Automated Assessment of Aortic Regurgitation using 2D Doppler Echocardiogram
29 Apr 2006-pp 95-99
TL;DR: Present work provides a novel automated tool for extraction of clinical parameters from 2D Doppler images and assesses the severity of AR thus overcoming the short comings of the manual technique.
Abstract: Based on 2D Doppler echocardiography a non-invasive automated method for assessing the severity of Aortic Regurgitation (AR) is explained in this paper. Using GE ultrasound machine equipped with 1.7MHz to 15MHz phased array transducers. Continuous Wave (CW) color Doppler echocardiographic images of aortic valve were obtained from Frontier Life Line Hospital, Chennai, India. Doppler index is extracted by applying image processing techniques. Proposed algorithm automatically detects Peak velocity envelope of the spectral Doppler ultrasound tracings for calculating Pressure Half Time (PHT) available in a single screen frame. Measurements extracted automatically from the maximal velocity envelope are compared with measurements obtained manually where PHT for severity assessment of AR show strong positive correlation (r=0.950313). Present work provides a novel automated tool for extraction of clinical parameters from 2D Doppler images and assesses the severity of AR thus overcoming the short comings of the manual technique.
Citations
More filters
18 Jun 2018
TL;DR: The first steps for a system that classifies ejection fraction in four classes, based on TTE exams, with the objective of automatically providing valuable information to physicians are proposed, and show that convolutional neural networks can be applied to this domain.
Abstract: Cardiovascular diseases are the leading cause of death worldwide. These diseases are related with a broad range of factors but usually show high correlation with diminished left ventricle function, which can be evaluated by measuring the ventricular ejection fraction through transthoracic echocardiography (TTE), a cost-effective and highly portable first-line diagnosing technique. Ejection fraction (EF) is currently determined through a semi-automatic process that requires manual delineation of the left ventricle area both in a diastolic and systolic frame of the patient's exam. To remove this manual annotation step, which is both time-consuming and user dependent, automatic Computer-Aided Diagnosis (CAD) systems can be used. Herein, we propose the first steps for such a system that classifies ejection fraction in four classes, based on TTE exams, with the objective of automatically providing valuable information to physicians. Our classification method is based on a 3D-Convolutional Neural Network (3D-CNN) trained on a dataset constructed with exams from a cardiology reference center. The dataset creation consisted of three main steps: firstly, for each exam, cine-loops showing the apical 4 chambers view were manually selected; then, 30 sequential frames were extracted from each cine-loop; finally, each frame was pre-processed to mask burned-in metadata. The neural network was designed to explore concepts such as convolutions using asymmetric filters and residual learning blocks. The model was trained on a dataset with 4000 TTE exams and tested on a separate dataset containing 1600 TTE cases. We obtained an accuracy of 78% and a F1 score of 71.3% for unhealthy EF (below 45%), 63.3% for intermediate EF (45-55%), 72.3% for healthy EF (55-75%) and 54.6% for abnormally high EF (above 75%). These results are promising and show that convolutional neural networks can be applied to this domain. Furthermore, this work will serve as a foundation for future research where other relevant cardiac metrics will be determined.
22 citations
Cites methods from "Automated Assessment of Aortic Regu..."
...For instance, it is possible to perform the automatic identification of the endocardium [12], tracking of anterior mitral leaflet [13] or even perform an automated assessment of Aortic Regurgitation [14]....
[...]
TL;DR: This review comprehensively and systematically review existing methods of four major tasks: echo quality assessment, view classification, boundary segmentation, and disease diagnosis and discusses the challenges that need to be addressed to obtain robust systems suitable for efficient use in clinical settings or point-of-care testing.
Abstract: Echocardiography (echo) is a critical tool in diagnosing various cardiovascular diseases. Despite its diagnostic and prognostic value, interpretation and analysis of echo images are still widely performed manually by echocardiographers. A plethora of algorithms has been proposed to analyze medical ultrasound data using signal processing and machine learning techniques. These algorithms provided opportunities for developing automated echo analysis and interpretation systems. The automated approach can significantly assist in decreasing the variability and burden associated with manual image measurements. In this paper, we review the state-of-the-art automatic methods for analyzing echocardiography data. Particularly, we comprehensively and systematically review existing methods of four major tasks: echo quality assessment, view classification, boundary segmentation, and disease diagnosis. Our review covers three echo imaging modes, which are B-mode, M-mode, and Doppler. We also discuss the challenges and limitations of current methods and outline the most pressing directions for future research. In summary, this review presents the current status of automatic echo analysis and discusses the challenges that need to be addressed to obtain robust systems suitable for efficient use in clinical settings or point-of-care testing.
21 citations
Cites methods from "Automated Assessment of Aortic Regu..."
...[83] proposed an automated method for assessing the severity of aortic valve regurgitation....
[...]
...Another low level image processing-based method is presented in [83]....
[...]
