Estimation of Segmental Longitudinal Strain in Transesophageal Echocardiography by Deep Learning.

2025-09-04

IEEE journal of biomedical and health informatics

AI Summary

Conventional segmental longitudinal strain (SLS) assessment of the left ventricle relies on manual contouring and subjective interpretation, resulting in low efficiency and poor reproducibility. To address this, we propose autoStrain—the first fully automated SLS analysis framework for transesophageal echocardiography (TEE). Our method introduces a novel, ground-truth synthetic TEE dataset generated via SIMUS simulation, and integrates two unsupervised models: TeeFlow (based on RAFT optical flow) for dense motion estimation and TeeTracker (based on CoTracker point tracking) for precise myocardial motion localization—achieving a mean tracking error of 0.65 ± 0.20 mm. Clinical validation demonstrates strong agreement between autoStrain-estimated SLS and reference-standard measurements (mean difference: 1.09%; 95% limits of agreement: −8.90% to 11.09%), meeting clinical feasibility criteria. autoStrain substantially lowers operational barriers while enhancing automation, accuracy, and generalizability of quantitative SLS analysis.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements

Abstract

Segmental longitudinal strain (SLS) of the left ventricle (LV) is an important prognostic indicator for evaluating regional LV dysfunction, in particular for diagnosing and managing myocardial ischemia. Current techniques for strain estimation require significant manual intervention and expertise, limiting their efficiency and making them too resource-intensive for monitoring purposes. This study introduces the first automated pipeline, autoStrain, for SLS estimation in transesophageal echocardiography (TEE) using deep learning (DL) methods for motion estimation. We present a comparative analysis of two DL approaches: TeeFlow, based on the RAFT optical flow model for dense frame-to-frame predictions, and TeeTracker, based on the CoTracker point trajectory model for sparse long-sequence predictions. As ground truth motion data from real echocardiographic sequences are hardly accessible, we took advantage of a unique simulation pipeline (SIMUS) to generate a highly realistic synthetic TEE (synTEE) dataset of 80 patients with ground truth myocardial motion to train and evaluate both models. Our evaluation shows that TeeTracker outperforms TeeFlow in accuracy, achieving a mean distance error in motion estimation of 0.65 $pm$ 0.20 mm on a synTEE test dataset. Clinical validation on 16 patients further demonstrated that SLS estimation with our autoStrain pipeline aligned with clinical references, achieving a mean difference (95% limits of agreement) of 1.09% (-8.90% to 11.09%). Incorporation of simulated ischemia in the synTEE data improved the accuracy of the models in quantifying abnormal deformation. Our findings indicate that integrating AI-driven motion estimation with TEE can significantly enhance the precision and efficiency of cardiac function assessment in clinical settings.

Problem

• Automating segmental longitudinal strain estimation in echocardiography using deep learning
• Reducing manual intervention required for cardiac function assessment in clinical settings
• Improving accuracy of myocardial motion tracking through AI-driven methods

Innovation

• Deep learning for automated segmental strain estimation
• Simulated echocardiography dataset for model training
• AI-driven motion estimation enhancing cardiac assessment precision