Key result
A novel 2D-to-3D echocardiography reconstruction framework generated left ventricular digital twins that predicted 1-year all-cause mortality with an AUC of 0.82.
Why the study?
Transthoracic echocardiography is subject to intra- and inter-user variability, and recordings are often limited to 2D imaging and end-diastolic and end-systolic volume assessments.
Does a novel machine learning framework for 4D LV shape reconstruction from 2D echocardiography improve diagnostic accuracy and risk assessment in patients with acute myocardial infarction?
Observational (n=458)
Yes
Does a novel machine learning framework for 4D LV shape reconstruction from 2D echocardiography improve diagnostic accuracy and risk assessment in patients with acute myocardial infarction?
A novel machine learning framework successfully reconstructs 4D left ventricular shapes from standard 2D echocardiography, yielding biomarkers that strongly predict 1-year mortality in patients with acute myocardial infarction.
Transthoracic Echocardiography (TTE) is a crucial tool for assessing cardiac morphology and function quickly and non-invasively without ionising radiation. However, the examination is subject to intra- and inter-user variability and recordings are often limited to 2D imaging and assessments of end-diastolic and end-systolic volumes. We have developed a novel, fully automated machine learning-based framework to generate a personalised 4D (3D plus time) model of the left ventricular (LV) blood pool with high temporal resolution. A 4D shape is reconstructed from specific 2D echocardiographic views employing deep neural networks, pretrained on a synthetic dataset, and fine-tuned in a self-supervised manner using a novel optimisation method for cross-sectional imaging data. No 3D ground truth is needed for model training. The generated digital twins enhance the interpretation of TTE data by providing a versatile tool for automated analysis of LV volume changes, localisation of infarct areas, and identification of new and clinically relevant biomarkers. Experiments are performed on a multicentre dataset that includes TTE exams of 144 patients with normal TTE and 314 patients with acute myocardial infarction (AMI). The novel biomarkers show a high predictive value for survival (area under the curve (AUC) of 0.82 for 1-year all-cause mortality), demonstrating that personalised 3D shape modelling has the potential to improve diagnostic accuracy and risk assessment. • Novel machine learning framework for creating personalised 4D models of the left ventricle from 2D echocardiography. • These digital twins enable a fully automated, robust, and interpretable analysis of echocardiography data. • Personalised 4D shape modelling has the potential to improve diagnostic accuracy.
No takes yet. Share an insight, caveat, or question.
Laumer et al. (2024) conducted an observational in Acute myocardial infarction and normal cardiac function (n=458). 2D to 3D echocardiography reconstruction (digital twin) vs. Standard 2D echocardiography (clinician-derived) was evaluated on 1-year all-cause mortality prediction (AUC) (AUC 0.82). A novel 2D-to-3D echocardiography reconstruction framework generated left ventricular digital twins that predicted 1-year all-cause mortality with an AUC of 0.82.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: