Key result
DeepLab and LSTM models outperform Simpson's method for LVEF estimation with ~6% mean absolute error.
Why the study?
Cardiologist quantification of LVEF from echocardiography data exhibits significant inter-observer and intra-observer variability.
Does a machine learning approach using DeepLab and LSTM improve the accuracy of LVEF estimation from echocardiograms compared to Simpson's method?
Does a machine learning approach using DeepLab and LSTM improve the accuracy of LVEF estimation from echocardiograms compared to Simpson's method?
Machine learning techniques, specifically DeepLab combined with LSTM, can estimate left ventricular ejection fraction from echocardiograms with high accuracy, outperforming traditional clinical methods like Simpson's method.
ML may reduce LVEF variability; leaves open whether it improves outcomes or should enter practice.
Echocardiography is one of the imaging systems most often utilized for assessing heart anatomy and function. Left ventricle ejection fraction (LVEF) is an important clinical variable assessed from echocardiography via the measurement of left ventricle (LV) parameters. Significant inter-observer and intra-observer variability is seen when LVEF is quantified by cardiologists using huge echocardiography data. Machine learning algorithms have the capability to analyze such extensive datasets and identify intricate patterns of structure and function of the heart that highly skilled observers might overlook, hence paving the way for computer-assisted diagnostics in this field. In this study, LV segmentation is performed on echocardiogram data followed by feature extraction from the left ventricle based on clinical methods. The extracted features are then subjected to analysis using both neural networks and traditional machine learning algorithms to estimate the LVEF. The results indicate that employing machine learning techniques on the extracted features from the left ventricle leads to higher accuracy than the utilization of Simpson's method for estimating the LVEF. The evaluations are performed on a publicly available echocardiogram dataset, EchoNet-Dynamic. The best results are obtained when DeepLab, a convolutional neural network architecture, is used for LV segmentation along with Long Short-Term Memory Networks (LSTM) for the regression of LVEF, obtaining a dice similarity coefficient of 0.92 and a mean absolute error of 5.736%.
No takes yet. Share an insight, caveat, or question.
Batool et al. (2023) studied Left ventricle ejection fraction estimation. DeepLab and LSTM machine learning algorithms vs. Simpson's method was evaluated on LVEF estimation accuracy (dice similarity coefficient and mean absolute error). DeepLab for LV segmentation combined with LSTM for LVEF regression achieved higher accuracy than Simpson's method, obtaining a dice similarity coefficient of 0.92 and a mean absolute error of 5.736%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: