Search Results (7)

To develop and assess MyoNet, a deep learning (DL)-based network for measuring myocardial regional function from cine cardiac magnetic resonance (CMR) images, and compare its efficacy with ResMyoNet as an efficient alternative to SinMod-derived reference. MyoNet was tested alongside ResMyoNet on datasets from Dahl salt-sensitive rat models undergoing radiation therapy (RT). Both networks were designed to extract displacement maps from cine images, were specifically optimized for detailed myocardial deformation, employed advanced convolution operations with alternating kernel sizes for spatial and temporal analysis, and robust loss functions. MyoNet demonstrated superior performance in myocardial strain measurement, achieving high consistency with the SinMod-derived reference strains. It outperformed ResMyoNet, achieving higher performance metrics, including SSIM of 0.961 and 0.960, ICC of 0.973 and 0.975, and Pearson CC of 0.973 and 0.953 for circumferential (Ecc) and radial (Err) strains, respectively. Its accuracy and efficiency in generating strain measurements were validated through comprehensive statistical analyses. MyoNet offers a significant advancement in myocardial strain analysis from cine CMR images, potentially revolutionizing cardiac imaging in pre-clinical studies. Its ability to provide detailed and reliable measurements positions it as a valuable tool for clinical applications, particularly in monitoring the cardiac health of cancer patients. Full article

Background/Objectives: Duchenne Muscular Dystrophy (DMD) is a prevalent fatal genetic disorder, and heart failure is the leading cause of mortality. Peak left ventricular (LV) circumferential strain (E_cc), twist, and circumferential-longitudinal shear angle (θ_CL) are promising biomarkers for the improved and early diagnosis of incipient heart failure. Our goals were as follows: 1) to characterize a spectrum of functional and rotational LV biomarkers in boys with DMD compared with healthy age-matched controls; and 2) to identify LV biomarkers of early cardiomyopathy in the absence of abnormal LVEF or LGE. Methods: Boys with DMD (N = 43) and age-matched healthy volunteers (N = 16) were prospectively enrolled and underwent a 3T CMR exam after obtaining informed consent. Breath-held MRI tagging was used to estimate left ventricular E_cc at the mid-ventricular level as well as the twist, torsion, and θ_CL between basal and apical LV short-axis slices. A two-tailed t-test with unequal variance was used to test group-wise differences. Multiple comparisons were performed with Holm–Sidak post hoc correction. Multiple-regression analysis was used to test for correlations among biomarkers. A binomial logistic regression model assessed each biomarker’s ability to distinguish the following: (1) healthy volunteers vs. DMD patients, (2) healthy volunteers vs. LGE(−) DMD patients, and (3) LGE(−) DMD patients vs. LGE(+) DMD patients. Results: There was a significant impairment in the peak mid-wall E_cc [−17.0 ± 4.2% vs. −19.5 ± 1.9%, p < 7.8 × 10⁻³], peak LV twist (10.4 ± 4.3° vs. 15.6 ± 3.1°, p < 8.1 × 10⁻⁴), and peak LV torsion (2.03 ± 0.82°/mm vs. 2.8 ± 0.5°/mm, p < 2.6 × 10⁻³) of LGE(−) DMD patients when compared to healthy volunteers. There was a further significant reduction in the E_cc, twist, torsion, and θ_CL for LGE(+) DMD patients when compared to LGE(−) DMD patients. In the LGE(+) DMD patients, age significantly correlated with LVEF (r² = 0.42, p = 9 × 10⁻³), peak mid-wall E_cc (r² = 0.27, p = 0.046), peak LV Twist (r² = 0.24, p = 0.06), peak LV torsion (r² = 0.28, p = 0.04), and peak LV θ_CL (r² = 0.23, p = 0.07). In the LGE(−) DMD patients, only the peak mid-wall E_cc was significantly correlated with age (r² = 0.25, p = 0.006). The peak LV twist outperformed the peak mid-wall LV E_cc and EF in distinguishing DMD patients from healthy volunteer groups (AUC = 0.88, 0.80, and 0.72), as well as in distinguishing LGE(−) DMD patients from healthy volunteers (AUC = 0.83, 0.74, and 0.62). The peak LV twist and peak mid-wall LV E_cc performed similarly in distinguishing the LGE(−) and LGE(+) DMD cohorts (AUC = 0.74, 0.77, and 0.79). Conclusions: The peak mid-wall LV E_cc, peak LV twist, peak LV torsion, and peak LV θ_CL were significantly impaired in advance of the decreased LVEF and the development of focal myocardial fibrosis in boys with DMD and therefore were apparent prior to significant irreversible injury. Full article

Cardiac magnetic resonance (CMR) allows for analysis of cardiac function and myocardial tissue characterization. Increased left ventricular mass (LVM) is an independent predictor of cardiovascular events; however, the diagnosis of left ventricular hypertrophy and its prognostic value strongly depend on the LVM indexation method. Evaluation of the quantity and distribution of late gadolinium enhancement assists in clinical decisions on diagnosis, cardiovascular assessment, and interventions, including the placement of cardiac implantable electronic devices and the choice of an optimal procedural approach. Novel CMR techniques, such as T1 and T2 mapping, may be used for the longitudinal follow-up of myocardial fibrosis and myocardial edema or inflammation in different groups of patients, including patients with systemic sclerosis, myocarditis, cardiac sarcoidosis, amyloidosis, and both ischemic and non-ischemic cardiomyopathy, among others. Moreover, CMR tagging and feature tracking techniques might improve cardiovascular risk stratification in patients with different etiologies of left ventricular dysfunction. This review summarizes the knowledge about the current role of CMR in diagnostics and cardiovascular risk assessment to enable more personalized approach in clinical decision making. Full article

Subclinical alterations in myocardial structure and function occur early during the natural disease course. In contrast, clinically overt signs and symptoms occur during late phases, being associated with worse outcomes. Identification of such subclinical changes is critical for timely diagnosis and accurate management. Hence, implementing cost-effective imaging techniques with accuracy and reproducibility may improve long-term prognosis. A growing body of evidence supports using cardiac magnetic resonance (CMR) to quantify deformation parameters. Tissue-tagging (TT-CMR) and feature-tracking CMR (FT-CMR) can measure longitudinal, circumferential, and radial strains and recent research emphasize their diagnostic and prognostic roles in ischemic heart disease and primary myocardial illnesses. Additionally, these methods can accurately determine LV wringing and functional dynamic geometry parameters, such as LV torsion, twist/untwist, LV sphericity index, and long-axis strain, and several studies have proved their utility in prognostic prediction in various cardiovascular patients. More recently, few yet important studies have suggested the superiority of fast strain-encoded imaging CMR-derived myocardial strain in terms of accuracy and significantly reduced acquisition time, however, more studies need to be carried out to establish its clinical impact. Herein, the current review aims to provide an overview of currently available data regarding the role of CMR in evaluating myocardial strain and biomechanics. Full article

The use of deep learning (DL) segmentation in cardiac MRI has the potential to streamline the radiology workflow, particularly for the measurement of myocardial strain. Recent efforts in DL motion tracking models have drastically reduced the time needed to measure the heart’s displacement field and the subsequent myocardial strain estimation. However, the selection of initial myocardial reference points is not automated and still requires manual input from domain experts. Segmentation of the myocardium is a key step for initializing reference points. While high-performing myocardial segmentation models exist for cine images, this is not the case for tagged images. In this work, we developed and compared two novel DL models (nnU-net and Segmentation ResNet VAE) for the segmentation of myocardium from tagged CMR images. We implemented two methods to transform cardiac cine images into tagged images, allowing us to leverage large public annotated cine datasets. The cine-to-tagged methods included (i) a novel physics-driven transformation model, and (ii) a generative adversarial network (GAN) style transfer model. We show that pretrained models perform better (+2.8 Dice coefficient percentage points) and converge faster (6×) than models trained from scratch. The best-performing method relies on a pretraining with an unpaired, unlabeled, and structure-preserving generative model trained to transform cine images into their tagged-appearing equivalents. Our state-of-the-art myocardium segmentation network reached a Dice coefficient of 0.828 and 95th percentile Hausdorff distance of 4.745 mm on a held-out test set. This performance is comparable to existing state-of-the-art segmentation networks for cine images. Full article

Purpose: In recent years, cardiac magnetic resonance (CMR) has been used to assess LV diastolic function. In this systematic review, studies were identified where CMR parameters had been evaluated in healthy and/or patient groups with proven diastolic dysfunction or known to develop heart failure with preserved ejection fraction. We aimed at describing the parameters most often used, thresholds where possible, and correlation to echocardiographic and invasive measurements. Methods and results: A systematic literature review was performed using the databases of PubMed, Embase, and Cochrane. In total, 3808 articles were screened, and 102 studies were included. Four main CMR techniques were identified: tagging; time/volume curves; mitral inflow quantification with velocity-encoded phase-contrast sequences; and feature tracking. Techniques were described and estimates were presented in tables. From published studies, peak change of torsion shear angle versus volume changes in early diastole (−dφ′/dV′) (from tagging analysis), early peak filling rate indexed to LV end-diastolic volume <2.1 s⁻¹ (from LV time-volume curve analysis), enlarged LA maximal volume >52 mL/m², lowered LA total (<40%), and lowered LA passive emptying fractions (<16%) seem to be reliable measures of LV diastolic dysfunction. Feature tracking, especially of the atrium, shows promise but is still a novel technique. Conclusion: CMR techniques of LV untwisting and early filling and LA measures of poor emptying are promising for the diagnosis of LV filling impairment, but further research in long-term follow-up studies is needed to assess the ability for the parameters to predict patient related outcomes. Full article

In this study, we used a single commercially available software solution to assess global longitudinal (GLS) and global circumferential strain (GCS) using cardiac computed tomography (CT) and cardiac magnetic resonance (CMR) feature tracking (FT). We compared agreement and reproducibility between these two methods and the reference standard, CMR tagging (TAG). Twenty-seven patients with severe aortic stenosis underwent CMR and cardiac CT examinations. FT analysis was performed using Medis suite version 3.0 (Leiden, The Netherlands) software. Segment (Medviso) software was used for GCS assessment from tagged images. There was a trend towards the underestimation of GLS by CT-FT when compared to CMR-FT (19.4 ± 5.04 vs. 22.40 ± 5.69, respectively; p = 0.065). GCS values between TAG, CT-FT, and CMR-FT were similar (p = 0.233). CMR-FT and CT-FT correlated closely for GLS (r = 0.686, p < 0.001) and GCS (r = 0.707, p < 0.001), while both of these methods correlated moderately with TAG for GCS (r = 0.479, p < 0.001 for CMR-FT vs. TAG; r = 0.548 for CT-FT vs. TAG). Intraobserver and interobserver agreement was excellent in all techniques. Our findings show that, in elderly patients with severe aortic stenosis (AS), the FT algorithm performs equally well in CMR and cardiac CT datasets for the assessment of GLS and GCS, both in terms of reproducibility and agreement with the gold standard, TAG. Full article