Segmentation Of Left Ventricle Research Articles

Abstract 4137796: Novel Deep Learning Aligned Strain Techniques in Repaired Tetralogy of Fallot

Introduction: Multicenter studies show that demographic and CMR-based volumetrics and strain predict death, ventricular tachycardia and fibrillation (DVTF) in repaired tetralogy of Fallot (rTOF). We developed a novel deep learning method to calculate radial (RS) and circumferential strain (CS) from end-diastole (ED) to other key frames: mid systole (MS), end-systole (ES), peak flow (PF) in diastole, and mid-diastole (MD) (called ED2K), as well as from each key frame to the next (called K2K strain), for each left ventricle (LV) segment. Hypothesis: We hypothesized that: H1) ED-ES strain; H2) septal strain; and H3) diastolic strain would be additionally predictive of DVTF as compared to a traditional model. Approach: 704 patients combined from the German Competence Network and INDICATOR cohorts had ED2K and K2K strain values calculated using CMR short axis stack. We first created a 4-variable “traditional” logistic regression model including age at CMR, RVEF%, LVEF% and RVESVi. We then separately added ED2K and K2K parameters to assess increased ability to discriminate DVTF, measured by the c-statistic. Results: In univariate analyses, H1: ED to ES RS and CS; H2: multiple systolic septal and non-septal variables; and H3: overall diastolic RS and CS were significantly associated with DVTF, with c-statistics between 0.65 and 0.73 (n=56, Table 1). When added to the traditional model, H1: ED to ES CS; and H2: septal and non-septal CS slightly improved model performance (Table 2). Model calibration was adequate for all models. Conclusion: Our key-frame specific strain recapitulates the CS prediction of adverse events in rTOF, and slightly improves prediction in a multiparameter model. Future work includes external validation.

Myocardial Strain Assessment for Early Duchenne Muscular Dystrophy Diagnosis in Pediatric Patients Using Cardiac MRI

Assessing myocardial strain remains challenging, particularly in the pediatric population, due to the smaller heart sizes, higher heart rates, and variability in strain parameters compared to adult populations. This study aimed to investigate the utility of myocardial strain measurements using cardiac magnetic resonance-feature tracking (CMR-FT) for early diagnosis of Duchenne muscular dystrophy (DMD) in pediatric patients. Twenty-eight DMD patients and 20 healthy controls were involved in this study. Global circumferential, longitudinal, and radial strain (GCS, GLS, and GRS) were measured for the left ventricle (LV) using CMR-FT. Segmental strain values only of the inferolateral and anterolateral LV segments in DMD patients without late gadolinium enhancement (LGE) and DMD patients with LGE were compared to the healthy controls. Strain measurements using CMR-FT in DMD patients were considerably lower than those of healthy controls, with all p-values lower than 0.001. DMD patients without LGE showed decreased inferolateral and anterolateral segmental values only relative to healthy controls. The same behavior was maintained for the LV geometry. Multivariable linear regression demonstrated that the end-systole (ES) wall thicknesses and thickening were associated with decreased GCS and GLS. CMR-FT is crucial in detecting cardiac abnormalities in patients with DMD. It represents an innovative imaging biomarker that can detect initial myocardial alterations in DMD cardiomyopathy without relying on gadolinium.

THE ROLE OF CARDIAC MAGNETIC RESONANCE IN CLINICAL MONITORING AND ASSESSMENT OF PATHOGENETIC THERAPY EFFICIENCY IN PATIENTS WITH SEVERE COURSE OF MYOCARDITIS

