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

Abstract

Background Cardiovascular magnetic resonance (CMR) cine displacement encoding with stimulated echoes (DENSE) measures heart motion by encoding myocardial displacement into the signal phase, facilitating high accuracy and reproducibility of global and segmental myocardial strain and providing benefits in clinical performance. While conventional methods for strain analysis of DENSE images are faster than those for myocardial tagging, they still require manual user assistance. The present study developed and evaluated deep learning methods for fully-automatic DENSE strain analysis. Methods Convolutional neural networks (CNNs) were developed and trained to (a) identify the left-ventricular (LV) epicardial and endocardial borders, (b) identify the anterior right-ventricular (RV)-LV insertion point, and (c) perform phase unwrapping. Subsequent conventional automatic steps were employed to compute strain. The networks were trained using 12,415 short-axis DENSE images from 45 healthy subjects and 19 heart disease patients and were tested using 10,510 images from 25 healthy subjects and 19 patients. Each individual CNN was evaluated, and the end-to-end fully-automatic deep learning pipeline was compared to conventional user-assisted DENSE analysis using linear correlation and Bland Altman analysis of circumferential strain. Results LV myocardial segmentation U-Nets achieved a DICE similarity coefficient of 0.87 ± 0.04, a Hausdorff distance of 2.7 ± 1.0 pixels, and a mean surface distance of 0.41 ± 0.29 pixels in comparison with manual LV myocardial segmentation by an expert. The anterior RV-LV insertion point was detected within 1.38 ± 0.9 pixels compared to manually annotated data. The phase-unwrapping U-Net had similar or lower mean squared error vs. ground-truth data compared to the conventional path-following method for images with typical signal-to-noise ratio (SNR) or low SNR (p < 0.05), respectively. Bland–Altman analyses showed biases of 0.00 ± 0.03 and limits of agreement of − 0.04 to 0.05 or better for deep learning-based fully-automatic global and segmental end-systolic circumferential strain vs. conventional user-assisted methods. Conclusions Deep learning enables fully-automatic global and segmental circumferential strain analysis of DENSE CMR providing excellent agreement with conventional user-assisted methods. Deep learning-based automatic strain analysis may facilitate greater clinical use of DENSE for the quantification of global and segmental strain in patients with cardiac disease.

Reproducibility of global and segmental myocardial strain using cine DENSE at 3 T: a multicenter cardiovascular magnetic resonance study in healthy subjects and patients with heart disease

“…This user is referred to as User UVA. As fully automatic deep learning (DL) methods have recently been developed for whole-slice and segmental E cc analysis of short-axis DENSE images [ 30 ], inter-user reproducibility was also assessed for DL vs. User 1 of all sites.…”

Suppression of artifact‐generating echoes in cine DENSE using deep learning

“…The SNR of DAS‐Net‐processed images was assessed and compared with that of phase‐cycled images. Because DENSE measures displacement using the myocardial phase, we measured the phase SNR 47 that was computed as described in Equation , as follows 48 :where the mean unwrapped phase of an end‐systolic region of interest measures the DENSE phase in the region with greatest displacement (representing the signal of interest), and the standard deviation of the phase of the end‐diastolic myocardium provides a measure of the standard deviation of phase at a cardiac frame where the mean phase is essentially zero.…”

“…[44][45][46] The SNR of DAS-Net-processed images was assessed and compared with that of phase-cycled images. Because DENSE measures displacement using the myocardial phase, we measured the phase SNR 47 that was computed as described in Equation 3 , as follows 48 :…”

Artificial Intelligence in Cardiac MRI: Is Clinical Adoption Forthcoming?

“…A similar approach was employed for automatic quantification of LV mass and scar volume on LGE images and has been successfully applied in patients post myocardial infarction ( 25 ). Additional applications of convolutional neural networks include automated phase velocity estimation and four-dimensional flow dataset segmentation along with the estimation of global and segmental myocardial strain in Displacement Encoding with stimulated echoes (DENSE) images, Figure 6 ( 26 , 27 ). Significant benefits include efficient CMR reporting and high levels of reproducibility in the measurements.…”

“…The AI-based end-systolic circumferential strain (Ecc) maps (left column), segmental (middle column) and global (right column) circumferential strain–time curves for a healthy subject (A) and a heart failure patient (B) demonstrate very close agreement with the conventional segmentation in the depicted mid-ventricular slices. Ghadimi et al ( 26 ). The article is published Open Access under a CC BY licence ( https://creativecommons.org/licenses/by/4.0/ ).…”