Home / Advanced Search

  • Title/Keywords

  • Author/Affliations

  • Journal

  • Article Type

  • Start Year

  • End Year

Update SearchingClear
  • Articles
  • Online
Search Results (13)
  • Open Access


    An Interpretable CNN for the Segmentation of the Left Ventricle in Cardiac MRI by Real-Time Visualization

    Jun Liu1, Geng Yuan2, Changdi Yang2, Houbing Song3, Liang Luo4,*

    CMES-Computer Modeling in Engineering & Sciences, Vol.135, No.2, pp. 1571-1587, 2023, DOI:10.32604/cmes.2022.023195

    Abstract The interpretability of deep learning models has emerged as a compelling area in artificial intelligence research. The safety criteria for medical imaging are highly stringent, and models are required for an explanation. However, existing convolutional neural network solutions for left ventricular segmentation are viewed in terms of inputs and outputs. Thus, the interpretability of CNNs has come into the spotlight. Since medical imaging data are limited, many methods to fine-tune medical imaging models that are popular in transfer models have been built using massive public ImageNet datasets by the transfer learning method. Unfortunately, this generates many unreliable parameters and makes… More >

  • Open Access


    Detection of Left Ventricular Cavity from Cardiac MRI Images Using Faster R-CNN

    Zakarya Farea Shaaf1,*, Muhammad Mahadi Abdul Jamil1, Radzi Ambar1, Ahmed Abdu Alattab2,3, Anwar Ali Yahya3,4, Yousef Asiri4

    CMC-Computers, Materials & Continua, Vol.74, No.1, pp. 1819-1835, 2023, DOI:10.32604/cmc.2023.031900

    Abstract The automatic localization of the left ventricle (LV) in short-axis magnetic resonance (MR) images is a required step to process cardiac images using convolutional neural networks for the extraction of a region of interest (ROI). The precise extraction of the LV’s ROI from cardiac MRI images is crucial for detecting heart disorders via cardiac segmentation or registration. Nevertheless, this task appears to be intricate due to the diversities in the size and shape of the LV and the scattering of surrounding tissues across different slices. Thus, this study proposed a region-based convolutional network (Faster R-CNN) for the LV localization from… More >

  • Open Access


    Concordant Atrioventricular Connection to L-Looped Ventricles with the Left Ventricle on Top of the Right Ventricle in Situs Solitus: A Case Report with 3D Modelling and Printing

    Mi Kyoung Song1, Gi Beom Kim1, Woong Han Kim2, Whal Lee3, Eun-Jung Bae1,*

    Congenital Heart Disease, Vol.17, No.4, pp. 393-398, 2022, DOI:10.32604/chd.2022.019603

    Abstract We report the case of a rare complex cardiac anomaly involving situs solitus, concordant atrioventricular connection with left-hand ventricular topology, and L-looped ventricles. The ventricles had a superior-inferior relationship with an inferiorly located right ventricle, which had a double outlet with far posteriorly located great arteries. The left atrium was elongated, with juxta-positioned atrial appendages on the right side. The 3D-printed model using a computed tomography scan taken on the fourth day of birth demonstrated the anatomy clearly and helped us decide on the surgical management. More > Graphic Abstract

    Concordant Atrioventricular Connection to L-Looped Ventricles with the Left Ventricle on Top of the Right Ventricle in Situs Solitus: A Case Report with 3D Modelling and Printing

  • Open Access


    Segmentation of the Left Ventricle in Cardiac MRI Using Random Walk Techniques

    Osama S. Faragallah1,*, Ghada Abdel-Aziz2, Hala S. El-sayed3, Gamal G. N. Geweid4,5

    Intelligent Automation & Soft Computing, Vol.30, No.2, pp. 575-588, 2021, DOI:10.32604/iasc.2021.019023

    Abstract As a regular tool for assessing and diagnosing cardiovascular disease (CVD), medical professionals and health care centers, are highly dependent on cardiac imaging. The purpose of dividing the cardiac images is to paint the inner and outer walls of the heart to divide all or part of the limb’s boundaries. In order to enhance cardiologist in the process of cardiac segmentation, new and accurate methods are needed to divide the selected object, which is the left ventricle (LV). Segmentation techniques aim to provide a fast segmentation process and improve the reliability of the process. In this paper, a comparative study… More >

  • Open Access


    D-Transposition of the Great Arteries after Arterial Switch Operation: Usefulness of 3D-Echocardiography for Left Ventricle Function Evaluation

    Ylenia Bartolacelli*, Giulia Bragantini

    Congenital Heart Disease, Vol.15, No.2, pp. 59-68, 2020, DOI:10.32604/CHD.2020.011448

    Abstract Objective: The objective of this study was to assess left ventricle (LV) function and remodeling by three-dimensional echocardiography (3DE) in patients who underwent arterial switch procedure (ASO) for transposition of great arteries (TGA) in long-term follow-up. Methods and Results: We studied 54 asymptomatic patients (39 male) who have undergone single-stage ASO for TGA, aged 13.7 ± 4.7 years, with a normal LV ejection fraction (EF), compared to healthy peers. We evaluated LV volume and function in asymptomatic patients with normal ejection fraction by 3DE. All patients had normal EF, measured by modified Simpson’s method (mean 60.9 ± 3.5%) and by… More >

