Endocardial Border Detection in Cardiac Magnetic Resonance Images Using Level Set Method

Biomedical Engineering Laboratory, University of Tlemcen Algeria, Tlemcen, Algeria.
Journal of Digital Imaging (Impact Factor: 1.19). 07/2011; 25(2):294-306. DOI: 10.1007/s10278-011-9404-z
Source: PubMed


Segmentation of the left ventricle in MRI images is a task with important diagnostic power. Currently, the evaluation of cardiac function involves the global measurement of volumes and ejection fraction. This evaluation requires the segmentation of the left ventricle contour. In this paper, we propose a new method for automatic detection of the endocardial border in cardiac magnetic resonance images, by using a level set segmentation-based approach. To initialize this level set segmentation algorithm, we propose to threshold the original image and to use the binary image obtained as initial mask for the level set segmentation method. For the localization of the left ventricular cavity, used to pose the initial binary mask, we propose an automatic approach to detect this spatial position by the evaluation of a metric indicating object's roundness. The segmentation process starts by the initialization of the level set algorithm and ended up through a level set segmentation. The validation process is achieved by comparing the segmentation results, obtained by the automated proposed segmentation process, to manual contours traced by tow experts. The database used was containing one automated and two manual segmentations for each sequence of images. This comparison showed good results with an overall average similarity area of 97.89%.

Download full-text


Available from: Mohammed Amine Chikh, Jun 03, 2014
1 Follower
38 Reads
  • [Show abstract] [Hide abstract]
    ABSTRACT: Curve of left ventricular (LV) volume changes throughout the cardiac cycle is a fundamental parameter for clinical evaluation of various cardiovascular diseases. Currently, this evaluation is often performed manually which is tedious and time consuming and suffers from significant interobserver and intraobserver variability. This paper introduces a new automatic method, based on nonlinear dimensionality reduction (NLDR) for extracting the curve of the LV volume changes over a cardiac cycle from two-dimensional (2-D) echocardiography images. Isometric feature mapping (Isomap) is one of the most popular NLDR algorithms. In this study, a modified version of Isomap algorithm, where image to image distance metric is computed using nonrigid registration, is applied on 2-D echocardiography images of one cycle of heart. Using this approach, the nonlinear information of these images is embedded in a 2-D manifold and each image is characterized by a symbol on the constructed manifold. This new representation visualizes the relationship between these images based on LV volume changes and allows extracting the curve of the LV volume changes automatically. Our method in comparison to the traditional segmentation algorithms does not need any LV myocardial segmentation and tracking, particularly difficult in the echocardiography images. Moreover, a large data set under various diseases for training is not required. The results obtained by our method are quantitatively evaluated to those obtained manually by the highly experienced echocardiographer on ten healthy volunteers and six patients which depict the usefulness of the presented method.
    Journal of Digital Imaging 07/2014; 28(1). DOI:10.1007/s10278-014-9722-z · 1.19 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Segmentation of the left ventricle is very important to quantitatively analyze global and regional cardiac function from magnetic resonance. The aim of this study is to develop a novel algorithm for segmenting left ventricle on short-axis cardiac magnetic resonance images (MRI) to improve the performance of computer-aided diagnosis (CAD) systems. In this research, an automatic segmentation method for left ventricle is proposed on the basis of local binary fitting (LBF) model and dynamic programming techniques. The validation experiments are performed on a pool of data sets of 45 cases. For both endo- and epi-cardial contours of our results, percentage of good contours is about 93.5%, the average perpendicular distance are about 2 mm. The overlapping dice metric is about 0.91. The regression and determination coefficient between the experts and our proposed method on the LV mass is 1.038 and 0.9033, respectively; they are 1.076 and 0.9386 for ejection fraction (EF). The proposed segmentation method shows the better performance and has great potential in improving the accuracy of computer-aided diagnosis systems in cardiovascular diseases.
    PLoS ONE 12/2014; 9(12):e114760. DOI:10.1371/journal.pone.0114760 · 3.23 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Automatic segmentation of medical cardiac images is one of the most important tasks used for early diagnosis of cardiac diseases, since its permits rapid and correct delimitation of cardiac structures. This operation allows achieving efficient analysis of the contractile heart function, which is the main criterion used to determine the prognostic of different cardiopathies. In this paper, we propose a new method for right ventricle automatic segmentation in cardiac magnetic resonance images by using an Active Shape Model (ASM) based segmentation approach. This method requires an initialization near to the actual contour in order to reach a good detection. The pose of the initial shape is a crucial step for such segmentation by deformable models. To do this, we propose in this work a new automatic initialization method, ideally close to the right ventricle, by using a Generalized Hough Transform (GHT) approach. In addition, we propose to use a distance transform in order to optimize the convergence of the model used for the ASM segmentation allowing a better accuracy of the right ventricle detection. To this aim, this distance transform information is computed and integrated to the segmentation process, so that it constraints the evolution of the model. Finally, quantitative evaluation was performed on a dataset composed of 60 subjects with a comparison to ground truth (manual segmentation). This comparison showed an overall average similarity area of 99.55% and a mean error of 2.15 ± 0.36 mm comparing favorably with published work. The results are encouraging and show that the proposed segmentation approach reaches more accurately the border of the right ventricle compared to the classic ASM based method.
    Journal of Medical Imaging and Health Informatics 02/2015; 5(1). DOI:10.1166/jmihi.2015.1353 · 0.50 Impact Factor