1
|
Wong KKL, Zhang A, Yang K, Wu S, Ghista DN. GCW-UNet segmentation of cardiac magnetic resonance images for evaluation of left atrial enlargement. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 221:106915. [PMID: 35653942 DOI: 10.1016/j.cmpb.2022.106915] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/13/2021] [Revised: 05/15/2022] [Accepted: 05/24/2022] [Indexed: 06/15/2023]
Abstract
BACKGROUND AND OBJECTIVE Left atrial enlargement (LAE) is an anatomical variation of the left atrium and the result of the long-term increase of left atrial pressure. Most of the increase in stress or volume is due to potential cardiovascular disease. Studies have shown that LAE can independently predict the development of clinically significant cardiovascular disease and heart failure. If the left atrial volume is accurately measured, it will be an essential indicator of human health and an essential means for doctors to find patients' potential diseases. We can analyze the dynamic changes in the left atrial structure and analyze left atrial dilation. However, manual segmentation was inefficient and error-prone before the 3D reconstruction of the left atrium. In order to solve this problem, a convolution neural network (CNN) method based on cardiac magnetic resonance image (MRI) is proposed to automatically segment the left atrial region. METHODOLOGY In this paper, we have proposed and developed a novel U-Net with Gaussian blur and channel weight neural network (GCW-UNet) to automatically segment the left atrial region in the MRI of a patient with LAE. After Gaussian blur, different resolutions of the MRI are obtained. High-resolution MRI clearly shows the detailed features of the left atrium, while low-resolution MRI clearly shows the overall outline of the left atrium, which can solve the problem of more minor MRI features. Adaptive channel weights can enhance the atrial segmentation capability of the network. RESULTS Compared with the state-of-the-art left atrial segmentation methods, our CNN-based technique results in the segmentation of the left atrium being closer to the manual segmentation by an experienced radiologist. On the test datasets, the mean Dice similarity coefficient reaches 93.57%. CONCLUSION Firstly, MRI has a small number of imaging artifacts, which results in low segmentation accuracy. Our method successfully solves the problem. Secondly, due to the high similarity between the background (the area outside the left atrium) and the foreground (the left atrium) in MRI, traditional neural networks misclassify the background as the foreground. Our GCW-Unit can address the imbalanced number of pixels between the foreground and background. Finally, after segmenting the left atrium in the MRI by GCW-Unit, we reconstructed the left atrium to model a three-dimensional heart of a patient suffering from LAE. Based on the different time frames of one heartbeat, we could present the dynamics of the left atrial structure during a cardiac cycle. This can better assist in the evaluation of LAE in heart patients.
Collapse
Affiliation(s)
- Kelvin K L Wong
- School of Computer Science and Engineering, Central South University, Changsha 410083, China.
| | - An Zhang
- Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan, China; Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, China
| | - Ke Yang
- Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan, China; Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, China
| | - Shiqian Wu
- Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan, China; Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, China
| | | |
Collapse
|
2
|
Varadarajan V, Ambale-Venkatesh B, Hong SY, Habibi M, Ashikaga H, Wu CO, Chen LY, Heckbert SR, Bluemke DA, Lima JAC. Association of Longitudinal Changes in NT-proBNP With Changes in Left Atrial Volume and Function: MESA. Am J Hypertens 2021; 34:626-635. [PMID: 33491080 DOI: 10.1093/ajh/hpab018] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2020] [Revised: 12/28/2020] [Accepted: 01/20/2021] [Indexed: 01/14/2023] Open
Abstract
BACKGROUND The mechanism of left atrial (LA) remodeling is poorly understood. The aim of this longitudinal study was to investigate whether changes in NT-proBNP levels relate to alterations of LA structure and function over time in a multiethnic population. METHODS From the prospective cohort study, the Multi-Ethnic Study of Atherosclerosis, our analysis included 1,838 participants who underwent cardiac magnetic resonance imaging at the baseline and 10-year examinations, had NT-proBNP levels available at both time points, and did not develop heart failure, myocardial infarction, and/or atrial fibrillation. Multivariable linear regression was used to analyze the association between NT-proBNP level (log-transformed) at the 2 time points and change in LA volumes, LA emptying fractions (total, active, and passive), and LA longitudinal strain. Log NT-proBNP was categorized into Low-Low (N = 681), Low-High (N = 238), High-Low (N = 237), and High-High (N = 682) based on the median value at both time points. RESULTS With the Low-Low group as the reference group, the High-High group experienced a greater increase in LA maximum and minimum indexed volumes: 3.1 ml/m2 (95% confidence interval 1.98, 4.20) and 2.7 ml/m2 (1.89, 3.51), respectively. The High-High group also experienced a greater decrease in LA total, passive, active emptying fraction, and longitudinal strain: -3.3% (-4.46, -2.11), -0.9% (-1.80, -0.02), -4.2% (-5.55, -2.76), and -2.3% (-3.80, -0.72), respectively. The Low-High group had similar associations, but the effect sizes were not as high. CONCLUSIONS Adverse LA remodeling over 10 years of follow-up strongly correlates with prolonged elevated levels of intracardiac stress, as assessed by NT-proBNP levels.
