Correlated Regression Feature Learning for Automated Right Ventricle Segmentation

Deep Learning Segmentation of the Right Ventricle in Cardiac MRI: The M&Ms Challenge

In recent years, several deep learning models have been proposed to accurately quantify and diagnose cardiac pathologies. These automated tools heavily rely on the accurate segmentation of cardiac structures in MRI images. However, segmentation of the right ventricle is challenging due to its highly complex shape and ill-defined borders. Hence, there is a need for new methods to handle such structure's geometrical and textural complexities, notably in the presence of pathologies such as Dilated Right Ventricle, Tricuspid Regurgitation, Arrhythmogenesis, Tetralogy of Fallot, and Inter-atrial Communication. The last MICCAI challenge on right ventricle segmentation was held in 2012 and included only 48 cases from a single clinical center. As part of the 12th Workshop on Statistical Atlases and Computational Models of the Heart (STACOM 2021), the M&Ms-2 challenge was organized to promote the interest of the research community around right ventricle segmentation in multi-disease, multi-view, and multi-center cardiac MRI. Three hundred sixty CMR cases, including short-axis and long-axis 4-chamber views, were collected from three Spanish hospitals using nine different scanners from three different vendors, and included a diverse set of right and left ventricle pathologies. The solutions provided by the participants show that nnU-Net achieved the best results overall. However, multi-view approaches were able to capture additional information, highlighting the need to integrate multiple cardiac diseases, views, scanners, and acquisition protocols to produce reliable automatic cardiac segmentation algorithms.

Anatomical structure segmentation from early fetal ultrasound sequences using global pollination CAT swarm optimizer-based Chan-Vese model

The structure of an early fetal heart provides essential information for the diagnosis of fetus defects. Accurate segmentation of anatomical structure is a major challenging task because of the small size, low signal-to-noise ratio, and rapid movement of the ultrasound images. In recent years, active contour methods have found applications to ultrasound image segmentation. The familiar region-based Chan-Vese (RCV) model is a strong and flexible technique that is able to segment many types of images compared to other active contours. However, the solution trapping in local minima is the main drawback determined on the RCV model with the exposure of improper initial contours. Also, the RCV model showed poor results with this situation. More probably, the images having large intensity differences between global and local structures usually suffered from this problem. To solve this issue, we develop an improved version of the RCV model which is expected to achieve satisfactory segmentation performance, irrespective of the initial selection of the contour. We have formulated a new and hybrid meta-heuristic optimization algorithm namely global pollination-based CAT swarm (GPCATS) optimizer to solve the fitting energy minimization problem. In the GPCATS method, the global pollination step of the flower pollination algorithm (FPA) is used for improving the distance averaging of the CATS algorithm. The performance of the proposed method was analyzed on different fetal heart ultrasound videos acquired from 12 subjects. Each frame of each video was manually annotated in order to provide labels for training and validating the model. Experimental results of the proposed model proved that the precision of locating boundaries is improved greatly and requires only a reduced number of iterations (75% less) for convergence compared to the traditional RCV model. This proposed method also proved that our model not only enhances the accuracy of locating boundaries but also works stronger robustness than some other active contour methods. Graphical Abstract Anatomical structure segmentation from early fetal ultrasound sequences using GPCATS based Chan-Vese Model.

Effect of myocardial heterogeneity on ventricular electro-mechanical responses: a computational study

BACKGROUND

The heart wall exhibits three layers of different thicknesses: the outer epicardium, mid-myocardium, and inner endocardium. Among these layers, the mid-myocardium is typically the thickest. As indicated by preliminary studies, heart-wall layers exhibit various characteristics with regard to electrophysiology, pharmacology, and pathology. Construction of an accurate three-dimensional (3D) model of the heart is important for predicting physiological behaviors. However, the wide variability of myocardial shapes and the unclear edges between the epicardium and soft tissues are major challenges in the 3D model segmentation approach for identifying the boundaries of the epicardium, mid-myocardium, and endocardium. Therefore, this results in possible variations in the heterogeneity ratios between the epicardium, mid-myocardium, and endocardium. The objective of this study was to observe the effects of different thickness ratios of the epicardium, mid-myocardium, and endocardium on cardiac arrhythmogenesis, reentry instability, and mechanical responses during arrhythmia.