Introduction. Diagnosis of myocarditis often causes significant difficulties due to the heterogeneity of clinical manifestations, the absence of specific symptoms and generally recognized recommendations for diagnosis and treatment. In recent years cardiac magnetic resonance (CMR) has become not only the most common and informative diagnostic tool for myocarditis, but also a method of monitoring the effectiveness of anti-inflammatory therapy.The purpose of the study was to investigate the structural and functional state of the heart and the prevalence of the inflammatory process in patients with severe course of myocarditis associated with COVID-19 infection, who received glucocorticoid therapy.Material and methods. 80 patients with a severe course of myocarditis and reduced ejection fraction (EF) of the left ventricle (LV) were included and divided into 4 groups: 1st group - 25 patients who received glucocorticoid (GC) therapy and had a history of COVID-19 infection; the 2nd group – 25 patients who received GC therapy and did not have a history of COVID-19 infection; the 3rd group – 15 patients who did not receive GC therapy and had a history of COVID-19 infection; the 4th group – 15 patients who did not receive GC therapy and had no history of COVID-19 infection. All patients underwent echocardiography with the speckle-tracking technique and CMR with gadolinium enhancement.Results and discussion. The use of glucocorticoids in addition to optimal drug therapy for heart failure in patients with severe myocarditis who had a recent history of COVID-19 infection showed high efficacy after 6 months: the number of LV segments with inflammatory changes or delayed enhancement on CMR was, respectively by 44,2% and 32,5% less, and the value of the LV EF and the index of longitudinal global systolic deformation of the left ventricle were 15,0% and 24,3% higher in comparison with those in patients who did not receive pathogenetic therapy. In patients of the 1st group, the absence of a linear lesion on CMR at the onset of the disease was associated with recovery of LVEF to ≥50% after 6 months of treatment (r=0,66; p<0.01); a similar regularity was established also in the 2nd group (r=0,59; p<0.05). On the other hand, in patients of the 3rd and 4th groups, who did not receive immunosuppressive therapy with GC, no reliable correlations were established between the absence of a linear lesion on CMR at the onset of myocarditis and recovery of LVEF after 6 months.Conclusions. CMR in patients with myocarditis, including those associated with coronavirus disease, is the main non-invasive method for diagnosis, clinical monitoring, prognosis and determining the tactics of pathogenetic therapy. The presence of a linear lesion on CMR in patients with myocarditis is associated both with a more severe course of the disease, pronounced dilatation and a more significant violation of the LV contractile ability at the onset of the disease, and with a slower recovery of the structural and functional state of the heart despite the influence of drug therapy.

Diagnostic performance of the fragmented QRS complex on electrocardiogram for detecting myocardial scars assessed by 3.0 Tesla cardiac magnetic resonance imaging

Abstract Background Fragmented QRS complex (f-QRS) on a 12-lead electrocardiogram (EKG) with a 100 Hz low-pass filter is known to be related to ischemic myocardial scars. Cardiac magnetic resonance (CMR) imaging enhances tissue characterization capability resulting in a better myocardial scar assessment over other noninvasive imaging modalities. However, the diagnostic values of f-QRS on non-ischemic scars and f-QRS from EKG with a 40 Hz low-pass filter (routine filter in clinical practice) are unknown. Therefore, this study aims to evaluate the diagnostic performance of f-QRS (from EKG with 40 Hz and 100 Hz low-pass filters) for detecting any myocardial scars assessed by 3.0 Tesla CMR. Methods This cross-sectional study included patients who underwent a 3.0 Tesla CMR scan from May 2020 to May 2023. A 12-lead EKG with 0.15-40 and 0.15-100 Hz low-pass filters, performed on the same day of the CMR scan, was assessed for the presence of f-QRS. The ECG leads were divided into 3 categories (e.g., anteroseptal leads V1-V4; lateral leads I, aVL, V5-V6; and inferior leads II, III, aVF). The f-QRS was defined as the presence of R’ wave or notching in the nadir of the S wave in 2 contiguous leads. The primary outcome was the diagnostic performance of f-QRS from EKG in myocardial scar detection in the corresponding left ventricle (LV) segments. The secondary outcomes were to compare diagnostic performance between f-QRS from EKG with 0.15-40 and 0.15-100 Hz low-pass filters. Results The study involved 1,692 participants with a median age of 67 (IQR: 59-85) years old and 52.5% males. Myocardial scars were found in 826 (49%) participants. Male, history of CAD, and myocardial scars were significantly more frequent in the participants with f-QRS (59.4% vs 46%, 26.4% vs 20.6%, and 48.9% vs 37.3%, respectively). The sensitivity, specificity, positive predictive value, negative predictive value, and AUC of f-QRS from EKG with 0.15-100 Hz low-pass filter for detecting myocardial scars were 25.6%, 88.7%, 45.1%, 76.8%, and 0.57 for anteroseptal segments; 22.1%, 91.5%, 36.8%, 84.1%, and 0.57 for lateral segments; and 42.9%, 63.4%, 36.9, 68.9%, and 0.53 for inferior segments. The f-QRS from 0.15-100 Hz showed a higher sensitivity but lower specificity and PPV for all LV segments. NPV and AUC were not significantly different between the two filters. Conclusion This study demonstrates a high specificity and negative predictive value of f-QRS from a 12-lead EKG with 0.15-40 and 0.15-100 Hz low-pass filters in diagnosing myocardial scars when correlated to the corresponding LV segments.central illustrationbaseline charateristic

