Automatic Segmentation Of Left Ventricle Research Articles

Automatic left ventricle segmentation in short-axis MRI using deep convolutional neural networks and central-line guided level set approach

In the clinical diagnosis of cardiovascular diseases, left ventricle (LV) segmentation in cardiac magnetic resonance images (MRI) is an indispensable procedure for doctors. To reduce the time needed for diagnosis, we develop an automatic LV segmentation method by integrating the convolutional neural network (CNN) with the level set approach. Firstly, a CNN based myocardial central-line detection algorithm was proposed to replace the manual initialization process for traditional level set approaches. Secondly, we present a novel central-line guided level set approach (CGLS) for delineating the myocardium region. In particular, we incorporate the myocardial central-line into the level set energy formulation as a constraint term. It plays two important roles in the iterative process: restricting the zero-level contour to stay around the myocardial central-line and preserving the anatomical geometry of myocardium segmentation result. In experiments, our method yields results as below: (1) 1.74 mm and 2.06 mm in terms of epicardium and endocardium perpendicular distance on MICCAI 2009 dataset, (2) 0.955 and 0.853 in terms of LV and myocardium Dice metric at the end-diastole on ACDC MICCAI 2017 dataset. The experimental data demonstrate that our method outperforms some state-of-the-art methods and achieves a good agreement with the manual segmentation results.

MFP-Unet: A novel deep learning based approach for left ventricle segmentation in echocardiography

Segmentation of the Left ventricle (LV) is a crucial step for quantitative measurements such as area, volume, and ejection fraction. However, the automatic LV segmentation in 2D echocardiographic images is a challenging task due to ill-defined borders, and operator dependence issues (insufficient reproducibility). U-net, which is a well-known architecture in medical image segmentation, addressed this problem through an encoder-decoder path. Despite outstanding overall performance, U-net ignores the contribution of all semantic strengths in the segmentation procedure. In the present study, we have proposed a novel architecture to tackle this drawback. Feature maps in all levels of the decoder path of U-net are concatenated, their depths are equalized, and up-sampled to a fixed dimension. This stack of feature maps would be the input of the semantic segmentation layer. The performance of the proposed model was evaluated using two sets of echocardiographic images: one public dataset and one prepared dataset. The proposed network yielded significantly improved results when comparing with results from U-net, dilated U-net, Unet++, ACNN, SHG, and deeplabv3. An average Dice Metric (DM) of 0.953, Hausdorff Distance (HD) of 3.49, and Mean Absolute Distance (MAD) of 1.12 are achieved in the public dataset. The correlation graph, bland-altman analysis, and box plot showed a great agreement between automatic and manually calculated volume, area, and length.

Dynamic pixel-wise weighting-based fully convolutional neural networks for left ventricle segmentation in short-axis MRI

Left ventricle (LV) segmentation in cardiac MRI is an essential procedure for quantitative diagnosis of various cardiovascular diseases. In this paper, we present a novel fully automatic left ventricle segmentation approach based on convolutional neural networks. The proposed network fully takes advantages of the hierarchical architecture and integrate the multi-scale feature together for segmenting the myocardial region of LV. Moreover, we put forward a dynamic pixel-wise weighting strategy, which can dynamically adjust the weight of each pixel according to the segmentation accuracy of upper layer and force the pixel classifier to take more attention on the misclassified ones. By this way, the LV segmentation performance of our method can be improved a lot especially for the apical and basal slices in cine MR images. The experiments on the CAP database demonstrate that our method achieves a substantial improvement compared with other well-know deep learning methods. Beside these, we discussed two major limitations in convolutional neural networks-based semantic segmentation methods for LV segmentation.

Automatic aorta and left ventricle segmentation for TAVI procedure planning using convolutional neural networks.

Transcatheter aortic valve implantation (TAVI) is a minimally invasive procedure which is performed on patients with aortic valve defects that are posing a high-risk for conducting a surgical treatment. Preoperative surgical planning and valve sizing play a crucial role in reducing surgery complications and adverse effects such as paravalvular leakage or stroke. Planning process incorporates performing measurements, detecting landmarks and visualizing relevant structures in 3D. To automatize this process, a segmentation is required. Due to the lack of methods enabling parallel aorta and left ventricle segmentation we propose a fully automatic neural network approach based on 2D U-Net architecture. Convolutional neural network architecture was trained on 44 studies (22 raw CTA datasets and 22 elastic deformed scans) and tested on another 18 stacks of data. During every epoch of network learning process cross validation was performed on 8 stacks. As a result, we achieve 0.95 mean Dice coefficient score with standard deviation 0.02 determining high precision of predicted aorta and left ventricle label maps.

Automatic segmentation of left ventricle from cardiac MRI via deep learning and region constrained dynamic programming

Segmentation of the left ventricle from cardiac magnetic resonance images (MRI) is an essential step to quantitatively analyze global and regional cardiac function. The aim of this study is to develop a novel and robust algorithm which can improve the accuracy of automatic left ventricle segmentation on short-axis cardiac MRI. The database used in this study are 900 cardiac MRI cases from Hubei Cancer Hospital. Three key techniques are developed in this segmentation algorithm: (1) deep learning schema is designed for coarse segmentation of LV (left ventricle) myocardial images, (2) trimmed mean approach is employed to build a proper region for epicardial contour searching, and (3) an edge map with non-maxima gradient suppression approach is put forward to improve the dynamic programming to derive the epicardial boundary. The accuracy of cardiac boundaries and cardiac functional parameters are benchmarked against those derived from expert manual boundary delineations and derived measurements on 900 samples of Hubei Cancer Hospital. The average Jaccard (overlap) indexes for endo and epicardial contours are 0.80 and 0.76. Bland-Altman analysis for LVEDV (LV End-diastolic Volume), LVESV (LV End-systolic Volume), LVSV (LV 232 Stroke volume), LVEF (LV Ejection Fraction), LVM-DP (LV mass in diastolic phase) and LVM-SP (LV mass in systolic phase), yielded biases of 4.15 ml, 0.26 ml, 3.89 ml, 0.32%, −7.24 g and -0.08 g, respectively, and limits of agreement of ±30.32 ml, ±11.10 ml, ±24.31 ml, ±12.89%, ±24.66 g and ±21.93 g, respectively. Our hybrid scheme combining deep learning and dynamic programming for automatic segmentation of the LV from cardiac MRI datasets is effective and robust and can compute LV functional indexes from population imaging.

An Automatic Left Ventricle Segmentation on Echocardiogram Exams via Morphological Geodesic Active Contour with Adaptive External Energy

This work proposes a new adaptive approach to left ventricle segmentation based on a non-parametric adaptive active contour method called Fast Morphological Geodesic Active Contour (FGAC) combined with adaptive external energy via deep learning model. The evaluation methodology considered echocardiogram exams obtained from volunteers. Beyond the manual segmentations made by two specialists medical as ground truth. The new approach is compared with three other segmentation methods, also based on the active contour method: pSnakes, radial snakes with derivative (RSD), and radial snakes with Hilbert energy (RSH). The FGAC combined with adaptive external energy showed better Precision (99.53%, 99.72%) against RSD (99.46%, 99.68%), RSH (99.51%, 99.71%) and pSnakes (99.52%, 99.72%). Besides, it achieved a relevant Jaccard similarity index (67.40%, 62.02%), and promising accuracy (98.64%, 98.46%). Even though the metrics differences are low, the proposed approach is fully automatic. Therefore, these results suggest the potential of the proposed approach to aid medical diagnosis systems in echocardiology.

A Combined Fully Convolutional Networks and Deformable Model for Automatic Left Ventricle Segmentation Based on 3D Echocardiography.

Segmentation of the left ventricle (LV) from three-dimensional echocardiography (3DE) plays a key role in the clinical diagnosis of the LV function. In this work, we proposed a new automatic method for the segmentation of LV, based on the fully convolutional networks (FCN) and deformable model. This method implemented a coarse-to-fine framework. Firstly, a new deep fusion network based on feature fusion and transfer learning, combining the residual modules, was proposed to achieve coarse segmentation of LV on 3DE. Secondly, we proposed a method of geometrical model initialization for a deformable model based on the results of coarse segmentation. Thirdly, the deformable model was implemented to further optimize the segmentation results with a regularization item to avoid the leakage between left atria and left ventricle to achieve the goal of fine segmentation of LV. Numerical experiments have demonstrated that the proposed method outperforms the state-of-the-art methods on the challenging CETUS benchmark in the segmentation accuracy and has a potential for practical applications.