METHODS

We used a computational method and simulated three heterogeneous ventricular models: Model 1 had the thickest M cell layer and thinnest epicardium and endocardium. Model 2 had intermediate layer thicknesses. Model 3 exhibited the thinnest mid-myocardium and thickest epicardium and endocardium. Electrical and mechanical simulations of the three heterogeneous models were performed under normal sinus rhythm and reentry conditions.

RESULTS

Model 1 exhibited the highest probability of terminating reentrant waves, and Model 3 exhibited to experience greater cardiac arrhythmia. In the reentry simulation, at 8 s, Model 3 generated the largest number of rotors (eight), while Models 1 and 2 produced five and seven rotors, respectively. There was no significant difference in the cardiac output obtained during the sinus rhythm. Under the reentry condition, the highest cardiac output was generated by Model 1 (19 mL/s), followed by Model 2 (9 mL/s) and Model 3 (7 mL/s).

CONCLUSIONS

A thicker mid-myocardium led to improvements in the pumping efficacy and contractility and reduced the probability of cardiac arrhythmia. Conversely, thinner M cell layers generated more unstable reentrant spiral waves and hindered the ventricular pumping.

The higher serum endocan levels may be a risk factor for the onset of cardiovascular disease: A meta-analysis

OBJECTIVE

Endothelial dysfunction was widely regarded as the initial lesion in the multifactorial pathogenesis of cardiovascular disease (CVD). Serum endocan, a novel endothelial dysfunction biochemical marker, is involved in the development of CVD. Here, we fulfilled a meta-analysis to evaluate the association between CVD and serum endocan levels.

METHOD

The relevant published literature was searched through large literature databases, including PubMed, Embase, Cochrane Library, SinoMed, and Web of Science, up to June 1, 2018. The data were extracted from the studies. Stata software was used to perform a meta-analysis.

RESULT

Fifteen original studies with a total of 1839 patients and 1258 controls fulfilled the inclusion criteria and were included in the study dataset. Meta-analysis showed that the levels of serum endocan in patients with hypertension, coronary artery disease, and coronary slow flow were higher than those in the control group. The pooled standardized mean differences and 95% confidence intervals of endocan concentrations in those 3 groups were 0.53 [0.19-0.86], P < .01; 0.99 [0.51-1.39], P < .01; and 0.62 [0.45-0.78], P < .01, respectively. Further analysis showed that the level of serum endocan in hypertension patients with coronary artery disease was higher than that in patients with hypertension (0.61 [0.30-0.92], P < .01). Sensitivity analysis and subgroup analysis were use to confirm the above results.

CONCLUSIONS

In this meta-analysis, we further confirmed that serum endocan level was significantly increased in the CVD population. The high serum endocan level may be one of the risk factors for CVD.

3.0T Contrast-enhanced whole-heart coronary magnetic resonance angiography for simultaneous coronary artery angiography and myocardial viability in chronic myocardial infarction: A single-center preliminary study

To evaluate the accuracy of contrast-enhanced whole-heart magnetic resonance coronary angiography at 3.0T for assessing significant stenosis (≥50% lumen diameter reduction) in patients with myocardial infarction, by using conventional coronary artery angiography as the reference standard, and also test the performance of that for the detection and assessment of chronic myocardial infarction (MI), compared with standard delayed-enhancement coronary magnetic resonance (DE-CMR) for the determination of infarct size.We studied 42 consecutive patients (37 men, 5 women, mean age 58.5 ± 10.7 years) with MI scheduled for conventional coronary angiography. Contrast-enhanced whole-heart coronary magnetic resonance angiography (CMRA) was employed after sublingual nitroglycerin (NTG) with the abdominal banding rolled tightly along the side of ribs. Finally, a 3D phase-sensitive inversion-recovery gradient-echo (3D-PSIR-GRE) sequence was performed during free breathing. The assessment of MI sizes on WH-CMRA reconstructed images and 3D-PSIR-GRE images were compared using a paired student t test.The acquisition of CMRA was completed in 40 (95.2%) of 42 patients, with an imaging time averaged at 9.5 ± 3.1 minutes. The average navigator efficiency was 47%. The sensitivity, specificity, and positive and negative predictive values of whole-heart CMRA for the detection of significant lesions on a segment-by-segment analysis were 91.7% (95% confidence interval [CI] 83.8-96.1), 84.0% (95% CI 80.0-87.4), 57.9% (95% CI 50.0-65.8), 97.7% (95% CI 95.3-98.9), respectively, and on a patient-based analysis 93.5% (95% CI 77.2-98.9), 88.9% (95% CI 50.7-99.4), 96.7% (95% CI 80.9-99.8), and 80.0% (95% CI 44.2-96.5), respectively. Infarcts were generally higher on the CE-CMRA technique compared with the standard technique (18.0 ± 7.2 cm vs 16.1 ± 6.4 cm; P < .0001).Contrast-enhanced whole-heart CMRA with 3.0-T not only may permit reliable detection of significant obstructive coronary artery disease in patients with myocardial infarction, but also could identify and quantify the volume of myocardial infarction. This technique could be considered the preferred approach in patients who could not overcome longer scanning times or unable to hold their breath instead of delayed-enhancement magnetic resonance imaging for detection of infarcted myocardium. However, compared with standard imaging, the volume of myocardial infarction is slightly overestimated.