Gene-echocardiography: unmasking the covert role of fatty acid metabolism gene mutations in adult cardiomyopathy

Abstract Background Although the role of fatty acid metabolic deficiencies in cardiomyopathy is established, the precise identity of causative genes and their respective phenotypes in adult cardiomyopathy remains unclear. Methods We implemented a combination of echocardiography and whole exome sequencing in clinically diagnosed cardiomyopathy patients to uncover this relationship. This involved recording cardiac phenotypes, identifying genes associated with disrupted fatty acid metabolism, and subsequently followed up with these patients. Results Out of 802 cardiomyopathy patients, 27 exhibited mutations in genes tied to fatty acid metabolism. Specifically, 16 patients demonstrated a hypertrophic cardiomyopathy (HCM) phenotype, and 11 showed a dilated cardiomyopathy (DCM) phenotype. The implicated genes were SLC22A5 (n=7), ACADVL (n=6), ACADS (n=4), ACADM (n=3), SLC25A20 (n=3), ACADL (n=2), HADH (n=1), and AGK (n=1), with a higher prevalence in males. Among these, the SLC22A5 mutation was predominant and correlated with HCM phenotype. Notably, compound mutations were frequently observed (16/27), leading to earlier disease onset and diminished aortic sinus dimension. Further investigation showed that smaller aortic sinus dimensions resulted from abnormal left ventricular myocardial work. HCM phenotype mutation carriers showed more consistent left ventricular hypertrophy and a higher probability of right ventricular hypertrophy, while DCM phenotype mutation carriers exhibited impaired contractile function across all left ventricle segments. After a 24-month follow-up, the DCM phenotype group demonstrated higher cardiovascular risk, including two fatalities. Conclusion Our investigation highlights the significant prevalence of mutations related to abnormal fatty acid metabolism in adult cardiomyopathy patients, underscoring the utility of a gene-echocardiography approach for diagnosis.

The Study of Echocardiography of Left Ventricle Segmentation Combining Transformer and Convolutional Neural Networks.

Accurate prediction of echocardiographic parameters is essential for diagnosis and treatment of cardiac disease, especially for segmentation of the left ventricle to obtain measurements such as left ventricular ejection fraction and volume. However, manually outlining left ventricle on echocardiographic images is a time-consuming and physician experience-dependent task. Therefore, it is crucial to develop an accurate and efficient automatic segmentation tool. Therefore, we aimed to explore a model to perform echocardiography of left ventricle segmentation by combining transformer and convolutional neural networks (CNN).ResNet-50 was used in CNN branch. The encoder-decoder architecture was used for transformer branch, which was fused to the corresponding feature maps of the CNN branches. Fusion module was used to effectively combine feature information from the CNN and transformer. Bridge attention used to increase sensitivity and prediction accuracy of model. The entire network was trained end-to-end using the binary cross-entropy with logits loss L.In this work, we propose an automatic left ventricular (LV) segmentation model based on Transformer and CNN that efficiently captures global dependencies and spatial details and create a fusion module using CBAM that fuses Transformer and CNN features. In addition, attention is also computed using multi-level fusion features to obtain the final attention segmentation map. The model was trained and evaluated on a large cardiac image dataset, EchoNet-Dynamic, with test dice coefficient of 92.4%.The results show that our model can better segment left ventricle. We also tested our model on clinical patient ultrasound images, and visualization results proved effectiveness of the model.

