Related Experiment Video
Updated: Feb 16, 2026
11:13
Quantification of Mouse Heart Left Ventricular Function, Myocardial Strain, and Hemodynamic Forces by Cardiovascular Magnetic Resonance Imaging
Published on: May 24, 2021
7.3K
Fast segmentation of the left ventricle in cardiac MRI using dynamic programming
Carlos Santiago1, Jacinto C Nascimento1, Jorge S Marques1
1Institute for Systems and Robotics (ISR/IST), LARSyS, Instituto Superior Técnico, Universidade Lisboa, Portugal.
Computer Methods and Programs in Biomedicine
|December 19, 2017
Summary
This study introduces a fast system for segmenting the left ventricle (LV) in cardiac MRI, significantly reducing manual effort for cardiologists. The automated approach offers rapid and accurate LV segmentation for improved cardiac function analysis.
Area of Science:
- Medical imaging analysis
- Cardiovascular diagnostics
- Computational anatomy
Background:
- Left ventricle (LV) segmentation in cardiac MRI is crucial for assessing cardiac function.
- Manual segmentation is time-consuming and labor-intensive for clinicians.
- Automated methods are needed to improve efficiency and reduce human intervention.
Purpose of the Study:
- To develop and evaluate a fast, automated system for LV segmentation in cardiac MRI.
- To reduce the time and workload associated with manual LV segmentation.
- To provide a tool that aids cardiologists in cardiac function analysis.
Main Methods:
- A dynamic programming approach was employed to delineate the LV border.
- The system utilizes simplified assumptions regarding segmentation shape and location.
- Evaluation was conducted on two public datasets comprising 660 and 90 cardiac MRI volumes.
Main Results:
- The system achieves segmentation of an entire cardiac MRI volume in just 1.5 seconds.
- High accuracy was demonstrated with an average Dice similarity coefficient of 86.0%.
- Low spatial error was observed, with an average perpendicular distance of 2.4 mm.
Conclusions:
- A novel, rapid system for left ventricle segmentation in cardiac MRI has been developed.
- This automated framework significantly decreases the time and effort required from cardiologists.
- The proposed system offers a promising solution for efficient and accurate cardiac MRI analysis.
