovascular MRI–tagged Images Using a Deep Learning Framework in the UK Biobank

Abstract

C ardiovascular MRI tissue tagging is the noninvasive reference standard for myocardial strain estimation (1-4). Although cardiovascular MRI feature tracking allows calculation of strain from standard steady-state free precession images, features are limited to myocardial edges (5) and structures outside the myocardium (6), whereas cardiovascular MRI tagging enables detection and tracking of features within the myocardium. Displacement encoding with stimulated echoes (7,8) has the potential to provide higher spatial resolution strain estimates (9) but, to date, has not been as widely used (10). The utility of cardiovascular MRI tagging has been demonstrated in many different patient groups (4). However, there is a lack of robust fully automated analysis tools for the quantification of strain from cardiovascular MRI-tagged images, leading to analysis times that are prohibitive in a high-throughput setting, such as studies with many hundreds of cases or high-volume clinical centers with more than 20 cases per week (4,11,12). The most common approaches for strain analysis of cardiovascular MRI-tagged images include profile matching and spline fitting (13), deformable contours (14), harmonic phase analysis (15), and sine wave modeling (16). However, these methods require manual initialization and lack robustness. Recently, deep learning methods, particularly convolutional neural networks

Fully-automated global and segmental strain analysis of DENSE cardiovascular magnetic resonance using deep learning for segmentation and phase unwrapping

“…While other strain imaging methods may provide reliable and reproducible global strain values and are well-suited to automatic DL-based analysis [ 20 , 28 , 29 ], cine DENSE has shown excellent reproducibility of segmental strain [ 7 ]. Our present results build upon these prior findings for segmental strain, and show excellent agreement of DL-based fully-automated segmental strain with user-assisted semi-automatically computed segmental strain.…”

“…Our present results build upon these prior findings for segmental strain, and show excellent agreement of DL-based fully-automated segmental strain with user-assisted semi-automatically computed segmental strain. Interestingly, our limits of agreement for DL automatic vs. user-assisted segmental circumferential strain are better than those for DL vs. user-assisted analysis of myocardial-tagging-based global circumferential strain [ 29 ]. A potential explanation for the substantially better results for DENSE is that for tag analysis, DL is used to perform motion tracking, and even when trained using data from thousands of subjects, there is error in motion tracking [ 29 ].…”

“…In this study we aimed to develop a fully-automated post-processing approach for DENSE. Recently, deep learning (DL) methods, particularly convolutional neural networks (CNN), have shown promising results for segmentation and analysis of various CMR techniques [ 19 – 29 ]. In this work, we developed a pipeline for fully-automated analysis of cine DENSE data using four CNNs to (a) identify the LV epicardial border, (b) identify the LV endocardial border, (c) identify the anterior RV-LV insertion point, and (d) perform phase unwrapping of the LV myocardium.…”

Cardiac Magnetic Resonance in Pulmonary Hypertension—an Update

“…Reduced RA strain is associated with decompensated RV function and stiffness [ 48 , 49 ]. The advancement of fully automated myocardial strain analysis is likely to push its role in future research in the diagnosis and prognosis of PH [ 50 ].…”

DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics

“…The tagging-MRI-based motion estimates were registered and resampled to the cine-MRI space. Global strain and SR values throughout the entire cardiac cycle were derived from the resampled estimates as described in [42].…”