Myocardium segmentation in Strain-Encoded (SENC) magnetic resonance images using graph-cuts

• Published in: IET image processing Vol. 7; no. 5; pp. 415 - 422
• Main Authors: Al-Agamy, Ahmed O, Osman, Nael F, Fahmy, Ahmed S
• Format: Journal Article
• Language: English
• Published: Stevenage The Institution of Engineering and Technology 01.07.2013; Institution of Engineering and Technology; The Institution of Engineering & Technology
• Subjects: Algorithms; Applied sciences; Biological and medical sciences; biomedical MRI; cardiology; Computerized, statistical medical data processing and models in biomedicine; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; graph‐cut optimisation algorithm; heart function; image coding; Image processing; image segmentation; Imaging; Information, signal and communications theory; left ventricles; Magnetic resonance; Mathematical models; medical image processing; Medical management aid. Diagnosis aid; Medical sciences; MRI; muscle; myocardial wall motion abnormality; Myocardium; myocardium borders; myocardium segmentation; optimisation; Pattern recognition; probability; right ventricles; Segmentation; Segments; SENC; Signal and communications theory; signal probabilistic model; Signal processing; Signal, noise; signal‐to‐noise ratio; skeletonisation algorithm; strain‐encoded magnetic resonance images; Telecommunications and information theory; biomedical MRI; SENC; heart function; MRI; myocardium borders; probability; right ventricles; cardiology; myocardial wall motion abnormality; optimisation; left ventricles; signal probabilistic model; image segmentation; myocardium segmentation; muscle; signal-to-noise ratio; image coding; skeletonisation algorithm; medical image processing; graph-cut optimisation algorithm; strain-encoded magnetic resonance images; Performance evaluation; Histogram; Image processing; Probabilistic approach; Motion estimation; Pattern recognition; Shape detection; Algorithm; Nuclear magnetic resonance imaging; Optimization; Image segmentation; Graph cut; Imaging; Signal processing; Cost function; Medical imagery; Probabilistic model; Edge detection; Signal to noise ratio
• ISSN: 1751-9659; 1751-9667; 1751-9667
• DOI: 10.1049/iet-ipr.2012.0513

Evaluation of cardiac functions using Strain Encoded (SENC) magnetic resonance (MR) imaging is a powerful tool for imaging the deformation of left and right ventricles. However, automated analysis of SENC images is hindered due to the low signal-to-noise ratio SENC images. In this work, the authors propose a method to segment the left and right ventricles myocardium simultaneously in SENC-MR short-axis images. In addition, myocardium seed points are automatically selected using skeletonisation algorithm and used as hard constraints for the graph-cut optimization algorithm. The method is based on a modified formulation of the graph-cuts energy term. In the new formulation, a signal probabilistic model is used, rather than the image histogram, to capture the characteristics of the blood and tissue signals and include it in the cost function of the graph-cuts algorithm. The method is applied to SENC datasets for 11 human subjects (five normal and six patients with known myocardial wall motion abnormality). The segmentation results of the proposed method are compared with those resulting from both manual segmentation and the conventional histogram-based graph-cuts segmentation algorithm. The results show that the proposed method outperforms the histogram-based graph-cuts algorithm especially to segment the thin structure of the right ventricle.