Related Experiment Video
Updated: Mar 1, 2026
07:45
Quantifying Intermembrane Distances with Serial Image Dilations
Published on: September 28, 2018
6.8K
Semiautomated biventricular segmentation in three-dimensional echocardiography by coupled deformable surfaces
Jørn Bersvendsen1,2,3, Fredrik Orderud2, Øyvind Lie3,4
1GE Vingmed Ultrasound AS, Horten, Norway.
Journal of Medical Imaging (Bellingham, Wash.)
|June 1, 2017
Summary
This study introduces a novel method for segmenting both left and right heart ventricles in 3D echocardiography, improving cardiovascular disease diagnosis. The technique accurately models heart chambers, enhancing patient-specific geometric analysis.
Area of Science:
- Cardiovascular Imaging
- Medical Image Analysis
- Computational Anatomy
Background:
- 3D real-time echocardiography enables patient-specific geometric models for clinical decisions.
- Current echocardiographic segmentation methods primarily focus on the left ventricle (LV), neglecting the right ventricle (RV).
- The RV's role in cardiovascular disease is increasingly recognized, highlighting the need for its accurate segmentation.
Purpose of the Study:
- To develop a method for coupled segmentation of endocardial and epicardial borders for both LV and RV in 3D ultrasound images.
- To address the gap in RV segmentation within cardiovascular imaging research.
Main Methods:
- Proposed an extension of a state-estimation segmentation framework incorporating coupled surface geometry.
- Introduced myocardial incompressibility as a regularization technique for segmentation.
- Validated the method against manual segmentations in 16 patient datasets.
Main Results:
- Achieved mean absolute distances of [Formula: see text] for LV endocardium, [Formula: see text] for RV endocardium, and [Formula: see text] for LV epicardium.
- Demonstrated computational efficiency with a computation time of [Formula: see text].
Conclusions:
- The developed method enables accurate and efficient coupled segmentation of both LV and RV borders in 3D echocardiography.
- This advancement supports improved clinical decision-making through comprehensive cardiac geometric modeling.
- The technique offers a valuable tool for research and clinical practice in cardiovascular disease management.