SimLVSeg: Simplifying Left Ventricular Segmentation in 2-D+Time Echocardiograms With Self- and Weakly Supervised Learning

ObjectiveAchieving reliable automatic left ventricle (LV) segmentation from echocardiograms is challenging due to the inherent sparsity of annotations in the dataset, as clinicians typically only annotate two specific frames for diagnostic purposes. Here we aim to address this challenge by introducing simplified LV segmentation (SimLVSeg), a novel paradigm that enables video-based networks for consistent LV segmentation from sparsely annotated echocardiogram videos. MethodsSimLVSeg consists of two training stages: (i) self-supervised pre-training with temporal masking, which involves pre-training a video segmentation network by capturing the cyclic patterns of echocardiograms from largely unannotated echocardiogram frames, and (ii) weakly supervised learning tailored for LV segmentation from sparse annotations. ResultsWe extensively evaluated SimLVSeg using EchoNet-Dynamic, the largest echocardiography dataset. SimLVSeg outperformed state-of-the-art solutions by achieving a 93.32% (95% confidence interval: 93.21–93.43%) dice score while being more efficient. We further conducted an out-of-distribution test to showcase SimLVSeg's generalizability on distribution shifts (CAM US dataset). ConclusionOur findings show that SimLVSeg exhibits excellent performance on LV segmentation with a relatively cheaper computational cost. This suggests that adopting video-based networks for LV segmentation is a promising research direction to achieve reliable LV segmentation. Our code is publicly available at https://github.com/BioMedIA-MBZUAI/SimLVSeg.

MultiJSQ: Direct joint segmentation and quantification of left ventricle with deep multitask‐derived regression network

MultiJSQ: Direct joint segmentation and quantification of left ventricle with deep multitask‐derived regression network

Analysis of myocardial T1, T2, and T2* values by age, sex, and cardiac segments in normal population: a prospective study.

This study examines myocardial T1, T2, and T2* values in a sizable cohort of healthy volunteers, analyzing variations by age, sex, and cardiac segments. It offers a novel approach to defining normal parametric mapping boundaries and represents the first comprehensive study of its kind in Turkey. Our prospective study was conducted between August 2021 and August 2022. Healthy volunteers aged 20-80 were grouped, with at least eight females and eight males per decade. Cardiac MRI examination measured T1 and T2 times in 16 left ventricle segments using parametric mapping techniques on a 1.5 Tesla MRI device. T2* mapping was also performed on the mid-section interventricular septum. The data analysis considered the impact of age, sex, and segments. One hundred eighteen cases were included in the study. Female volunteers observed significantly higher T1, T2, and T2* values than male volunteers. For the T2* and T1 times, significantly lower values were detected in women over 50 than those under 50. It was observed that the Midventricular approach (middle section) gave closer results than the Midventricular Septal approach (septal region of middle section) in predicting Global times. We present the normal reference ranges for cardiac T1, T2, and T2* times in a large cohort of healthy volunteers with homogeneous sex and age distribution. Sex was the most influential factor in our study. Therefore, we suggest using separate reference values for males, and females above and below 50 years old, instead of the standard reference intervals that do not account for specified sex in current guidelines.

Basal inferoseptal segment is highly susceptible to deformation in the clinical spectrum of transthyretin-derived amyloid cardiomyopathy.

