Related Experiment Videos
Clinical validation of an automated boundary tracking algorithm on cardiac MR images
L A Latson1, K A Powell, B Sturm
1Case Western Reserve University, Cleveland, OH, USA.
Insights
This study developed an automated algorithm for tracking left ventricle (LV) borders in cine-MRI scans. The algorithm accurately calculates LV volumes in healthy individuals and patients with heart conditions.
Area of Science:
- Cardiovascular Imaging
- Medical Image Analysis
- Computational Cardiology
Background:
- Accurate assessment of left ventricular (LV) volumes is crucial for diagnosing and managing cardiac diseases.
- Manual tracing of LV borders in cine-MRI is time-consuming and subject to inter-observer variability.
Purpose of the Study:
- To develop and validate an automated algorithm for tracking LV borders in cine-MRI gradient-echo temporal datasets.
- To assess the algorithm's performance across diverse patient populations.
Main Methods:
- An automated algorithm was developed to track endocardial and epicardial borders throughout the cardiac cycle in short-axis cine-MRI slices.
- The algorithm utilized peak gradients along chords perpendicular to a centerline for border detection.
- Validation involved comparing algorithm-derived LV volumes at end-systole (ES) with manual tracings.
Main Results:
- The automated algorithm demonstrated high correlation with manual tracings for both endocardial (r2 = 0.72 - 0.98) and epicardial (r2 = 0.96 - 0.99) LV volumes at ES.
- Favorable agreement was observed across healthy volunteers and patients with dilated cardiomyopathy, left ventricular hypertrophy, or left ventricular aneurysm.
Conclusions:
- The developed automated algorithm provides a reliable and efficient method for LV border tracking and volume calculation from cine-MRI data.
- This automated approach has the potential to improve the accuracy and consistency of cardiac MRI analysis in clinical practice.
Abstract:
The goal of this research was to develop an automated algorithm for tracking the borders of the left ventricle (LV) in a cine-MRI gradient-echo temporal data set. The algorithm was validated on four patient populations: healthy volunteers and patients with dilated cardiomyopathy (DCM), left ventricular hypertrophy (LVH), or left ventricular aneurysm (LVA). A full tomographic set (approximately 11 slices/case) of short-axis images through systole was obtained for each patient. Initial endocardial and epicardial contours for the end-diastolic (ED) and end-systolic (ES) frames were manually traced on the computer by an experienced radiologist. The ED tracings were used as the starting point for the algorithm. The borders were tracked through each phase of the temporal data set, until the ES frame was reached (approximately 7 phases/slice). Peak gradients along equally spaced chords calculated perpendicular to a centerline determined midway between the endocardial and epicardial borders were used for border detection. This approach was tested by comparing the LV epicardial and endocardial volumes calculated at ES to those based on the manual tracings. The results of the algorithm compared favorably with both the endocardial (r2 = 0.72 - 0.98) and epicardial (r2 = 0.96 - 0.99) volumes of the tracer.