  • Open Access


    Time course of the changes in right and left ventricle function and associated factors after transcatheter closure of atrial septal defects

    Byung W. Yoo1, Jung O. Kim2, Lucy Y. Eun2, Jae Y. Choi2, Dong S. Kim3

    Congenital Heart Disease, Vol.13, No.1, pp. 131-139, 2018, DOI:10.1111/chd.12541

    Abstract Objective: The purpose of this study was to evaluate the changes in right ventricle (RV) and left ventricle (LV) function after transcatheter atrial septal defect (ASD) closure and to assess the influence of the age and the amount of shunt.
    Design: Retrospective study
    Patients: Fifty-three adult patients who underwent transcatheter closure were enrolled, then divided into subgroups according to the age (< 40 years vs ≥ 40 years), and the amount of shunt flow (QpQs < 2.5 vs QpQs ≥ 2.5).
    Outcome Measures: Two-dimensional tissue Doppler imaging was performed in a four-chamber view at the basal ventricular septum (VS) and… More >

  • Open Access


    Fully-Coupled Fluid-Structure Interaction (FSI) Simulations of Heart Valve-Left Ventricle Dynamics

    Wei Sun1,*

    Molecular & Cellular Biomechanics, Vol.16, Suppl.2, pp. 64-64, 2019, DOI:10.32604/mcb.2019.08533

    Abstract Fluid–structure interaction (FSI) is a common phenomenon in biological systems. FSI problems of practical interest, such as fish/mammalian swimming, insect/bird flight, and human cardiac blood flow and respiration often involve multiple 3D immersed bodies with complex geometries undergoing very large structural displacements, and inducing very complex flow phenomena. Simulation of heart valve FSI is a technically challenging problem due to the large deformation of the valve leaflets through the cardiac fluid domain in the atrium and ventricular chambers.
    Recently, we developed a FSI computational framework [1] for modeling patient-specific left heart (LH) dynamics using smoothed particle hydrodynamics (SPH) for… More >

  • Open Access


    Comparisons of Patient-specific Active and Passive Models for Left Ventricle in Hypertrophic Obstructive Cardiomyopathy

    Xueying Huang1,*, Long Deng2, Chun Yang3, Mary Lesperance4, Dalin Tang5

    Molecular & Cellular Biomechanics, Vol.16, Suppl.2, pp. 58-58, 2019, DOI:10.32604/mcb.2019.06969

    Abstract Hypertrophic cardiomyopathy (HCM) occurs in about 1 of every 500 adults in the general population. It has been reported that left ventricular outflow tract obstruction (LVOTO) is observed in 70% patients with HCM. Systolic anterior motion (SAM) of the mitral valve (MV) is the dominant cause of dynamic outflow tract obstruction in most patients with hypertrophic obstructive cardiomyopathy (HOCM). Currently, the hemodynamic mechanisms of SAM remain unclear. In this study, we developed 12 active and corresponding passive models based on 6 patients’ pre- and post-operative ECG-gated cardiac CT images of patients’ LV at the pre-SAM time point (5% RR interval).… More >

  • Open Access


    Patient-Specific Echo-Based Fluid-Structure Interaction Modeling Study of Blood Flow in the Left Ventricle with Infarction and Hypertension

    Longling Fan1,*, Jing Yao 2, *, Chun Yang3, Di Xu2, Dalin Tang1, 4, §

    CMES-Computer Modeling in Engineering & Sciences, Vol.114, No.2, pp. 221-237, 2018, DOI:10.3970/cmes.2018.114.221

    Abstract Understanding cardiac blood flow behaviors is of importance for cardiovascular research and clinical assessment of ventricle functions. Patient-specific Echo-based left ventricle (LV) fluid-structure interaction (FSI) models were introduced to perform ventricle mechanical analysis, investigate flow behaviors, and evaluate the impact of myocardial infarction (MI) and hypertension on blood flow in the LV. Echo image data were acquired from 3 patients with consent obtained: one healthy volunteer (P1), one hypertension patient (P2), and one patient who had an inferior and posterior myocardial infarction (P3). The nonlinear Mooney-Rivlin model was used for ventricle tissue with material parameter values chosen to match echo-measure… More >

  • Open Access


    Modeling Active Contraction and Relaxation of Left Ventricle Using Different Zero-load Diastole and Systole Geometries for Better Material Parameter Estimation and Stress/Strain Calculations

    Longling Fan1,§, Jing Yao2,§, Chun Yang3, Di Xu2, Dalin Tang1,4*

    Molecular & Cellular Biomechanics, Vol.13, No.1, pp. 33-55, 2016, DOI:10.3970/mcb.2016.013.044

    Abstract Modeling ventricle active contraction based on in vivo data is extremely challenging because of complex ventricle geometry, dynamic heart motion and active contraction where the reference geometry (zero-stress geometry) changes constantly. A new modeling approach using different diastole and systole zero-load geometries was introduced to handle the changing zero-load geometries for more accurate stress/strain calculations. Echo image data were acquired from 5 patients with infarction (Infarct Group) and 10 without (Non-Infarcted Group). Echo-based computational two-layer left ventricle models using one zero-load geometry (1G) and two zero-load geometries (2G) were constructed. Material parameter values in Mooney-Rivlin models were adjusted to match… More >

Displaying 1-10 on page 1 of 13. Per Page