4.An image classification method for arrhythmias based on Gramian angular summation field and improved Inception-ResNet-v2.
Xiangkui WAN ; Jing LUO ; Yang LIU ; Yunfan CHEN ; Xingwei PENG ; Xi WANG
Journal of Biomedical Engineering 2023;40(3):465-473
Arrhythmia is a significant cardiovascular disease that poses a threat to human health, and its primary diagnosis relies on electrocardiogram (ECG). Implementing computer technology to achieve automatic classification of arrhythmia can effectively avoid human error, improve diagnostic efficiency, and reduce costs. However, most automatic arrhythmia classification algorithms focus on one-dimensional temporal signals, which lack robustness. Therefore, this study proposed an arrhythmia image classification method based on Gramian angular summation field (GASF) and an improved Inception-ResNet-v2 network. Firstly, the data was preprocessed using variational mode decomposition, and data augmentation was performed using a deep convolutional generative adversarial network. Then, GASF was used to transform one-dimensional ECG signals into two-dimensional images, and an improved Inception-ResNet-v2 network was utilized to implement the five arrhythmia classifications recommended by the AAMI (N, V, S, F, and Q). The experimental results on the MIT-BIH Arrhythmia Database showed that the proposed method achieved an overall classification accuracy of 99.52% and 95.48% under the intra-patient and inter-patient paradigms, respectively. The arrhythmia classification performance of the improved Inception-ResNet-v2 network in this study outperforms other methods, providing a new approach for deep learning-based automatic arrhythmia classification.
Humans
;
Arrhythmias, Cardiac/diagnostic imaging*
;
Cardiovascular Diseases
;
Algorithms
;
Databases, Factual
;
Electrocardiography
5.Computational Fluid Dynamics in Cardiovascular Disease.
Korean Circulation Journal 2011;41(8):423-430
Computational fluid dynamics (CFD) is a mechanical engineering field for analyzing fluid flow, heat transfer, and associated phenomena, using computer-based simulation. CFD is a widely adopted methodology for solving complex problems in many modern engineering fields. The merit of CFD is developing new and improved devices and system designs, and optimization is conducted on existing equipment through computational simulations, resulting in enhanced efficiency and lower operating costs. However, in the biomedical field, CFD is still emerging. The main reason why CFD in the biomedical field has lagged behind is the tremendous complexity of human body fluid behavior. Recently, CFD biomedical research is more accessible, because high performance hardware and software are easily available with advances in computer science. All CFD processes contain three main components to provide useful information, such as pre-processing, solving mathematical equations, and post-processing. Initial accurate geometric modeling and boundary conditions are essential to achieve adequate results. Medical imaging, such as ultrasound imaging, computed tomography, and magnetic resonance imaging can be used for modeling, and Doppler ultrasound, pressure wire, and non-invasive pressure measurements are used for flow velocity and pressure as a boundary condition. Many simulations and clinical results have been used to study congenital heart disease, heart failure, ventricle function, aortic disease, and carotid and intra-cranial cerebrovascular diseases. With decreasing hardware costs and rapid computing times, researchers and medical scientists may increasingly use this reliable CFD tool to deliver accurate results. A realistic, multidisciplinary approach is essential to accomplish these tasks. Indefinite collaborations between mechanical engineers and clinical and medical scientists are essential. CFD may be an important methodology to understand the pathophysiology of the development and progression of disease and for establishing and creating treatment modalities in the cardiovascular field.
Aortic Diseases
;
Cardiovascular Diseases
;
Cooperative Behavior
;
Diagnostic Imaging
;
Heart Diseases
;
Heart Failure
;
Hot Temperature
;
Human Body
;
Hydrodynamics
;
Magnetic Resonance Imaging
;
Viscosity
6.Evaluation of the relationship between cardiac calcification and cardiovascular disease using the echocardiographic calcium score in patients undergoing peritoneal dialysis: a cross-sectional study.
Ho-Kwan SIN ; Ping-Nam WONG ; Kin-Yee LO ; Man-Wai LO ; Shuk-Fan CHAN ; Kwok-Chi LO ; Yuk-Yi WONG ; Lo-Yi HO ; Wing-Tung KWOK ; Kai-Chun CHAN ; Andrew Kui-Man WONG ; Siu-Ka MAK
Singapore medical journal 2023;64(6):379-384
INTRODUCTION:
An echocardiographic calcium score (ECS) predicts cardiovascular disease (CVD) in the general population. Its utility in peritoneal dialysis (PD) patients is unknown.
METHODS:
This cross-sectional study assessed 125 patients on PD. The ECS (range 0-8) was compared between subjects with CVD and those without.
RESULTS:
Among the subjects, 54 had CVD and 71 did not. Subjects with CVD were older (69 years vs. 56 years, P < 0.001) and had a higher prevalence of diabetes mellitus (DM) (81.5% vs. 45.1%, P < 0.001). They had lower diastolic blood pressure (72 mmHg vs. 81 mmHg, P < 0.001), lower phosphate (1.6 mmol/L vs. 1.9 mmol/L, P = 0.002), albumin (30 g/L vs. 32 g/L, P = 0.001), parathyroid hormone (34.4 pmol/L vs. 55.8 pmol/L, P = 0.002), total cholesterol (4.5 vs. 4.9, P = 0.047), LDL cholesterol (2.4 mmol/L vs. 2.8 mmol/L, P = 0.019) and HDL cholesterol (0.8 mmol/L vs. 1.1 mmol/L, P = 0.002). The ECS was found to be higher in subjects with CVD than in those without (2 vs. 1, P = 0.001). On multivariate analysis, only DM and age were independently associated with CVD.
CONCLUSION
The ECS was significantly higher in PD patients with CVD than in those without, reflecting a higher vascular calcification burden in the former. It is a potentially useful tool to quantify vascular calcification in PD patients.
Humans
;
Cardiovascular Diseases/diagnostic imaging*
;
Cross-Sectional Studies
;
Calcium
;
Peritoneal Dialysis/adverse effects*
;
Vascular Calcification/epidemiology*
;
Echocardiography
7.Reference values for carotid artery intima-media thickness among community adult dwellers in Shenzhen City.
Yu Xin XIE ; De Liang LYU ; Ke PENG ; Hong Wei XIE ; Yong JIANG ; Xin Bo ZHONG ; Xi Lin WEN ; Zi Wei FU ; Gui Li ZHOU ; Zhi Guang ZHAO ; Yi Chong LI
Chinese Journal of Preventive Medicine 2023;57(7):1011-1017
Objective: To establish reference values for carotid intima-media thickness (CIMT) of adult dwellers in Shenzhen City. Methods: The study was conducted based on the Shenzhen heart failure epidemiological survey from 2021 to 2022. In this survey, residents aged 18 years and above in Shenzhen were selected by using a multi-stage stratified random sampling method. General information, cardiovascular disease (CVD) related behavior and carotid ultrasound examination and etc. were collected from the participants. People with CVD factors, a history of atherosclerotic cardiovascular disease, carotid plaque or having no carotid ultrasound examination results were excluded. The parameter regression model based on fractional polynomial was used to establish the reference values of CIMT by age and sex. Results: A total of 2 163 healthy individuals were enrolled in the final analysis, including 576 males (26.6%) and 1 587 females (73.4%). The fractional polynomial regression of the CIMT mean and standard deviation was obtained. For men, the regression was meanCIMT=0.324 7+0.006 9×age and SDCIMT=0.076 9+0.001 2×age. For women, the regression was meanCIMT=0.354 9+0.005 4×age and SDCIMT=0.041 6+0.002 0×age. Conclusion: The age and sex reference values for CIMT of adult people in Shenzhen established in this study could provide the latest reference standards for early screening of subclinical CVD.
Male
;
Humans
;
Adult
;
Female
;
Carotid Intima-Media Thickness
;
Cardiovascular Diseases
;
Reference Values
;
Carotid Arteries/diagnostic imaging*
;
Ultrasonography, Carotid Arteries
;
Risk Factors
;
Carotid Artery Diseases
8.Study of the relationship between cardiovascular risk factors and severity of coronary artery disease in patients underwent coronary angiography.
Yong-he GUO ; Wei-jun ZHANG ; Yu-jie ZHOU ; Dong ZHAO ; Zhi-ming ZHOU ; Hong ZHANG
Chinese Journal of Cardiology 2005;33(5):415-418
OBJECTIVETo evaluate the correlation between multiple cardiovascular risk factors and the extent and severity of angiographic coronary artery disease (CAD) in patients underwent coronary angiography.
METHODSNine hundred and twenty consecutive patients underwent coronary angiography were selected according to inclusion criteria. The extent and severity of angiographic CAD was diagnosed by: (1) whether or not CAD was diagnosed by angiography; (2) the number of diseased vessels; (3) The CAD Gensini cumulative index. Cardiovascular risk factors included were age, gender, hypertension, smoking status, type 2 diabetes mellitus, dyslipidemia, and high uric acid level. Analyses were achieved by univariate and multivariate analysis.
RESULTS(1) Logistic regression analysis showed that high low-density lipoprotein was a prominent predictor of the extent and severity of angiographic CAD (OR = 2.816, 95% CI 1.903 - 4.167, P = 0.001). (2) High low-density lipoprotein was the most important risk factor in men, whereas smoking and high uric acid were the most important risk factors in women.
