Related Experiment Video
Updated: May 14, 2026
07:21
Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking
Published on: February 12, 2011
Regional heart motion abnormality detection: an information theoretic approach
Kumaradevan Punithakumar1, Ismail Ben Ayed, Ali Islam
1Servier Virtual Cardiac Centre, Department of Radiology & Diagnostic Imaging, University of Alberta, Edmonton, AB, Canada. punithak@ualberta.ca
Medical Image Analysis
|February 5, 2013
Summary
This study introduces an advanced unscented Kalman smoother and a naive Bayes classifier to accurately detect regional heart motion abnormalities from noisy cardiac MRI data. The method significantly improves diagnostic accuracy for cardiovascular diseases.
Area of Science:
- Cardiovascular Imaging and Diagnostics
- Biomedical Signal Processing
- Medical Image Analysis
Background:
- Accurate tracking of regional heart motion is crucial for diagnosing cardiovascular diseases.
- Analysis of myocardial motion from functional images is challenging due to noise and inaccuracies.
- Incorporating prior knowledge is essential to improve the accuracy of heart motion analysis.
Purpose of the Study:
- To develop and evaluate a novel method for detecting and classifying regional heart motion abnormalities using magnetic resonance imaging (MRI).
- To enhance the accuracy of myocardial motion estimation in the presence of noise and model uncertainties.
- To automatically identify abnormal functional regions within the myocardium.
Main Methods:
- An unscented Kalman smoother was employed to estimate myocardial points from noisy data using a nonlinear dynamic model.
- Shannon's differential entropy was utilized to analyze feature distributions for detecting and locating abnormalities.
- A naive Bayes classifier was constructed based on differential entropy features for automatic abnormality detection.
Main Results:
- The proposed method achieved high classification accuracy: 86.5% (base), 89.4% (mid-cavity), and 84.5% (apex), with an overall accuracy of 87.1%.
- Performance was quantitatively evaluated against radiologist ground truth on 928 myocardial segments from 174 MRI cines.
- The algorithm demonstrated superior performance compared to other recent methods, yielding a kappa statistic of 0.73 against visual scoring.
Conclusions:
- The proposed unscented Kalman smoother and naive Bayes classifier effectively detect and classify regional heart motion abnormalities from cardiac MRI.
- This approach offers a significant improvement in accuracy for diagnosing cardiovascular conditions based on myocardial motion analysis.
- The method shows strong agreement with expert visual assessment, indicating its clinical potential for automated cardiac diagnostics.
Related Concept Videos
01:25Correlation between ECG and Cardiac Cycle
The electrical signals recorded on an electrocardiogram (ECG) occur before the mechanical processes of contraction and relaxation during the cardiac cycle.
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...
01:13Location and Orientation of the Heart
The human heart, despite its modest size and weight, is an organ of remarkable strength and endurance. Roughly the size of a fist, the heart weighs between 250 and 350 grams and is nestled within the mediastinum, the medial cavity of the thorax. It extends obliquely for about 12 to 14 cm, resting on the superior surface of the diaphragm. The heart is positioned anterior to the vertebral column and posterior to the sternum, with two-thirds of its mass lying to the left of the midsternal line.