Neural multi-atlas label fusion: Application to cardiac MR images.

Multi-atlas segmentation approach is one of the most widely-used image segmentation techniques in biomedical applications. There are two major challenges in this category of methods, i.e., atlas selection and label fusion. In this paper, we propose a novel multi-atlas segmentation method that formulates multi-atlas segmentation in a deep learning framework for better solving these challenges. The proposed method, dubbed deep fusion net (DFN), is a deep architecture that integrates a feature extraction subnet and a non-local patch-based label fusion (NL-PLF) subnet in a single network. The network parameters are learned by end-to-end training for automatically learning deep features that enable optimal performance in a NL-PLF framework. The learned deep features are further utilized in defining a similarity measure for atlas selection. By evaluating on two public cardiac MR datasets of SATA-13 and LV-09 for left ventricle segmentation, our approach achieved 0.833 in averaged Dice metric (ADM) on SATA-13 dataset and 0.95 in ADM for epicardium segmentation on LV-09 dataset, comparing favorably with the other automatic left ventricle segmentation methods. We also tested our approach on Cardiac Atlas Project (CAP) testing set of MICCAI 2013 SATA Segmentation Challenge, and our method achieved 0.815 in ADM, ranking highest at the time of writing.

Left ventricle segmentation in echocardiography based on adaptive mean shift

The use of echocardiography ventricle segmentation can obtain ventricular volume parameters, and it is helpful to evaluate cardiac function. However, the ultrasound images have the characteristics of high noise and difficulty in segmentation, bringing huge workload to segment the object region manually. Meanwhile, the automatic segmentation technology cannot guarantee the segmentation accuracy. In order to solve this problem, a novel algorithm framework is proposed to segment the ventricle. Firstly, faster region-based convolutional neural network is used to locate the object to get the region of interest. Secondly, K-means is used to pre-segment the image; then a mean shift with adaptive bandwidth of kernel function is proposed to segment the region of interest. Finally, the region growing algorithm is used to get the object region. By this framework, ventricle is obtained automatically without manual localization. Experiments prove that this framework can segment the object accurately, and the algorithm of adaptive mean shift is more stable and accurate than the mean shift with fixed bandwidth on quantitative evaluation. These results show that the method in this paper is helpful for automatic segmentation of left ventricle in echocardiography.

Deep convolutional neural networks for automatic segmentation of left ventricle cavity from cardiac magnetic resonance images

This work conducts a feasibility study of deep learning approaches for automatic segmentation of left ventricle (LV) cavity from cardiac magnetic resonance (CMR) images. Automatic LV cavity segmentation is a challenging task, partially due to the small size of the object as compared to the large CMR image background, especially at the apex. To cater for small object segmentation, the authors present a localisation‐segmentation framework, to first locate the object in the large full image, then segment the object within the small cropped region of interest. The localisation is performed by a deep regression model based on convolutional neural networks, while the segmentation is done by the deep neural networks based on U‐Net architecture. They also employ the Dice loss function for the training process of the segmentation models, to investigate its effects on the segmentation performance. The deep learning models are trained and evaluated by using public endocardium‐annotated CMR datasets from York University and MICCAI 2009 LV Challenge websites. The average dice metric values of the authors’ proposed framework are 0.91 and 0.93, respectively, on these two databases. These results are promising as compared to the best results achieved by the current state‐of‐art, which shows the potentials of deep learning approaches for this particular application.