Prognostic value role of radiofrequency lesion size by cardiac magnetic resonance imaging on outcomes of ablation in patients with ischemic scar-related ventricular tachycardia: A single center pilot study

Inadequate ablation lesion formation may be responsible for post-ablation ventricular tachycardia (VT) recurrences.We aimed to evaluate whether visualisation of radiofrequency (RF) lesion size by cardiac magnetic resonance imaging (CMR) has any role in predicting adequacy of lesion and in estimating outcome.Retrospective pilot studyNine consecutive patients (8 male, age 60 ± 13 years) underwent ablation for sustained VT because of ischemic scar were evaluated for pre- and post-procedure scar tissue by CMR to characterize ablation lesions. Microvascular obstruction (MVO) surrounded by late gadolinium enhancement was defined as irreversible RF lesion. All patients were followed for at least 6 months for recurrences.Five of the patients had previous inferior myocardial infarction (MI), whereas remaining 4 had anterior MI. Acute procedural success, as defined by termination of the arrhythmia without recurrence in 30 minutes, was attained in all patients. Contrast enhancement and wall motion abnormality in presumed infarction area were confirmed by pre-ablation CMR images. MVO was detected at the reported ablation site in 6/9 patients, all arrhythmia- and symptom-free at median 24 months (range 8-38 months) follow-up. In remaining 3 patients who had VT recurrence (clinical VT in 2, sustain VT with a new morphology in 1), MVO was not detected despite achievement of acute procedural success. There was no correlation with pre-ablation scar size and clinical arrhythmia recurrence.CMR is a useful imaging modality to guide ablation procedures by detecting scar tissue. Additionally MVO seen by post-procedural imaging may be related to adequacy of RF ablation lesions and may correlate with clinical outcome.

Vitamin D and bisphosphonates therapies for osteoporosis are associated with different risks of atrial fibrillation in women: A nationwide population-based analysis

Osteoporosis and atrial fibrillation (AF) are common in post-menopausal women. Vitamin D and bisphosphonates are widely used to treat osteoporosis, and these may have different effects on the risk of AF.The goal of this study was to evaluate whether different agents for treating osteoporosis modulate the risk of AF in a population-based database.We identified 20,788 female patients suffering from osteoporosis who were or were not treated with vitamin D or bisphosphonates using the Taiwan National Health Insurance nationwide database from 2000 to 2008 and followed them up for 5 consecutive years to determine if they had a new diagnosis of AF after the diagnosis of osteoporosis.There were 14 (2.67%) new AF diagnoses in osteoporosis patients treated with bisphosphonates, one (0.28%) new AF diagnosis in patients treated with vitamin D, and 279 (1.40%) new AF diagnoses in patients who were not treated with vitamin D or bisphosphonates (neither group). Osteoporosis patients who received bisphosphonates showed a higher incidence of AF occurrence than those that were not treated with bisphosphonates (P = .015). In contrast, 1 patient who received vitamin D had a new diagnosis of AF during the study period; thus, the incidence was significantly lower than that in the patients treated with bisphosphonates (P = .007). In addition, the patients who were treated with vitamin D had a lower incidence of AF than did those who were not treated with either vitamin D or bisphosphonates (P = .074). Kaplan-Meier analysis also showed a significant difference in AF occurrence in different groups during the 5-year follow-up (P = .010).Different treatment for osteoporosis may carry diverse risks of AF occurrence. Vitamin D may have potential beneficial effects of reducing AF occurrence in osteoporosis patients.