TL;DR: Excellent detection performance is revealed, suggesting that the proposed approach can be adopted for the automatic analysis of long PWD traces or embedded in ultrasound machines as a first step for the extraction of measurements and reference clinical parameters.
11 citations
TL;DR: In this article , a 3-stage DL framework was developed to automatically analyze echocardiographic videos for the presence of valvular heart diseases (VHDs) and quantifies key metrics related to VHD severities.
Abstract: This study sought to develop a deep learning (DL) framework to automatically analyze echocardiographic videos for the presence of valvular heart diseases (VHDs).Although advances in DL have been applied to the interpretation of echocardiograms, such techniques have not been reported for interpretation of color Doppler videos for diagnosing VHDs.The authors developed a 3-stage DL framework for automatic screening of echocardiographic videos for mitral stenosis (MS), mitral regurgitation (MR), aortic stenosis (AS), and aortic regurgitation (AR) that classifies echocardiographic views, detects the presence of VHDs, and, when present, quantifies key metrics related to VHD severities. The algorithm was trained (n = 1,335), validated (n = 311), and tested (n = 434) using retrospectively selected studies from 5 hospitals. A prospectively collected set of 1,374 consecutive echocardiograms served as a real-world test data set.Disease classification accuracy was high, with areas under the curve of 0.99 (95% CI: 0.97-0.99) for MS; 0.88 (95% CI: 0.86-0.90) for MR; 0.97 (95% CI: 0.95-0.99) for AS; and 0.90 (95% CI: 0.88-0.92) for AR in the prospective test data set. The limits of agreement (LOA) between the DL algorithm and physician estimates of metrics of valve lesion severities compared to the LOAs between 2 experienced physicians spanned from -0.60 to 0.77 cm2 vs -0.48 to 0.44 cm2 for MV area; from -0.27 to 0.25 vs -0.23 to 0.08 for MR jet area/left atrial area; from -0.86 to 0.52 m/s vs -0.48 to 0.54 m/s for peak aortic valve blood flow velocity (Vmax); from -10.6 to 9.5 mm Hg vs -10.2 to 4.9 mm Hg for average peak aortic valve gradient; and from -0.39 to 0.32 vs -0.31 to 0.32 for AR jet width/left ventricular outflow tract diameter.The proposed deep learning algorithm has the potential to automate and increase efficiency of the clinical workflow for screening echocardiographic images for the presence of VHDs and for quantifying metrics of disease severity.
10 citations
TL;DR: In this paper, a 3-stage DL framework was developed for automatic screening of echocardiographic videos for the presence of valvular heart diseases (VHDs) and quantifying key metrics related to VHD severities.
Abstract: Objectives This study sought to develop a deep learning (DL) framework to automatically analyze echocardiographic videos for the presence of valvular heart diseases (VHDs). Background Although advances in DL have been applied to the interpretation of echocardiograms, such techniques have not been reported for interpretation of color Doppler videos for diagnosing VHDs. Methods We developed a 3-stage DL framework for automatic screening of echocardiographic videos for mitral stenosis (MS), mitral regurgitation (MR), aortic stenosis (AS), and aortic regurgitation (AR) that classifies echocardiographic views, detects the presence of VHDs, and, when present, quantifies key metrics related to VHD severities. The algorithm was trained (n = 1,335), validated (n = 311), and tested (n = 434) using retrospectively selected studies from 5 hospitals. A prospectively collected set of 1,374 consecutive echocardiograms served as a real-world test data set. Results Disease classification accuracy was high, with areas under the curve of 0.99 (95% CI: 0.97-0.99) for MS; 0.88 [95% CI: 0.86-0.90] for MR; 0.97 [95% CI: 0.95-0.99] for AS; and 0.90 [95% CI: 0.88-0.92]) for AR in the prospective test data set. The limits of agreement (LOA) between the DL algorithm and physician estimates of metrics of valve lesion severities compared to the LOAs between 2 experienced physicians spanned from −0.60 to 0.77 cm2 vs −0.48 to 0.44 cm2 for MV area; from −0.27 to 0.25 vs −0.23 to 0.08 for MR jet area/left atrial area; from −0.86 to 0.52 m/s vs −0.48 to 0.54 m/s for peak aortic valve blood flow velocity (Vmax); from −10.6 to 9.5 mm Hg vs −10.2 to 4.9 mm Hg for average peak aortic valve gradient; and from −0.39 to 0.32 vs −0.31 to 0.32 for AR jet width/left ventricular outflow tract diameter. Conclusions The proposed deep learning algorithm has the potential to automate and increase efficiency of the clinical workflow for screening echocardiographic images for the presence of VHDs and for quantifying metrics of disease severity.
10 citations
References
More filters
TL;DR: A report from the American Society of Echocardiography’s Nomenclature and Standards Committee and The Task Force on Valvular Regurgitation developed in conjunction with the American College of Cardiology EchOCardiography Committee.