Collapse
Affiliation(s)
| | | | - Seo Young Hong
- Office of the Director, Center for Scientific Review, National Institutes of Health, Bethesda, Maryland, USA
| | - Mohammadali Habibi
- Department of Cardiology, Johns Hopkins University, Baltimore, Maryland, USA
| | - Hiroshi Ashikaga
- Department of Cardiology, Johns Hopkins University, Baltimore, Maryland, USA
| | - Colin O Wu
- Department of Medicine, National Heart, Lung and Blood Institute, Bethesda, Maryland, USA
| | - Lin Y Chen
- Cardiovascular Division, Department of Medicine, University of Minnesota, Minneapolis, Minnesota, USA
| | - Susan R Heckbert
- Department of Epidemiology, University of Washington, Seattle, Washington, USA
| | - David A Bluemke
- Department of Radiology, University of Wisconsin, Madison, Wisconsin, USA
| | - Joao A C Lima
- Department of Cardiology, Johns Hopkins University, Baltimore, Maryland, USA
| |
Collapse
|
3
|
Fredgart MH, Lindholt JS, Brandes A, Steffensen FH, Frost L, Lambrechtsen J, Karon M, Busk M, Urbonaviciene G, Egstrup K, Diederichsen ACP. Prognostic importance of left atrial size measured by non-contrast cardiac computed tomography - A DANCAVAS study. Int J Cardiol 2020; 328:220-226. [PMID: 33359284 DOI: 10.1016/j.ijcard.2020.12.029] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/07/2020] [Accepted: 12/14/2020] [Indexed: 01/20/2023]
Abstract
BACKGROUND Enlargement of left atrium (LA) is a valuable marker of cardiovascular events, and LA size is readily available while performing non-contrast cardiac computed tomography (NCCT) for preventive purposes. We aimed to evaluate the predictive value of a single LA area from NCCT in a population-based cohort. METHOD Mainly men aged 60-75 years from DANCAVAS were included. Traditional risk factors were recorded, and an NCCT scan performed at baseline. Coronary artery calcifications (CAC) score and the largest LA area were measured. LA was indexed to body surface area and categorised into four groups. Data on incident atrial fibrillation (AF), thromboembolic events, heart failure (HF) and death were obtained from Danish national registries. RESULTS In total, 14,557 individuals were eligible, excluding those without LA measurement (N = 232) and with heart valve replacement (N = 197). Known AF or HF were respectively excluded from follow-up. Median follow-up time was 2.1 to 3.4 years. In total, 304 developed AF, 149 had thromboembolism, 129 developed HF and 482 died. In adjusted analysis, LA enlargement was associated with AF (HR (95% CI): large 1.99 (1.46-2.71) and very large LA 3.77 (2.31-6.14)) and HF (large 2.40 (1.50-3.85) and very large LA 6.54 (4.07-10.51)). A very large LA significantly increased mortality (HR: 2.01 (1.44-2.82)), and was associated with a two-fold increased risk of thromboembolism; however, not significantly in adjusted analysis (p = 0.09). CONCLUSION We demonstrated that determination of LA area from NCCT was an important predictor of AF, HF and death. This knowledge could inform current risk assessment beyond CAC score.
Collapse
Affiliation(s)
- Maise Hoeigaard Fredgart
- Department of Cardiology, Odense University Hospital, Odense, Denmark; OPEN, Odense Patient Data Explorative Network, Odense University Hospital, Odense, Denmark.
| | - Jes Sanddal Lindholt
- Department of Cardiothoracic and Vascular Surgery, Odense University Hospital, Odense, Denmark; Cardiovascular Centre of Excellence (CAVAC), Denmark; Odense University Hospital, Elitary Research Centre of Individualized Medicine in Arterial Disease (CIMA), Odense, Denmark
| | - Axel Brandes
- Department of Cardiology, Odense University Hospital, Odense, Denmark
| | | | - Lars Frost
- Department of Cardiology, Regional Hospital Central Jutland, Silkeborg, Denmark
| | | | - Marek Karon
- Department of Medicine, Nykoebing Falster Hospital, Nykoebing Falster, Denmark
| | - Martin Busk
- Department of Cardiology, Sygehus Lillebaelt, Vejle, Denmark
| | | | - Kenneth Egstrup
- Department of Cardiology, Svendborg Hospital, Svendborg, Denmark
| | - Axel Cosmus Pyndt Diederichsen
- Department of Cardiology, Odense University Hospital, Odense, Denmark; Odense University Hospital, Elitary Research Centre of Individualized Medicine in Arterial Disease (CIMA), Odense, Denmark
| |
Collapse
|
4
|
Fung MJ, Thomas L, Leung DY. Left atrial function: Correlation with left ventricular function and contractile reserve in patients with hypertension. Echocardiography 2018; 35:1596-1605. [DOI: 10.1111/echo.14051] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/25/2022] Open
Affiliation(s)
- Matle J. Fung
- Cardiology Department; Liverpool Hospital; Liverpool, Sydney NSW Australia
- South Western Sydney Clinical School; Faculty of Medicine; The University of New South Wales; Sydney NSW Australia
| | - Liza Thomas
- Cardiology Department; Liverpool Hospital; Liverpool, Sydney NSW Australia
- South Western Sydney Clinical School; Faculty of Medicine; The University of New South Wales; Sydney NSW Australia
- Cardiology Department; Westmead Hospital; Westmead, Sydney NSW Australia
- Faculty of Medicine; The University of Sydney; Sydney NSW Australia
| | - Dominic Y. Leung
- Cardiology Department; Liverpool Hospital; Liverpool, Sydney NSW Australia
- South Western Sydney Clinical School; Faculty of Medicine; The University of New South Wales; Sydney NSW Australia
| |
Collapse
|
5
|
Differences in left ventricular functional adaptation to arterial stiffness and neurohormonal activation in patients with hypertension: a study with two-dimensional layer-specific speckle tracking echocardiography. Clin Hypertens 2017; 23:21. [PMID: 29119005 PMCID: PMC5667034 DOI: 10.1186/s40885-017-0078-9] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2017] [Accepted: 09/27/2017] [Indexed: 01/19/2023] Open
Abstract
Background Arterial stiffness increases pressure load to the left ventricle (LV), leading to LV hypertrophy and subendocardial ischemia. Neurohormones stimulate myocardial fibrosis and LV dysfunction. We aimed to explore the associations of arterial stiffness and plasma aldosterone with multi-directional, layer-specific LV, and left atrial (LA) mechanical function in hypertensive patients. Methods Layer-specific LV global longitudinal strain (GLS-trans, GLS-endo, GLS-epi), global circumferential strain (GCS-trans, GCS-endo, GCS-epi), LV torsional parameters, and LA global longitudinal strain (LA GLS) were analyzed by two-dimensional speckle tracking echocardiography in 195 hypertensive patients (110 men, mean age 55 years). Pulse wave velocity (PWV) was analyzed as a measure of arterial stiffness, and plasma aldosterone was measured for evaluation of neurohormonal activation. Results In a simple correlation, PWV significantly correlated with LV GLS-endo and LA GLS. Log aldosterone correlated with both LV GCS-endo and LV GCS-trans. Multiple regression analysis revealed that LV GLS-endo (β = 0.223, p = 0.031) and LA GLS (β = −0.311, p = 0.002) were independently correlated with PWV even after controlling for confounding factors. Conclusions In hypertensive patients without clinically apparent target organ damage, LV GLS, especially endocardium, and LA GLS were more dominantly affected by arterial stiffness because, among the three myocardial layers, the endocardium is most susceptible to pressure overload. Two-dimensional layer-specific speckle-tracking echocardiography sensitively detects LV mechanical dysfunction and provides pathophysiologic insights into LV mechanical adaptations in hypertension.
Collapse
|
6
|
Liu Y, Wang K, Su D, Cong T, Cheng Y, Zhang Y, Wu J, Sun Y, Shang Z, Liu J, Zhong L, Zou L, Chitian C, Zhang X, Jiang Y. Noninvasive assessment of left atrial phasic function in patients with hypertension and diabetes using two-dimensional speckle tracking and volumetric parameters. Echocardiography 2013; 31:727-35. [PMID: 24354465 DOI: 10.1111/echo.12492] [Citation(s) in RCA: 53] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022] Open
Abstract
OBJECTIVE To evaluate the left atrial phasic function of hypertensive patients with or without coexisting diabetes using two-dimensional speckle tracking echocardiography (2DSTE)-based strain and strain rate imaging and volumetric parameters. METHODS The study included an isolated hypertension group (HT group) comprising 99 patients, a hypertension and diabetes group (HT + DM group) comprising 65 patients, and 26 age-matched healthy controls. The 2DSTE-based strain and strain rate images were studied, and the following parameters were measured: peak left atrial longitudinal strain (LAS-S ), early diastolic (LAS-E ) and late diastolic (LAS-A ) atrial longitudinal strains, and systolic (LASR-S ), early diastolic (LASR-E ) and late diastolic (LASR-A ) strain rates. RESULTS The LAS-S and LASR-S were lower in the HT group and the HT + DM group compared with the control group (P < 0.001). The LAS-E and LASR-E were lower in the HT group (14.9 ± 5.5% and -1.1 ± 0.4/sec, respectively) than in the control group (22.1 ± 8.3% and -1.7 ± 0.6/sec, respectively) (P < 0.001), and they were further depressed in the HT + DM group (12.3 ± 6.3% and -1.0 ± 0.4/sec, respectively) (P < 0.05). There were no significant differences in LAS-A or LASR-A among the 3 groups (P > 0.05). Multivariate regression analysis revealed that HT and DM were independently related to LAS-E and LASR-E . CONCLUSIONS Hypertension can lead to abnormal left atrial reservoir and conduit functions, and coexisting diabetes can further impair conduit function. 2DSTE-derived strain and strain rate imaging are sensitive methods for evaluating left atrial phasic function.
Collapse
Affiliation(s)
- Yan Liu
- The First Affiliated Hospital of Dalian Medical University, Liaoning, China
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|