While the prevalence of transthyretin-derived amyloid cardiomyopathy (ATTR-CM) is on the rise, detailed understanding of its morphological and functional characteristics within the left ventricle (LV) across heart failure (HF) remains limited. Utilizing two-dimensional (2D) speckle-tracking echocardiography, we assessed longitudinal strain (LS) in 63 histology-confirmed ATTR-CM patients. Additionally, cardiac magnetic resonance (CMR) images measured native T1 and extracellular volume (ECV), compared with LS across 18 LV segments. Patients were categorized into three groups based on HF status: Group 1 (no HF symptoms), Group 2 (HF with preserved LV ejection fraction), and Group 3 (HF with reduced LV ejection fraction). LS analysis unveiled susceptibility to deformation in the basal inferoseptal segment, persisting even in asymptomatic cases. CMR demonstrated increasing native T1 deviation, particularly evident in segments distant from the inferoseptal region. Contrastingly, maximal ECV was consistently observed in the basal and mid-ventricular inferior-septum, even in asymptomatic individuals. Segmental LS decline correlated with ECV expansion but not with native T1 values. Our findings suggest that the inferoseptal segment is highly susceptible to amyloid infiltration, and 2D speckle-tracking echocardiography and CMR may serve as a valuable tool for its early detection.

Echocardiogram revealing left ventricle ejection fraction of 20% with severe hypokinesis of all left ventricle segments except the basal segments along with a left ventricular filling pattern consistent with abnormal relaxation.

Echocardiogram revealing left ventricle ejection fraction of 20% with severe hypokinesis of all left ventricle segments except the basal segments along with a left ventricular filling pattern consistent with abnormal relaxation.

Визначення предикторів стійких порушень серцевого ритму у військовослужбовців із тяжким перебігом міокардиту

The aim – to study heart rhythm and conduction disturbances in different localization and distribution of myocardial lesions in combatants with severe myocarditis based on the results of a 6-month follow-up.Materials and methods. 46 male military personnel with a severe course of acute myocarditis (AM) with a reduced ejection fraction (EF) of the left ventricle (LV) (≤ 40 %) with an average age of (35,1±2,4) years were examined. Examinations were carried out in the 1st month after the onset of symptoms of myocarditis and after 6 months of observation. The diagnosis of myocarditis and the severe course of the disease were established on the basis of the Recommendations for the diagnosis and treatment of myocarditis of the All-Ukrainian Association of Cardiologists of Ukraine. All patients underwent for 24-hour ECG monitoring with analysis of the frequency and spectrum of rhythm and conduction disturbances and cardiac magnetic resonance (CMR) imaging with contrast analysis of the topography of the lesion and counting the number of LV segments affected by inflammatory changes and LV segments with the presence of late gadolinium enhancement (LGE).Results and discussion. When comparing the results of heart MRI with the data of daily ECG monitoring, a clear association of the presence of frequent ventricular extrasystoles (VE) and paroxysms of non-sustained ventricular tachycardia (NSVT) with the localization of LGE in the interventricular septum (IS) was established – among patients with LGE lesions at the onset of AM more than in a third (37.0 %) had frequent VE, and NSVT paroxysms, which increase the risk of developing life-threatening ventricular arrhythmias, were detected in 25,9 % of cases. After 6 months of observation in the presence of LGE in the IS, the frequency of detection of frequent VE and NSVT paroxysms was also significantly higher compared to other localization of the lesion and amounted to 20,0 and 13,3 %, respectively. With the help of correlation analysis, an associative relationship was revealed between the presence of LGE in the IS and the presence of frequent VE and NSVT paroxysms in the debut of myocarditis – r=0.73 (р<0.01) and r=0.66 (р<0,01) respectively, and also after 6 months of observation – r=0.65 (р<0.01) and r=0.59 (р<0.05), respectively. According to the results of the multivariate regression analysis, predictors of frequent VE persistence after 6 months were: LVEF ≤30 %; LV end-diastolic volume index ≥105 ml/m2; presence of inflammatory changes in ≥5.0 LV segments; presence of LGE in ≥4.0 LV segments and its presence in the IS, determined in the 1st month from the onset of the disease. The predictors NSVT paroxysms persistence after 6 months were the same factors with the exception of LV EF, and, according to the value of the β coefficient (β=1.302; p<0.001), the most significant contribution was the presence of LGE in the IS.Conclusions. In combatants with severe myocarditis, the presence of late gadolinium enhancement in the interventricular septum is an additional risk factor for the persistence of frequent ventricular extrasystoles and paroxysms of non-sustained ventricular tachycardia during 6 months, while the presence of late gadolinium enhancement in the posterior and lateral walls of the left ventricle has no reliable relationship with the presence of rhythm and conduction disorders. On the basis of multivariate regression analysis, predictors of frequent ventricular extrasystoles and paroxysms of non-sustained ventricular tachycardia persistence were established in combatants with myocarditis.

EFNet: A multitask deep learning network for simultaneous quantification of left ventricle structure and function

Purpose:The purpose of this study is to develop an automated method using deep learning for the reliable and precise quantification of left ventricle structure and function from echocardiogram videos, eliminating the need to identify end-systolic and end-diastolic frames. This addresses the variability and potential inaccuracies associated with manual quantification, aiming to improve the diagnosis and management of cardiovascular conditions. Methods:A single, fully automated multitask network, the EchoFused Network (EFNet) is introduced that simultaneously addresses both left ventricle segmentation and ejection fraction estimation tasks through cross-module fusion. Our proposed approach utilizes semi-supervised learning to estimate the ejection fraction from the entire cardiac cycle, yielding more dependable estimations and obviating the need to identify specific frames. To facilitate joint optimization, the losses from task-specific modules are combined using a normalization technique, ensuring commensurability on a comparable scale. Results:The assessment of the proposed model on a publicly available dataset, EchoNet-Dynamic, shows significant performance improvement, achieving an MAE of 4.35% for ejection fraction estimation and DSC values of 0.9309 (end-diastolic) and 0.9135 (end-systolic) for left ventricle segmentation. Conclusions:The study demonstrates the efficacy of EFNet, a multitask deep learning network, in simultaneously quantifying left ventricle structure and function through cross-module fusion on echocardiogram data.

Deep Learning Based Automatic Left Ventricle Segmentation from the Transgastric Short-Axis View on Transesophageal Echocardiography: A Feasibility Study.

Segmenting the left ventricle from the transgastric short-axis views (TSVs) on transesophageal echocardiography (TEE) is the cornerstone for cardiovascular assessment during perioperative management. Even for seasoned professionals, the procedure remains time-consuming and experience-dependent. The current study aims to evaluate the feasibility of deep learning for automatic segmentation by assessing the validity of different U-Net algorithms. A large dataset containing 1388 TSV acquisitions was retrospectively collected from 451 patients (32% women, average age 53.42 years) who underwent perioperative TEE between July 2015 and October 2023. With image preprocessing and data augmentation, 3336 images were included in the training set, 138 images in the validation set, and 138 images in the test set. Four deep neural networks (U-Net, Attention U-Net, UNet++, and UNeXt) were employed for left ventricle segmentation and compared in terms of the Jaccard similarity coefficient (JSC) and Dice similarity coefficient (DSC) on the test set, as well as the number of network parameters, training time, and inference time. The Attention U-Net and U-Net++ models performed better in terms of JSC (the highest average JSC: 86.02%) and DSC (the highest average DSC: 92.00%), the UNeXt model had the smallest network parameters (1.47 million), and the U-Net model had the least training time (6428.65 s) and inference time for a single image (101.75 ms). The Attention U-Net model outperformed the other three models in challenging cases, including the impaired boundary of left ventricle and the artifact of the papillary muscle. This pioneering exploration demonstrated the feasibility of deep learning for the segmentation of the left ventricle from TSV on TEE, which will facilitate an accelerated and objective alternative of cardiovascular assessment for perioperative management.

A Lightweight Bilateral Left Ventricle Segmentation Method for Echocardiography

A Lightweight Bilateral Left Ventricle Segmentation Method for Echocardiography

Optimized target delineation procedure for the radiosurgery treatment of ventricular tachycardia: observer-independent accuracy.

