Key result
Deep learning model achieves ~1 mm absolute LVOTd error versus expert cardiologists.
Why the study?
Measurement of LVOTd in echocardiography is a common source of error when calculating stroke volume, prompting evaluation of whether deep learning can perform automatic measurements on par with experts.
Does a deep learning model perform automatic LVOTd measurements on par with expert cardiologists in patients with coronary artery disease?
Observational (n=649)
No
Does a deep learning model perform automatic LVOTd measurements on par with expert cardiologists in patients with coronary artery disease?
A deep learning model can automatically measure LVOTd in 2D echocardiography with an error margin comparable to clinical inter-observer variability, though it requires further validation and refinement.
May enable automated LVOTd measurement; leaves open prospective validation before clinical adoption.
BACKGROUND: Measurement of the left ventricular outflow tract diameter (LVOTd) in echocardiography is a common source of error when used to calculate the stroke volume. The aim of this study is to assess whether a deep learning (DL) model, trained on a clinical echocardiographic dataset, can perform automatic LVOTd measurements on par with expert cardiologists. METHODS: Data consisted of 649 consecutive transthoracic echocardiographic examinations of patients with coronary artery disease admitted to a university hospital. 1304 LVOTd measurements in the parasternal long axis (PLAX) and zoomed parasternal long axis views (ZPLAX) were collected, with each patient having 1-6 measurements per examination. Data quality control was performed by an expert cardiologist, and spatial geometry data was preserved for each LVOTd measurement to convert DL predictions into metric units. A convolutional neural network based on the U-Net was used as the DL model. RESULTS: The mean absolute LVOTd error was 1.04 (95% confidence interval [CI] 0.90-1.19) mm for DL predictions on the test set. The mean relative LVOTd errors across all data subgroups ranged from 3.8 to 5.1% for the test set. Generally, the DL model had superior performance on the ZPLAX view compared to the PLAX view. DL model precision for patients with repeated LVOTd measurements had a mean coefficient of variation of 2.2 (95% CI 1.6-2.7) %, which was comparable to the clinicians for the test set. CONCLUSION: DL for automatic LVOTd measurements in PLAX and ZPLAX views is feasible when trained on a limited clinical dataset. While the DL predicted LVOTd measurements were within the expected range of clinical inter-observer variability, the robustness of the DL model requires validation on independent datasets. Future experiments using temporal information and anatomical constraints could improve valvular identification and reduce outliers, which are challenges that must be addressed before clinical utilization.
No takes yet. Share an insight, caveat, or question.
Zha et al. (2023) conducted an observational in Coronary artery disease (n=649). Deep learning (DL) model vs. Expert cardiologist measurements was evaluated on Mean absolute LVOTd error on the test set (95% CI 0.90-1.19). A deep learning model trained on clinical echocardiographic data achieved a mean absolute left ventricular outflow tract diameter error of 1.04 mm compared to expert cardiologist measurements.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: