Related Experiment Video
Updated: May 30, 2026
Development and Evaluation of 3D-Printed Cardiovascular Phantoms for Interventional Planning and Training
Published on: January 18, 2021
2D/3D fetal cardiac dataset segmentation using a deformable model
Irving Dindoyal1, Tryphon Lambrou, Jing Deng
1Institute of Surgical Technology and Biomechanics, University of Bern, Stauffacherstrasse 78, Bern, Switzerland. irving.dindoyal@istb.unibe.ch
Insights
This study presents an automated method for segmenting fetal heart chambers using ultrasound, improving 3D cardiac assessments. The novel approach accurately delineates structures, reducing errors and enhancing functional analysis.
Area of Science:
- Medical Imaging
- Biomedical Engineering
- Fetal Cardiology
Background:
- Ultrasound imaging of the fetal heart is crucial for assessing cardiac function and structure.
- Image artifacts, such as signal dropout, pose challenges for accurate fetal cardiac segmentation.
- Existing methods may struggle with the precise delineation of small fetal cardiac chambers.
Purpose of the Study:
- To develop an automated method for segmenting the fetal heart.
- To facilitate accurate 3D assessment of fetal cardiac function and structure.
- To overcome limitations posed by ultrasound artifacts in fetal cardiac imaging.
Main Methods:
- A level set deformable model was employed for automatic delineation of fetal cardiac chambers.
- A novel collision detection term was introduced to penalize the model from growing into adjacent compartments.
- A region-based model allowed simultaneous segmentation of all four chambers from user-defined seed points.
Main Results:
- The algorithm demonstrated accurate segmentation with root mean square errors within 2 mm compared to manual tracings.
- Penalties prevented boundary intersection at signal dropout walls, improving segmentation integrity.
- Validation using a physical phantom showed volume segmentation errors within 13%.
Conclusions:
- The developed algorithm offers an accurate and automated solution for fetal cardiac segmentation.
- This method aids in the 3D assessment of fetal cardiac function and structure.
- The study validates the algorithm's performance against manual tracings and physical phantoms.
Purpose:
To segment the fetal heart in order to facilitate the 3D assessment of the cardiac function and structure.
Methods:
Ultrasound acquisition typically results in drop-out artifacts of the chamber walls. The authors outline a level set deformable model to automatically delineate the small fetal cardiac chambers. The level set is penalized from growing into an adjacent cardiac compartment using a novel collision detection term. The region based model allows simultaneous segmentation of all four cardiac chambers from a user defined seed point placed in each chamber.
Results:
The segmented boundaries are automatically penalized from intersecting at walls with signal dropout. Root mean square errors of the perpendicular distances between the algorithm's delineation and manual tracings are within 2 mm which is less than 10% of the length of a typical fetal heart. The ejection fractions were determined from the 3D datasets. We validate the algorithm using a physical phantom and obtain volumes that are comparable to those from physically determined means. The algorithm segments volumes with an error of within 13% as determined using a physical phantom.
Conclusions:
Our original work in fetal cardiac segmentation compares automatic and manual tracings to a physical phantom and also measures inter observer variation.