Related Experiment Video
Updated: Dec 31, 2025
Development and Evaluation of 3D-Printed Cardiovascular Phantoms for Interventional Planning and Training
Published on: January 18, 2021
Integrated 3D Anatomical Model for Automatic Myocardial Segmentation in Cardiac CT Imagery
N Dahiya1, A Yezzi1, M Piccinelli2
1Georgia Institute of Technology, North Ave NW, Atlanta, GA 30332, USA.
Insights
This study introduces an automatic algorithm for segmenting heart boundaries in CT scans, improving cardiovascular diagnosis. The novel method accurately identifies Left Ventricle, Right Ventricle, and Epicardium boundaries, overcoming manual segmentation limitations.
Area of Science:
- Medical Imaging
- Computational Anatomy
- Cardiovascular Imaging
Background:
- Manual segmentation of cardiac boundaries in Computed Tomography Angiography (CTA) is subjective and time-consuming.
- Accurate segmentation is crucial for diagnosing cardiovascular function.
Purpose of the Study:
- To develop a novel, automated algorithm for segmenting epicardial and endocardial boundaries in cardiac CTA.
- To improve the efficiency and accuracy of myocardial segmentation for clinical diagnosis.
Main Methods:
- A multi-dimensional automatic edge detection algorithm utilizing shape priors and Principal Component Analysis (PCA).
- A customized parametric model for implicit 3D curve representations of Left Ventricle (LV), Right Ventricle (RV), and Epicardium (Epi).
- A region-based image modeling framework with high-level constraints for complex cardiac structures.
Main Results:
- Robust segmentation of LV, RV, and Epi boundaries achieved on 30 short-axis CTA datasets.
- Mean segmentation errors were reported as 1.46 ± 0.41 mm for LV, 2.06 ± 0.65 mm for RV, and 2.88 ± 0.59 mm for Epi.
- The algorithm demonstrated effective modeling of complex cardiac anatomical structures.
Conclusions:
- The proposed automated segmentation algorithm offers a significant improvement over manual methods for cardiac CTA analysis.
- This technique provides accurate and efficient segmentation of cardiac chambers and epicardial borders, aiding in cardiovascular function assessment.
- The method's robustness and accuracy support its potential for clinical application in heart patient diagnosis.
Abstract:
Segmentation of epicardial and endocardial boundaries is a critical step in diagnosing cardiovascular function in heart patients. The manual tracing of organ contours in Computed Tomography Angiography (CTA) slices is subjective, time-consuming and impractical in clinical setting. We propose a novel multi-dimensional automatic edge detection algorithm based on shape priors and principal component analysis (PCA). We have developed a highly customized parametric model for implicit representations of segmenting curves (3D) for Left Ventricle (LV), Right Ventricle (RV), and Epicardium (Epi) used simultaneously to achieve myocardial segmentation. We have combined these representations in a region-based image modeling framework with high level constraints enabling the modeling of complex cardiac anatomical structures to automatically guide the segmentation of endo/epicardial boundaries. Test results on 30 short-axis CTA datasets show robust segmentation with error (mean ± std mm) of (1.46 ± 0.41), (2.06 ± 0.65), (2.88 ± 0.59) for LV, RV and Epi respectively.