3,769 citations
"Automated Assessment of Aortic Regu..." refers result in this paper
...Studies show that these indices are best predictors of AR giving better support to angiogram results [5][6][7][8]....
[...]
TL;DR: A highly automated method for the identification and quantization of maximum blood velocity curves from Doppler ultrasound flow diagrams is presented and excellent correlation of r = 0.99 is achieved.
Abstract: A highly automated method for the identification and quantization of maximum blood velocity curves from Doppler ultrasound flow diagrams is presented. The method uses an image processing scheme to analyze video-recorded image sequences of flow diagrams. The sequences are acquired, a sequence of images relating to chronological cardiac cycles is extracted, and a maximum blood velocity envelope is determined and quantified. The results are verified against hand-traced reference curves. Excellent correlation of r = 0.99 is achieved.
45 citations
"Automated Assessment of Aortic Regu..." refers methods in this paper
...The work by Tschirren et al [4] deals with the automated extraction of parameters from Doppler tracings taken from the Brachial Artery....
[...]
...Automatic detection of Doppler indices are mostly based on some form of noise reduction and edgedetection algorithm, followed by parameter extraction [2],[3],[4]....
[...]
TL;DR: In this article, the authors developed, tested and verified a computerized method of Doppler velocity profile (DVP) acquisition and reproduction, and carried out numerical determination of model-to-model and model to data goodness-of-fit.
Abstract: Anatomic/physiologic and kinematic mathematical models of diastolic filling which employ (lumped) parameters of diastolic function have been used to predict or characterize transmitral flow. The ability to determine model parameters from clinical transmitral flow, the Doppler velocity profile (DVP), is equivalent to solving the “inverse problem” of diastole. Systematic model-to-model and model-to-data comparison has never been carried out, in part due to the requirement that DVPs be digitized by hand. We developed, tested and verified a computerized method of DVP acquisition and reproduction, and carried out numerical determination of model-to-model and model-to-data goodness-of-fit. The transmitral flow velocity of two anatomic/physiologic models and one kinematic model were compared. Each model's ability to fit computer-acquired and reproduced transmitral DVPs was assessed. Results indicate that transmitral flow velocities generated by the three models are graphically indistinguishable and are able to fit the E-wave of clinical DVPs with comparable mean-square errors. Nonunique invertibility of the anatomic/physiologic models was verified, i.e. , multiple sets of model parameters could be found that fit a single DVP with comparable mean-square error. The kinematic formulation permitted automated, unique, model-parameter determination, solving the “inverse problem” for the Doppler E-wave. We conclude that automated, quantitative characterization of clinical Doppler E-wave contours using this method is feasible. The relation of kinematic parameters to physiologic variables is a subject of current investigation.
28 citations
"Automated Assessment of Aortic Regu..." refers methods in this paper
...Automatic detection of Doppler indices are mostly based on some form of noise reduction and edgedetection algorithm, followed by parameter extraction [2],[3],[4]....
[...]
TL;DR: The newly-developed automated method for Doppler analysis based on image processing and computer vision algorithms offers a new, accurate and reliable clinical tool, particularly for the assessment of patients with irregular heart rate.
Abstract: Currently, Doppler echocardiography analysis is performed manually. An automated method that analyzes the Doppler signal can potentially improve accuracy and result in a powerful tool for noninvasive evaluation of cardiac hemodynamics, especially for patients with atrial fibrillation, where multiple samples are needed to obtain an accurate averaged measurement. The aim of this study was to develop an automated method for Doppler analysis based on image processing and computer vision algorithms. Images were obtained from the mitral valve and the tricuspid valve Doppler tracings from 45 patients, 20 with normal sinus rhythm and 25 with atrial fibrillation. The proposed algorithm automatically detects the maximal velocity envelope of the spectral Doppler ultrasound tracings. Averaged values for the time velocity integral, peak mitral inflow velocity and peak tricuspid regurgitation velocity were calculated for multiple beats available in a single screen frame. Measurements extracted automatically from the maximal velocity envelope were compared to measurements obtained manually by two expert technicians. High linear correlation (r) was found between the automatically- and the manually-extracted parameters (0.95 hayit@eng.tau.ac.il )
27 citations
"Automated Assessment of Aortic Regu..." refers methods in this paper
...The proposed scheme is motivated by the automated system suggested by Hayit Greenspan[1] (2004-2005) to analyze the complex data present in cardiac Doppler tracings using advanced image processing and computer vision tools....
[...]
...The proposed scheme is motivated by the automated system suggested by Hayit Greenspan[1] (2004-2005) to analyze the complex data present in cardiac Doppler tracings using advanced image processing and computer vision tools....
[...]
TL;DR: In this article, the benefit of combining information from different Doppler methods has not been defined, and the authors proposed a strategy based on considering as the definitive severity grade that in which the two best methods agreed, particularly when the jet was eccentric.
25 citations