Factors Affecting the Level Set Segmentation of the Heart Ventricles in Short Axis Cardiac Perfusion MRI Images
0
Citation
0
Reference
20
Related Paper
Abstract:
This paper studies the effect of the registration and initialization of the level set segmentation on the performance of the extracting the heart ventricles for perfusion MRI images. Through the registration experiments, the translational transformation was studied based on both the spatial and frequency domain. The frequency domain based registration is mainly established on the phase correlation methodology. As for the segmentation experiments, the level set initialization, was done through extracting the ventricles’ real shape from each slice, using threshold and a combination of morphological operations. Though, the final contour of any frame was used as the initial contour for the next frame. This proposed strategy differs from conventional ones in using the real shape of the ventricles as an initial contour than assuming it as circle or ellipse as in the literature. The second initialization strategy was based on defining the initial contour for each frame using the polar representation of the image. Two short axis view datasets of cardiac magnetic resonance (CMR) perfusion imaging were used in testing the proposed methods. Dice coefficient, sensitivity, specificity and Hausdorff distance have been used to evaluate and validate the segmentation results. The segmentation accuracy for left and right ventricles improved from 72% to 77% and from 70 % to 81% using the spatial domain based registration algorithm. The polar based initialization strategy improves the segmentation accuracy from 77 % to 81% and from 81% to 82% for the left and right ventricles respectively.Keywords:
Initialization
Sørensen–Dice coefficient
Hausdorff distance
Cite
The anatomical and functional cardiac cavities information obtained by Ultrasound images allows a qualitative and quantitative analysis to determine patient's health and detect possible pathologies. Several approaches have been proposed for semiautomatic or fully automatic segmentation. Texture based presegmentation combined with an active contour model have proven to be a promising way to extract cardiac structures from echographic images. In this work a novel procedure for 3D cardiac image segmentation is introduced. A robust pre-processing step that reduces noise and extracts an initial frontier of cardiac structures is combined with an Active Surface Model to obtain final 3D segmentation. Preprocessing is performed by the Mean Shift algorithm that integrates 3D edge confidence map and includes entropy, echoes intensity and spatial information as input features. This procedure locates adequately homogeneous regions in 3D echocardiographic images. The external energy terms included in the Active Surface Model are the 3D edge confidence map and the entropy component obtained by the Mean Shift pre-segmentation. The results demonstrate that the pre-processing provides homogeneous regions and a good initial frontier between blood and myocardium. The Active Surface Model adjusts the initial surface computed by the mean-shift algorithm to the cardiac border. Finally, the obtained results are compared with the experts' manual segmentation and the Tanimoto index between these segmentations is calculated.
Active contour model
Mean-shift
Cite
Citations (3)
The segmentation of left ventricle especially the outer contour is difficult in cardiac Magnetic Resonance Imaging (MRI) analysis. It is affected by imaging mechanism and nearby cardiac apparatus therefore is hard to segment use single tool. A new hybrid model was proposed, first, Anti-Geometric Diffusion model was integrated with Level Set curve involving. This hybrid model makes good use of the advantage of diffusion method, and it can segment the whole contour of left ventricle contour simultaneously based on only one initial curve. Second, this new framework introduces a high efficiency shape and anatomy prior constraints model. The experiments on the cardiac MR images show the Diffusion Level Set can get nice result.
Active contour model
Cite
Citations (0)
In this paper, we develop a new semi-automated segmentation method to cancel the chaotic blood flow signal within the left ventricle (LV) in cardiac magnetic resonance (MR) images with parallel imaging. The segmentation is performed using a deformable model driven by a new external energy based on estimated probability density function (pdf) of the MR signal in the LV. The use of noise distribution through the data allows us both to pull the contour towards the myocardium edges and to ensure the smoothness of the curve. Since data for each slice are acquired with the GRAPPA parallel imaging technique, the spatial segmentation is followed by a temporal propagation to improve the convergence in terms of quality and rapidity. Experiments demonstrate that the proposed model provides better results than those obtained from the standard Active Contour, which should facilitate the use of the method for clinical purposes.
Maxima and minima
Smoothness
Active contour model
Cite
Citations (0)
Active contour model
Initialization
Energy functional
Cite
Citations (9)
This paper proposes a new level set algorithm for left ventricular segmentation based on prior information. First, the improved U-Net network is used for coarse segmentation to obtain pixel-level prior position information. Then, the segmentation result is used as the initial contour of level set for fine segmentation. In the process of curve evolution, based on the shape of the left ventricle, we improve the energy function of the level set and add shape constraints to solve the “burr” and “sag” problems during curve evolution. The proposed algorithm was successfully evaluated on the MICCAI 2009: the mean dice score of the epicardium and endocardium are 92.95% and 94.43%. It is proved that the improved level set algorithm obtains better segmentation results than the original algorithm.
Level set method
Dice
Endocardium
Cite
Citations (0)
The optical flow enables the accurate estimation of cardiac motion. In this research, this tool is exploited to obtain the 2-D segmentation of the left ventricle in a cardiac sequence of magnetic resonance images. The proposed technique consists in taking a manually extracted left ventricle contour corresponding to an instant of the cardiac sequence. Then, the Left Ventricle contour for the next time instant is estimated based on calculation of the optical flow using the Horn and Schunck algorithm. The method is validated using two synthetic image sequences whose velocity field is known. Then, the technique is applied to a 3D magnetic resonance image sequence and it is validated by performing the comparison with respect to the manual segmentation using the Dice coefficient. The results show that the segmentation near the base, the equator and the apex have a Dice coefficient higher than 84%.
Optical Flow
Cardiac Ventricle
Sørensen–Dice coefficient
Cardiac magnetic resonance
Cite
Citations (1)
Maxima and minima
Active contour model
Smoothness
Cite
Citations (5)
Vector flow
Cite
Citations (48)
We develop a semiautomated segmentation method to assist in the analysis of functional pathologies of the left ventricle of the heart. The segmentation is performed using an optimal geodesic active contour with minimal structural knowledge to choose the most likely surfaces of the myocardium. The use of an optimal segmentation algorithm avoids the problems of contour leakage and false minima associated with variational active contour methods. The resulting surfaces may be analysed to obtain quantitative measures of the heart's function. We have applied the proposed segmentation method to multislice MRI data. The results demonstrate the reliability and efficiency of this scheme as well as its robustness to noise and background clutter.
Active contour model
Maxima and minima
Robustness
Cite
Citations (4)
Cut
Connected component
Connected-component labeling
Spline (mechanical)
Cite
Citations (153)