Part of the current stereotactic arrythmia radioablation (STAR) workflow is transfer of findings from the electroanatomic mapping (EAM) to computed tomography (CT). Here, we analyzed inter- and intraobserver variation in a modified EAM-CT registration using automatic registration algorithms designed to yield higher robustness. This work is based on data of 10 patients who had previously undergone STAR. Two observers participated in this study: (1) an electrophysiologist technician (cardiology) with substatial experience in EAM-CT merge, and (2) a clinical engineer (radiotherapy) with minimum experience with EAM-CT merge. EAM-CT merge consists of 3 main steps: segmentation of left ventricle from CT (CT LV), registration of the CT LV and EAM, clinical target volume (CTV) delineation from EAM specific points. Mean Hausdorff distance (MHD), Dice Similarity Coefficient (DSC) and absolute difference in Center of Gravity (CoG) were used to assess intra/interobserver variability. Intraobserver variability: The mean DSC and MHD for 3 CT LVs altogether was 0.92 ± 0.01 and 1.49 ± 0.23 mm. The mean DSC and MHD for 3 CTVs altogether was 0,82 ± 0,06 and 0,71 ± 0,22 mm. Interobserver variability: Segmented CT LVs showed great similarity (mean DSC of 0,91 ± 0,01, MHD of 1,86 ± 0,47 mm). The mean DSC comparing CTVs from both observers was 0,81 ± 0,11 and MHD was 0,87 ± 0,45 mm. The high interobserver similarity of segmented LVs and delineated CTVs confirmed the robustness of the proposed method. Even an inexperienced user can perform a precise EAM-CT merge following workflow instructions.

Fine grained automatic left ventricle segmentation via ROI based Tri-Convolutional neural networks.

The left ventricle segmentation (LVS) is crucial to the assessment of cardiac function. Globally, cardiovascular disease accounts for the majority of deaths, posing a significant health threat. In recent years, LVS has gained important attention due to its ability to measure vital parameters such as myocardial mass, end-diastolic volume, and ejection fraction. Medical professionals realize that manually segmenting data to evaluate these processes takes a lot of time, effort when diagnosing heart diseases. Yet, manually segmenting these images is labour-intensive and may reduce diagnostic accuracy. This paper, propose a combination of different deep neural networks for semantic segmentation of the left ventricle based on Tri-Convolutional Networks (Tri-ConvNets) to obtain highly accurate segmentation. CMRI images are initially pre-processed to remove noise artefacts and enhance image quality, then ROI-based extraction is done in three stages to accurately identify the LV. The extracted features are given as input to three different deep learning structures for segmenting the LV in an efficient way. The contour edges are processed in the standard ConvNet, the contour points are processed using Fully ConvNet and finally the noise free images are converted into patches to perform pixel-wise operations in ConvNets. The proposed Tri-ConvNets model achieves the Jaccard indices of 0.9491 ± 0.0188 for the sunny brook dataset and 0.9497 ± 0.0237 for the York dataset, and the dice index of 0.9419 ± 0.0178 for the ACDC dataset and 0.9414 ± 0.0247 for LVSC dataset respectively. The experimental results also reveal that the proposed Tri-ConvNets model is faster and requires minimal resources compared to state-of-the-art models.

Automated Left Ventricle Segmentation in Echocardiography Using YOLO: A Deep Learning Approach for Enhanced Cardiac Function Assessment

Accurate segmentation of the left ventricle (LV) using echocardiogram (Echo) images is essential for cardiovascular analysis. Conventional techniques are labor-intensive and exhibit inter-observer variability. Deep learning has emerged as a powerful tool for automated medical image segmentation, offering advantages in speed and potentially superior accuracy. This study explores the efficacy of employing a YOLO (You Only Look Once) segmentation model for automated LV segmentation in Echo images. YOLO, a cutting-edge object detection model, achieves exceptional speed–accuracy balance through its well-designed architecture. It utilizes efficient dilated convolutional layers and bottleneck blocks for feature extraction while incorporating innovations like path aggregation and spatial attention mechanisms. These attributes make YOLO a compelling candidate for adaptation to LV segmentation in Echo images. We posit that by fine-tuning a pre-trained YOLO-based model on a well-annotated Echo image dataset, we can leverage the model’s strengths in real-time processing and precise object localization to achieve robust LV segmentation. The proposed approach entails fine-tuning a pre-trained YOLO model on a rigorously labeled Echo image dataset. Model performance has been evaluated using established metrics such as mean Average Precision (mAP) at an Intersection over Union (IoU) threshold of 50% (mAP50) with 98.31% and across a range of IoU thresholds from 50% to 95% (mAP50:95) with 75.27%. Successful implementation of YOLO for LV segmentation has the potential to significantly expedite and standardize Echo image analysis. This advancement could translate to improved clinical decision-making and enhanced patient care.

