Related Experiment Video
Updated: May 14, 2026
08:10
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Automatic segmentation of the left atrium from MRI images using salient feature and contour evolution
Liangjia Zhu1, Yi Gao, Anthony Yezzi
1School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30303, USA. ljzhu@gatech.edu
Summary
This study introduces an automated method for segmenting the left atrium in MRI scans. The approach uses the thoracic aorta to locate the left atrium, improving cardiac image analysis.
Area of Science:
- Medical Imaging
- Cardiovascular Imaging
- Image Segmentation
Background:
- Accurate segmentation of the left atrium is crucial for diagnosing cardiovascular diseases.
- Manual segmentation of the left atrium from MRI images is time-consuming and prone to inter-observer variability.
Purpose of the Study:
- To develop an automatic and robust approach for segmenting the left atrium in MRI images.
- To leverage salient anatomical features for improved segmentation accuracy.
Main Methods:
- Detection of the thoracic aorta to identify a seed region within the left atrium.
- Application of a hybrid active contour model integrating robust statistics and localized region intensity.
- Evolution of active contours from the seed region to delineate the entire left atrium.
Main Results:
- The proposed method successfully segments the left atrium from MRI images.
- Experimental results validate the accuracy and robustness of the automated segmentation approach.
- The use of the thoracic aorta as a feature enhances the reliability of seed region localization.
Conclusions:
- The developed automatic approach offers an efficient and accurate solution for left atrium segmentation in MRI.
- This method has the potential to streamline cardiovascular image analysis and improve diagnostic capabilities.
- The integration of robust statistics and region intensity in active contours provides a powerful segmentation tool.