CONCLUSION(1) It is very important to control risk factors in the intervention and prevention of CAD. (2) Distribution of risk factors and their severities vary in different genders, therefore the treatment of risk factors should be done differently.
Adult ; Aged ; Cardiovascular Diseases ; etiology ; Coronary Angiography ; Coronary Disease ; diagnostic imaging ; Female ; Humans ; Logistic Models ; Male ; Middle Aged ; Multivariate Analysis ; Risk Factors
9.The flow convergence method in the quantitative assessment of valvular regurgitation by real-time tri-plane echocardiography: an in vitro model study.
Journal of Biomedical Engineering 2012;29(6):1078-1083
This paper is aimed to evaluate the accuracy and influence factors about quantitative assessment of valve regurgitation using flow convergence (FC) method with real-time tri-plane echocardiography. By an in vitro model made by ourselves we observed the areas of the FC of the regurgitant orifice under different diameters with the real-time tri-plane echocardiography. The effective regurgitant orifice areas (EROA) and the flow rate were calculated under different pressure gradients, instrument gain and color Doppler surveying range. The results were compared with the real size of the regurgitation orifice and flow rate. In 4mm, 6mm, and 8mm diameter of the regurgitant orifice, the instrument gain and color Doppler surveying rage have not significant influence on the measurement result of flow rate (P = 0.384, P = 0.903). But the measurement result of flow rate was increased following the pressure gradient augment (P = 0.00). While in the regurgitant orifice with diameter 2mm the measurement result of flow rate was influenced by the instrument gain but was not influenced by the pressure gradient or color Doppler surveying range (P = 0.55, P = 0.39). The measurement result of EROA was correlated well with the real regurgitant orifice area (r = 0.99). Using FC method with real-time tri-plane echocardiography to quantitatively assess the valvular regurgitation is simple and feasible. But it should be noted that the pressure gradient and diameter of regurgitant orifice have shown their influence on the results.
Blood Flow Velocity
;
physiology
;
Blood Volume
;
physiology
;
Computer Simulation
;
Echocardiography, Three-Dimensional
;
methods
;
Heart Valve Diseases
;
diagnostic imaging
;
physiopathology
;
Humans
;
Image Interpretation, Computer-Assisted
;
methods
;
Models, Cardiovascular
10.The relationship between resting heart rate and target organs damage in senile essential hypertension.
Ping LIU ; Su-jia WANG ; Yun ZHANG
Chinese Journal of Cardiology 2005;33(1):49-53
OBJECTIVETo investigate the relationship between resting heart rate (RHR)and target organs damage in senile essential hypertension.
METHODSAll 206 elderly essential hypertensive patients (age: 60 - 85 years) were divided into three groups according to the levels of systolic blood pressure (SBP): SBP < 160 mm Hg, 160 mm Hg = SBP < 180 mm Hg, SBP >/= 180 mm Hg. Each of the groups mentioned above were divided into five groups according to the levels of RHR [RHR1 group: RHR < 65 beats/minute(bpm); RHR2: 65 bpm = RHR < 69 bpm; RHR 3: 70 bpm = RHR < 74 bpm; RHR4: 75 bpm = RHR < 79 bpm; RHR5: RHR >/= 80 bpm]. Electrocardiography, carotid ultrasonography, echocardiography, creatinine clearance rate (CCr) and quantitative test for 24 hours' urinary microalbuminuria (MAU) were performed.
RESULTS(1) Compared with RHR1-RHR4 groups, the RHR5 group showed with lower levels of MAU and left ventricular ejection fraction (LVEF) (P < 0.05 or P < 0.01). Compared with RHR1 and RHR2 groups, RHR5 or RHR4 group showed with higher levels of carotid intima-medial thickness (IMT) and carotid arterial diameter (CAD), lower CCr and MAU (P < 0.05 or P < 0.01). (2) The levels of IMT, CAD, LVMI, MAU were positively correlated to RHR (r = 0.312, 0.289, 0.630, 0.563, 0.576 respectively, all P < 0.01), however, the levels of LVEF, CCr were negatively correlated to RHR (r = -0.563, -0.510. all P < 0.01).
CONCLUSIONSTarget organ damage (TOD) seems not only related with PP, SBP, DBP, but also related with RHR in senile essential hypertension. RHR may be one of the important risk factors in TOD.
Aged ; Aged, 80 and over ; Blood Pressure ; Cardiovascular Diseases ; etiology ; Female ; Heart Rate ; Humans ; Hypertension ; complications ; diagnostic imaging ; physiopathology ; Hypertrophy, Left Ventricular ; Male ; Middle Aged ; Ultrasonography