Segmentation of the left ventricle in cardiac MRI using a hierarchical extreme learning machine model

Segmentation of the left ventricle (LV) from cardiac magnetic resonance imaging (MRI) images is an essential step for calculation of clinical indices such as stroke volume, ejection fraction. In this paper, a new automatic LV segmentation method combines a Hierarchical Extreme Learning Machine (H-ELM) and a new location method is developed. An H-ELM can achieve more compact and meaningful feature representations and learn the segmentation task from the ground truth. A new automatic LV location method is integrated to improve the accuracy of classification and reduce the cost of segmentation. Experimental results (including 30 cases, 10 cases for training, 20 cases for testing) show that the mean absolute deviation of images segmented by our proposed method is about 67.9, 81.3 and 98.7% of those images segmented by the level set, the SVM and Hu’s method, respectively. The mean maximum absolute deviation of images segmented by our proposed method is about 63.5, 77.3 and 98.0% of those images segmented by the level set, the SVM and Hu’s method, respectively. The mean dice similarity coefficient of images segmented by our proposed method is about 13.7, 9.3 and 0.5% higher than that of those images segmented by the level set, the SVM and Hu’s method, respectively. The mean speed of our proposed method is about 38.3, 6.7 and 23.8 times faster than that of the level set, the SVM and Hu’s method, respectively. The standard deviation of our proposed method is the lowest among four methods. The results validate that our proposed method is efficient and satisfactory for the LV segmentation.

Fully automatic segmentation of left ventricular anatomy in 3-D LGE-MRI

The current challenge for electrophysiology procedures, targeting the left ventricle, is the localization and qualification of myocardial scar. Late gadolinium enhanced magnetic resonance imaging (LGE-MRI) is the current gold standard to visualize regions of myocardial infarction. Commonly, a stack of 2-D images is acquired of the left ventricle in short-axis orientation. Recently, 3-D LGE-MRI methods were proposed that continuously cover the whole heart with a high resolution within a single acquisition. The acquisition promises an accurate quantification of the myocardium to the extent of myocardial scarring. The major challenge arises in the analysis of the resulting images, as the accurate segmentation of the myocardium is a requirement for a precise scar tissue quantification. In this work, we propose a novel approach for fully automatic left ventricle segmentation in 3-D whole-heart LGE-MRI, to address this limitation. First, a two-step registration is performed to initialize the left ventricle. In the next step, the principal components are computed and a pseudo short axis view of the left ventricle is estimated. The refinement of the endocardium and epicardium is performed in polar space. Prior knowledge for shape and inter-slice smoothness is used during segmentation. The proposed method was evaluated on 30 clinical 3-D LGE-MRI datasets from individual patients obtained at two different clinical sites and were compared to gold standard segmentations of two clinical experts. This comparison resulted in a Dice coefficient of 0.83 for the endocardium and 0.80 for the epicardium.

Automatic segmentation and quantification of the cardiac structures from non-contrast-enhanced cardiac CT scans

Early structural changes to the heart, including the chambers and the coronary arteries, provide important information on pre-clinical heart disease like cardiac failure. Currently, contrast-enhanced cardiac computed tomography angiography (CCTA) is the preferred modality for the visualization of the cardiac chambers and the coronaries. In clinical practice not every patient undergoes a CCTA scan; many patients receive only a non-contrast-enhanced calcium scoring CT scan (CTCS), which has less radiation dose and does not require the administration of contrast agent. Quantifying cardiac structures in such images is challenging, as they lack the contrast present in CCTA scans. Such quantification would however be relevant, as it enables population based studies with only a CTCS scan. The purpose of this work is therefore to investigate the feasibility of automatic segmentation and quantification of cardiac structures viz whole heart, left atrium, left ventricle, right atrium, right ventricle and aortic root from CTCS scans. A fully automatic multi-atlas-based segmentation approach is used to segment the cardiac structures. Results show that the segmentation overlap between the automatic method and that of the reference standard have a Dice similarity coefficient of 0.91 on average for the cardiac chambers. The mean surface-to-surface distance error over all the cardiac structures is mm. The automatically obtained cardiac chamber volumes using the CTCS scans have an excellent correlation when compared to the volumes in corresponding CCTA scans, a Pearson correlation coefficient (R) of 0.95 is obtained. Our fully automatic method enables large-scale assessment of cardiac structures on non-contrast-enhanced CT scans.

