Related Experiment Video
Updated: Aug 11, 2026
3D Modeling of the Lateral Ventricles and Histological Characterization of Periventricular Tissue in Humans and Mouse
Published on: May 19, 2015
Left ventricle Hermite-based segmentation
Jimena Olveres1, Rodrigo Nava2, Boris Escalante-Ramírez1
1Facultad de Ingeniería, Universidad Nacional Autónoma de México, Mexico.
Insights
This study introduces a new 2D technique for segmenting cardiac boundaries using computed tomography (CT) imaging. The method automates segmentation of heart cavities, aiding in faster and more accurate heart disease diagnosis.
Area of Science:
- Medical Imaging
- Biomedical Engineering
- Cardiology
Background:
- Computed tomography (CT) is crucial for cardiac imaging, but manual segmentation of heart cavities is time-consuming.
- Accurate segmentation is vital for diagnosing conditions affecting heart function.
Purpose of the Study:
- To develop a novel 2D technique for segmenting endocardium and epicardium boundaries in cardiac CT images.
- To automate the segmentation process, reducing the time and effort required for cardiac diagnosis.
Main Methods:
- A 2D approach utilizing the Hermite transform to compute information from the left ventricle and adjacent structures.
- Integration of computed information with active shape models and level sets for enhanced segmentation.
- Evaluation using Dice coefficient, Hausdorff distance, and a novel Ray Feature error metric.
Main Results:
- The proposed method accurately discriminates cardiac tissue.
- The technique demonstrates potential for improving the efficiency and accuracy of cardiac segmentation.
- Quantitative assessment showed promising results using established and novel metrics.
Conclusions:
- The novel segmentation technique offers a valuable tool for supporting heart disease diagnosis.
- Automated segmentation can streamline the diagnostic workflow and aid in treatment planning.
- This approach may enhance the clinical utility of cardiac CT imaging.
Abstract:
In recent years, computed tomography (CT) has become a standard technique in cardiac imaging because it provides detailed information that may facilitate the diagnosis of the conditions that interfere with correct heart function. However, CT-based cardiac diagnosis requires manual segmentation of heart cavities, which is a difficult and time-consuming task. Thus, in this paper, we propose a novel technique to segment endocardium and epicardium boundaries based on a 2D approach. The proposal computes relevant information of the left ventricle and its adjacent structures using the Hermite transform. The novelty of the work is that the information is combined with active shape models and level sets to improve the segmentation. Our database consists of mid-third slices selected from 28 volumes manually segmented by expert physicians. The segmentation is assessed using Dice coefficient and Hausdorff distance. In addition, we introduce a novel metric called Ray Feature error to evaluate our method. The results show that the proposal accurately discriminates cardiac tissue. Thus, it may be a useful tool for supporting heart disease diagnosis and tailoring treatments.