A Multi‐Fusion Residual Attention U‐Net Using Temporal Information for Segmentation of Left Ventricular Structures in 2D Echocardiographic Videos

ABSTRACTThe interpretation of cardiac function using echocardiography requires a high level of diagnostic proficiency and years of experience. This study proposes a multi‐fusion residual attention U‐Net, MURAU‐Net, to construct automatic segmentation for evaluating cardiac function from echocardiographic video. MURAU‐Net has two benefits: (1) Multi‐fusion network to strengthen the links between spatial features. (2) Inter‐frame links can be established to augment the temporal coherence of sequential image data, thereby enhancing its continuity. To evaluate the effectiveness of the proposed method, we performed nine‐fold cross‐validation using CAMUS dataset. Among state‐of‐the‐art methods, MURAU‐Net achieves highly competitive score, for example, Dice similarity of 0.952 (ED phase) and 0.931 (ES phase) in , 0.966 (ED phase) and 0.957 (ES phase) in , and 0.901 (ED phase) and 0.917 (ES phase) in , respectively. It also achieved the Dice similarity of 0.9313 in the EchoNet‐Dynamic dataset for the overall left ventricle segmentation. In addition, we show MURAU‐Net can accurately segment multiclass cardiac ultrasound videos and output the animation of segmentation results using the original two‐chamber cardiac ultrasound dataset MUCO.

Left ventricular deformation in the presence of left ventricular 'rigid body rotation' in healthy adults-three-dimensional speckle-tracking echocardiographic insights from the MAGYAR-Healthy Study.

During the heart cycle, the left ventricle (LV) not only shows a contraction-relaxation pattern, but LV has a rotational mechanics, as well. It is a known fact that certain pathologies may be associated with an absence of LV twist, when LV basal and apical regions rotate in the same clockwise (cw) or counterclockwise (ccw) direction called LV 'rigid body rotation' (LV-RBR), but it can also occur in healthy subjects. The present cohort study aimed to examine LV strains in healthy subjects with LV-RBR versus with normally directed LV rotational mechanics by three-dimensional speckle-tracking echocardiography (3DSTE). The study consisted of 181 healthy individuals, from which 171 cases had normally directed LV rotational mechanics (mean age: 32.5±12.3 years, 79 males) and 10 healthy subject showed LV-RBR (mean age: 35.4±11.3 years, 3 males). Complete two-dimensional (2D) Doppler echocardiography and 3DSTE were performed in all healthy individuals. None of routine 2D Doppler echocardiographic parameters showed differences between the groups examined. There were no subjects with ≥ grade 1 regurgitation on any valves or with significant stenosis on any valves. 3DSTE-derived LV volumes, global and mean segmental strains did not differ between the groups examined. Apical anterior and lateral segments showed reduced segmental LV circumferential strain (CS) (-18.9%±8.5% vs. -26.7%±10.7%, P=0.02; -27.3%±12.6% vs. -34.8%±13.2%, P=0.08, respectively) and LV area strain (AS) (-26.8%±9.8% vs -36.8%±12.0%, P=0.01; -35.7%±13.2% vs. -45.0%±14.6%) in healthy subjects having LV-RBR as compared to cases with normally directed LV rotational mechanics. These abnormalities were present only in subjects having cwLV-RBR. Although global LV deformation is normal in the presence of LV-RBR in healthy adults, reduction of apical anterior and lateral LV-CS (and LV-AS) are present in cases with cwLV-RBR only suggesting segmental deformation abnormalities.