Cardiac image segmentation from cine cardiac MRI using graph cuts and shape priors
Related Experiment Video
Updated: May 15, 2026
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
1Department of Computer Science, Swiss Federal Institute of Technology (ETH), CAB F 61.1, Universitätstrasse 6, 8092 Zurich, Switzerland. dmahapatra@gmail.com
Insights
This study introduces a novel graph cut method for segmenting cardiac structures in MRI scans. The approach effectively uses prior shape information to improve segmentation accuracy, outperforming existing methods.
Area of Science:
- Medical Imaging
- Computer Vision
- Cardiology
Background:
- Accurate segmentation of cardiac structures, specifically the left ventricle, right ventricle, and myocardium, is crucial for diagnosing heart conditions using cine cardiac magnetic resonance (CMR) images.
- Existing segmentation methods often struggle with poor edge definition and significant shape variations within and between patients, necessitating improved techniques.
Purpose of the Study:
- To develop and evaluate a novel segmentation method for cardiac structures in CMR images.
- To incorporate prior shape information within a graph cut framework to enhance segmentation accuracy, addressing limitations of existing approaches.
Main Methods:
- A two-stage segmentation approach is proposed, utilizing a graph cut framework.
- The method incorporates prior shape information derived from distance functions and orientation angle histograms, adapted for individual datasets due to interpatient variability.
- A two-stage process involves initial segmentation using intensity information, followed by a second stage combining intensity and shape priors to refine results.
Main Results:
- Experimental results on 30 real patient datasets demonstrate higher segmentation accuracy when shape information is utilized.
- The proposed method shows superior performance compared to other competing segmentation techniques.
- The approach effectively handles challenges posed by poor edge information and significant shape variations.
Conclusions:
- The novel graph cut-based method effectively segments cardiac structures in CMR images by integrating prior shape information.
- The strategy of adapting shape priors to individual datasets addresses interpatient variability, leading to improved accuracy.
- This method offers a robust and accurate solution for cardiac MRI segmentation, outperforming existing approaches.
Abstract:
In this paper, we propose a novel method for segmentation of the left ventricle, right ventricle, and myocardium from cine cardiac magnetic resonance images of the STACOM database. Our method incorporates prior shape information in a graph cut framework to achieve segmentation. Poor edge information and large within-patient shape variation of the different parts necessitates the inclusion of prior shape information. But large interpatient shape variability makes it difficult to have a generalized shape model. Therefore, for every dataset the shape prior is chosen as a single image clearly showing the different parts. Prior shape information is obtained from a combination of distance functions and orientation angle histograms of each pixel relative to the prior shape. To account for shape changes, pixels near the boundary are allowed to change their labels by appropriate formulation of the penalty and smoothness costs. Our method consists of two stages. In the first stage, segmentation is performed using only intensity information which is the starting point for the second stage combining intensity and shape information to get the final segmentation. Experimental results on different subsets of 30 real patient datasets show higher segmentation accuracy in using shape information and our method's superior performance over other competing methods.
