Evaluation of fully automated myocardial segmentation techniques in native and contrast‐enhanced T1‐mapping cardiovascular magnetic resonance images using fully convolutional neural networks

PURPOSE: T1-mapping cardiac magnetic resonance (CMR) imaging permits noninvasive quantification of myocardial fibrosis (MF); however, manual delineation of myocardial boundaries is time-consuming and introduces user-dependent variability for such measurements. In this study, we compare several automated pipelines for myocardial segmentation of the left ventricle (LV) in native and contrast-enhanced T1-maps using fully convolutional neural networks (CNNs). METHODS: Sixty patients with known MF across three distinct cardiomyopathy states (20 ischemic (ICM), 20 dilated (DCM), and 20 hypertrophic (HCM)) underwent a standard CMR imaging protocol inclusive of cinematic (CINE), late gadolinium enhancement (LGE), and pre/post-contrast T1 imaging. Native and contrast-enhanced T1-mapping was performed using a shortened modified Look-Locker imaging (shMOLLI) technique at the basal, mid-level, and/or apex of the LV. Myocardial segmentations in native and post-contrast T1-maps were performed using three state-of-the-art CNN-based methods: standard U-Net, densely connected neural networks (Dense Nets), and attention networks (Attention Nets) after dividing the dataset using fivefold cross validation. These direct segmentation techniques were compared to an alternative registration-based segmentation method, wherein spatially corresponding CINE images are segmented automatically using U-Net, and a nonrigid registration technique transforms and propagates CINE contours to the myocardial regions of T1-maps. The methodologies were validated in 125 native and 100 contrast-enhanced T1-maps using standard segmentation accuracy metrics. Pearson correlation coefficient r and Bland-Altman analysis were used to compare the computed global T1 values derived by manual, U-Net, and CINE registration methodologies. RESULTS: The U-Net-based method yielded optimal results in myocardial segmentation of native, contrast-enhanced, and CINE images compared to Dense Nets and Attention Nets. The direct U-Net-based method outperformed the CINE registration-based method in native T1-maps, yielding Dice similarity coefficient (DSC) of 82.7 ± 12% compared to 81.4 ± 6.9% (P < 0.0001). However, in contrast-enhanced T1-maps, the CINE-registration-based method outperformed direct U-Net segmentation, yielding DSC of 77.0 ± 9.6% vs 74.2 ± 18% across all patient groups (P = 0.0014) and specifically 73.2 ± 7.3% vs 65.5 ± 18% in the ICM patient group. High linear correlation of global T1 values was demonstrated in Pearson analysis of the U-Net-based technique and the CINE-registration technique in both native T1-maps (r = 0.93, P < 0.0001 and r = 0.87, P < 0.0001, respectively) and contrast-enhanced T1-maps (r = 0.93, P < 0.0001 and r = 0.98, P < 0.0001, respectively). CONCLUSIONS: The direct U-Net-based myocardial segmentation technique provided accurate, fully automated segmentations in native and contrast-enhanced T1-maps. Myocardial borders can alternatively be segmented from spatially matched CINE images and applied to T1-maps via deformation and propagation through a modality-independent neighborhood descriptor (MIND). The direct U-Net approach is more efficient in myocardial segmentation of native T1-maps and eliminates cross-technique dependence. However, the CINE-registration-based technique may be more appropriate for contrast-enhanced T1-maps and/or for patients with dense regions of replacement fibrosis, such as those with ICM.