Tpeak-Tend/QT interval predicts ST-segment resolution and major adverse cardiac events in acute ST-segment elevation myocardial infarction patients undergoing percutaneous coronary intervention

Elevated ST-segment and increased Tpeak-Tend interval (Tp-e) were prognostic predictors in major adverse cardiac events (MACEs) in ST-segment elevation myocardial infarction (STEMI). The electrophysiologic relationship between them during percutaneous coronary intervention (PCI) needs to elucidate.Patients with STEMI admitted to hospital were prospectively evaluated. ST-segment resolution (STR) (defined as ≥50% reduction as the complete-STR [CSTR] group, <50% as incomplete-STR [ISTR] group), Tp-e interval, and ratio of Tp-e to QT interval (Tp-e/QT) were measured, calculated and analyzed with MACEs.Tp-ec interval (corrected Tp-e interval, P < .001) and Tp-e/QT ratio (P < .001) were significantly increased by myocardial infarction and partly recovered post-PCI. Patients with ISTR showed more increased Tp-ec interval (P < .001) and Tp-e/QT ratio (P < .001) than those in CSTR groups post-PCI. In multivariate analysis and receiver operating characteristic curves analysis, Tp-e/QT was an independent and strongest predictor for STR. STR and electrocardiogram parameters with a cutoff value for predicting STR showed prognostic value for MACE in STEMI in Kaplan-Meier survival analysis.Both STR and change of Tp-e parameters were not only predictors of arrhythmia, but also prognostic factors of MACE in patients with STEMI after PCI.

Quantitative evaluation of myocardial layer-specific strain using two-dimensional speckle tracking echocardiography among young adults with essential hypertension in China

The myocardial wall of the left ventricle is a complex, multilayered structure, which is altered in young adults with hypertension. The aim of this study was to define the characteristics of longitudinal and circumferential strain in young adults with hypertension.Two-dimensional speckle tracking echocardiography was used to analyze longitudinal and circumferential strain parameters in 67 young adults with hypertension, 70 older young adults with essential hypertension and 62 healthy adults.The global longitudinal strain (GLS) and global circumferential strain (GCS) was the highest at endocardium, and lowest at epicardium. A layer-specific analysis of myocardial deformation in all adults revealed that all of the peak systolic longitudinal strain (LS) and the peak systolic circumferential strain (CS) in the endocardium, mid-myocardium and epicardium were gradually increased from the base to the apex. The peak systolic LS showed significant differences at basal, mid-ventricular, and apical level among normal adults, young NLVH (nonleft ventricular hypertrophy), and young LVH (left ventricular hypertrophy). In all the adults with hypertension, young adults were associated with higher peak systolic longitudinal strain values compared with older adults, but the small differences of LS may be meaningless in clinical settings. Between the young LVH and older LVH, the peak systolic CS showed significant differences except data of epicardium at basal and mid-ventricular level.This study provides reference values for layer-specific strain in young adults with hypertension. This detailed strain analysis provides layer-oriented information to reveal the different characteristics of circumferential and longitudinal strain in young adults with hypertension. This systolic dysfunction could be detected conveniently and accurately by 2DSTE.

Texture analysis of magnetic resonance T1 mapping with dilated cardiomyopathy: A machine learning approach

The diagnosis of dilated cardiomyopathy (DCM) remains a challenge in clinical radiology. This study aimed to investigate whether texture analysis (TA) parameters on magnetic resonance T1 mapping can be helpful for the diagnosis of DCM.A total of 50 DCM cases were retrospectively screened and 24 healthy controls were prospectively recruited between March 2015 and July 2017. T1 maps were acquired using the Modified Look-Locker Inversion Recovery (MOLLI) sequence at a 3.0 T MR scanner. The endocardium and epicardium were drawn on the short-axis slices of the T1 maps by an experienced radiologist. Twelve histogram parameters and 5 gray-level co-occurrence matrix (GLCM) features were extracted during the TA. Differences in texture features between DCM patients and healthy controls were evaluated by t test. Support vector machine (SVM) was used to calculate the diagnostic accuracy of those texture parameters.Most histogram features were higher in the DCM group when compared to healthy controls, and 9 of these had significant differences between the DCM group and healthy controls. In terms of GLCM features, energy, correlation, and homogeneity were higher in the DCM group, when compared with healthy controls. In addition, entropy and contrast were lower in the DCM group. Moreover, entropy, contrast, and homogeneity had significant differences between these 2 groups. The diagnostic accuracy when using the SVM classifier with all these histogram and GLCM features was 0.85 ± 0.07.A computer-based TA and machine learning approach of T1 mapping can provide an objective tool for the diagnosis of DCM.