Video Transformer for Segmentation of Echocardiography Images in Myocardial Strain Measurement
Open Access
- 17 September 2025
- journal article
- research article
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (3) , 2661-2679
Abstract
The adoption of left ventricular global longitudinal strain (LVGLS) is still restricted by variability among various vendors and observers, despite advancements from tissue Doppler to speckle tracking imaging, machine learning, and, more recently, convolutional neural network (CNN)-based segmentation strain analysis. While CNNs have enabled fully automated strain measurement, they are inherently constrained by restricted receptive fields and a lack of temporal consistency. Transformer-based networks have emerged as a powerful alternative in medical imaging, offering enhanced global attention. Among these, the Video Swin Transformer (V-SwinT) architecture, with its 3D-shifted windows and locality inductive bias, is particularly well suited for ultrasound imaging, providing temporal consistency while optimizing computational efficiency. In this study, we propose the DTHR-SegStrain model based on a V-SwinT backbone. This model incorporates contour regression and utilizes an FCN-style multiscale feature fusion. As a result, it can generate accurate and temporally consistent left ventricle (LV) contours, allowing for direct calculation of myocardial strain without the need for conversion from segmentation to contours or any additional postprocessing. Compared to EchoNet-dynamic and Unity-GLS, DTHR-SegStrain showed greater efficiency, reliability, and validity in LVGLS measurements. Furthermore, the hybridization experiments assessed the interaction between segmentation models and strain algorithms, reinforcing that consistent segmentation contours over time can simplify strain calculations and decrease measurement variability. These findings emphasize the potential of V-SwinT-based frameworks to enhance the standardization and clinical applicability of LVGLS assessments.Keywords
Funding Information
- National Science and Technology Council (NSTC 113 - 2314 - B - 002 - 144 - MY3)
- National Science and Technology Council (MOST 111-2628-B-002-034-MY3.)
This publication has 20 references indexed in Scilit:
- Artificial Intelligence for Automatic Measurement of Left Ventricular Strain in EchocardiographyJACC: Cardiovascular Imaging, 2021
- Artificial Intelligence Aids Cardiac Image Quality Assessment for Improving Precision in Strain MeasurementsJACC: Cardiovascular Imaging, 2021
- Video-based AI for beat-to-beat assessment of cardiac functionNature, 2020
- Deep Learning for Segmentation Using an Open Large-Scale Dataset in 2D EchocardiographyIEEE Transactions on Medical Imaging, 2019
- A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability ResearchJournal of Chiropractic Medicine, 2016
- Fully Convolutional Networks for Semantic SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Fact or Artifact in Two-Dimensional Echocardiography: Avoiding Misdiagnosis and Missed DiagnosisJournal of the American Society of Echocardiography, 2016
- Beyond ejection fraction: an integrative approach for assessment of cardiac structure and function in heart failureEuropean Heart Journal, 2015
- Intervendor Variability of Two-Dimensional Strain Using Vendor-Specific and Vendor-Independent SoftwareJournal of the American Society of Echocardiography, 2015
- Definitions for a common standard for 2D speckle tracking echocardiography: consensus document of the EACVI/ASE/Industry Task Force to standardize deformation imagingEuropean Heart Journal - Cardiovascular Imaging, 2014