Segmentation of MRI Volume Data Based on Clustering Method

Here we analyze the difficulties of segmentation without tag line of left ventricle MR images, and propose an algorithm for automatic segmentation of left ventricle (LV) internal and external profiles. Herein, we propose an Incomplete K-means and Category Optimization (IKCO) method. Initially, using Hough transformation to automatically locate initial contour of the LV, the algorithm uses a simple approach to complete data subsampling and initial center determination. Next, according to the clustering rules, the proposed algorithm finishes MR image segmentation. Finally, the algorithm uses a category optimization method to improve segmentation results. Experiments show that the algorithm provides good segmentation results.

Myocardial Iron Loading Assessment by Automatic Left Ventricle Segmentation with Morphological Operations and Geodesic Active Contour on T2* images.

Myocardial iron loading thalassemia patients could be identified using T2* magnetic resonance images (MRI). To quantitatively assess cardiac iron loading, we proposed an effective algorithm to segment aligned free induction decay sequential myocardium images based on morphological operations and geodesic active contour (GAC). Nine patients with thalassemia major were recruited (10 male and 16 female) to undergo a thoracic MRI scan in the short axis view. Free induction decay images were registered for T2* mapping. The GAC were utilized to segment aligned MR images with a robust initialization. Segmented myocardium regions were divided into sectors for a region-based quantification of cardiac iron loading. Our proposed automatic segmentation approach achieve a true positive rate at 84.6% and false positive rate at 53.8%. The area difference between manual and automatic segmentation was 25.5% after 1000 iterations. Results from T2* analysis indicated that regions with intensity lower than 20 ms were suffered from heavy iron loading in thalassemia major patients. The proposed method benefited from abundant edge information of the free induction decay sequential MRI. Experiment results demonstrated that the proposed method is feasible in myocardium segmentation and was clinically applicable to measure myocardium iron loading.

Left ventricle segmentation in MRI via convex relaxed distribution matching

A fundamental step in the diagnosis of cardiovascular diseases, automatic left ventricle (LV) segmentation in cardiac magnetic resonance images (MRIs) is still acknowledged to be a difficult problem. Most of the existing algorithms require either extensive training or intensive user inputs. This study investigates fast detection of the left ventricle (LV) endo- and epicardium surfaces in cardiac MRI via convex relaxation and distribution matching. The algorithm requires a single subject for training and a very simple user input, which amounts to a single point (mouse click) per target region (cavity or myocardium). It seeks cavity and myocardium regions within each 3D phase by optimizing two functionals, each containing two distribution-matching constraints: (1) a distance-based shape prior and (2) an intensity prior. Based on a global measure of similarity between distributions, the shape prior is intrinsically invariant with respect to translation and rotation. We further introduce a scale variable from which we derive a fixed-point equation (FPE), thereby achieving scale-invariance with only few fast computations. The proposed algorithm relaxes the need for costly pose estimation (or registration) procedures and large training sets, and can tolerate shape deformations, unlike template (or atlas) based priors. Our formulation leads to a challenging problem, which is not directly amenable to convex-optimization techniques. For each functional, we split the problem into a sequence of sub-problems, each of which can be solved exactly and globally via a convex relaxation and the augmented Lagrangian method. Unlike related graph-cut approaches, the proposed convex-relaxation solution can be parallelized to reduce substantially the computational time for 3D domains (or higher), extends directly to high dimensions, and does not have the grid-bias problem. Our parallelized implementation on a graphics processing unit (GPU) demonstrates that the proposed algorithm requires about 3.87 s for a typical cardiac MRI volume, a speed-up of about five times compared to a standard implementation. We report a performance evaluation over 400 volumes acquired from 20 subjects, which shows that the obtained 3D surfaces correlate with independent manual delineations. We further demonstrate experimentally that (1) the performance of the algorithm is not significantly affected by the choice of the training subject and (2) the shape description we use does not change significantly from one subject to another. These results support the fact that a single subject is sufficient for training the proposed algorithm.

Automatic segmentation of left ventricle in 3D echocardiography using a level set approach

Automatic segmentation of left ventricle in 3D echocardiography using a level set approach

Hybrid segmentation of left ventricle in cardiac MRI using gaussian-mixture model and region restricted dynamic programming

Segmentation of the left ventricle from cardiac magnetic resonance images (MRI) is very important to quantitatively analyze global and regional cardiac function. The aim of this study is to develop a novel and robust algorithm which can improve the accuracy of automatic left ventricle segmentation on short-axis cardiac MRI. The database used in this study consists of three data sets obtained from the Sunnybrook Health Sciences Centre. Each data set contains 15 cases (4 ischemic heart failures, 4 non-ischemic heart failures, 4 left ventricle (LV) hypertrophies and 3 normal cases). Three key techniques are developed in this segmentation algorithm: (1) ray scanning approach is designed for segmentation of images with left ventricular outflow tract (LVOT), (2) a region restricted technique is employed for epicardial contour extraction, and (3) an edge map with non-maxima gradient suppression approach is put forward to improve the dynamic programming to derive the epicardial boundary. The validation experiments were 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 91%, the average perpendicular distance is about 2mm. The overlapping dice metric is about 0.92. The regression and determination coefficient between the experts and our proposed method on the ejection fraction (EF) is 1.01 and 0.9375, respectively; they are 0.9 and 0.8245 for LV mass. The proposed segmentation method shows the better performance and is very promising in improving the accuracy of computer-aided diagnosis systems in cardiovascular diseases.

Automatic left ventricle segmentation in volumetric SPECT data set by variational level set

Left ventricle (LV) quantification in nuclear medicine images is a challenging task for myocardial perfusion scintigraphy. A hybrid method for left ventricle myocardial border extraction in SPECT datasets was developed and tested to automate LV ventriculography. Automatic segmentation of the LV in volumetric SPECT data was implemented using a variational level set algorithm. The method consists of two steps: (1) initialization and (2) segmentation. Initially, we estimate the initial closed curves in SPECT images using adaptive thresholding and morphological operations. Next, we employ the initial closed curves to estimate the final contour by variational level set. The performance of the proposed approach was evaluated by comparing manually obtained boundaries with automated segmentation contours in 10 SPECT data sets obtained from adult patients. Segmented images by proposed methods were visually compared with manually outlined contours and the performance was evaluated using ROC analysis. The proposed method and a traditional level set method were compared by computing the sensitivity and specificity of ventricular outlines as well as ROC analysis. The results show that the proposed method can effectively segment LV regions with a sensitivity and specificity of 88.9 and 96.8%, respectively. Experimental results demonstrate the effectiveness and reasonable robustness of the automatic method. A new variational level set technique was able to automatically trace the LV contour in cardiac SPECT data sets, based on the characteristics of the overall region of LV images. Smooth and accurate LV contours were extracted using this new method, reducing the influence of nearby interfering structures including a hypertrophied right ventricle, hepatic or intestinal activity, and pulmonary or intramammary activity.

Automatic Left Ventricle Segmentation in Cardiac MRI Using Topological Stable-State Thresholding and Region Restricted Dynamic Programming

Segmentation of the left ventricle (LV) is very important in the assessment of cardiac functional parameters. The aim of this study is to develop a novel and robust algorithm which can improve the accuracy of automatic LV segmentation on short-axis cardiac magnetic resonance images (MRI). The database used in this study consists of 45 cases obtained from the Sunnybrook Health Sciences Centre. The 45 cases contain 12 ischemic heart failures, 12 non-ischemic heart failures, 12 LV hypertrophies, and 9 normal cases. Three key techniques are developed in this segmentation algorithm: 1) topological stable-state thresholding method is proposed to refine the endocardial contour, 2) an edge map with non-maxima gradient suppression approach, and 3) a region-restricted technique that is proposed to improve the dynamic programming to derive the epicardial boundary. The validation experiments were performed on a pool of data sets of 45 cases. For both endo- and epicardial contours of our results, percentage of good contours is about 91%, the average perpendicular distance is about 2 mm, and the overlapping dice metric is about 0.91. The regression and determination coefficient for the experts and our proposed method on the ejection fraction is 1.05 and 0.9048, respectively; they are 0.98 and 0.8221 for LV mass. An automatic method using topological stable-state thresholding and region restricted dynamic programming has been proposed to segment left ventricle in short-axis cardiac MRI. Evaluation results indicate that the proposed segmentation method can improve the accuracy and robust of left ventricle segmentation. The proposed segmentation approach shows the better performance and has great potential in improving the accuracy of computer-aided diagnosis systems in cardiovascular diseases.