Automatic segmentation of left ventricle using parallel end–end deep convolutional neural networks framework

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

Automatic segmentation of left ventricle (LV) myocardium in cardiac short-axis cine MR images acquired on subjects with myocardial infarction is a challenging task, mainly because of the various types of image inhomogeneity caused by the infarctions. Among the approaches proposed to automate the LV myocardium segmentation task, methods based upon deep convolutional neural networks (CNN) have demonstrated their exceptional accuracy and robustness in recent years. However, most of the CNN-based approaches treat the frames in a cardiac cycle independently, which fails to capture the valuable dynamics of heart motion. Herein, an approach based on recurrent neural network (RNN), specifically a multi-level convolutional long short-term memory (ConvLSTM) model, is proposed to take the motion of the heart into consideration. Based on a ResNet-56 CNN, LV-related image features in consecutive frames of a cardiac cycle are extracted at both the low- and highresolution levels, which are processed by the corresponding multi-level ConvLSTM models to generate the myocardium segmentations. A leave-one-out experiment was carried out on a set of 3,600 cardiac cine MR slices collected in-house for 8 porcine subjects with surgically induced myocardial infarction. Compared with a solely CNN-based approach, the proposed approach demonstrated its superior robustness against image inhomogeneity by incorporating information from adjacent frames. It also outperformed a one-level ConvLSTM approach thanks to its capabilities to take advantage of image features at multiple resolution levels.

This study investigates a fully automatic left ventricle segmentation method from cine short axis MR images. Advantages of this method include that it: 1) is image-driven and does not require manually drawn initial contours. 2) provides not only endocardial and epicardial contours, but also papillary muscles and trabeculations’ contours; 3) introduces a roundness measure that is fast and automatically locates the left ventricle; 4) simplifies the epicardial contour segmentation by mapping the pixels from Cartesian to approximately polar coordinates; and 5) applies a fast Fourier transform to smooth the endocardial and epicardial contours. Quantitative evaluation was performed on the 15 subjects of the MICCAI 2009 Cardiac MR Left Ventricle Segmentation hallenge. The average perpendicular distance between manually drawn and automatically selected contours over all slices, all studies, and two phases (end-diastole and end-systole) was 2.07 0.61 mm for endocardial and 1.91 0.63 mm for epicardial contours. These results indicate a promising method for automatic segmentation of left ventricle for clinical use.

Left ventricle (LV) segmentation is crucial to assess left ventricle global function. U-Net; a Convolutional Neural Network (CNN); boosted the performance of many biomedical image segmentation tasks. In LV segmentation, U-Net suffered from accurately extracting small objects such as the apical short-axis slices. In this paper, we propose a fully automated left ventricle segmentation method for both short-axis and long-axis views. The proposed model utilizes U-Net architecture and Multi-Gate input block to enhance the performance by aggregating multi-scale features and adding different vision scopes providing a more robust model against scale variance of objects within the images. The proposed approach was validated against left ventricle segmentation challenge (LVSC) and Automated cardiac diagnosis challenge (ACDC). For LV myocardium segmentation, the proposed approach achieved mean dice index 82% on LVSC and 90% and 91% for end-diastole (ED) and end-systole (ES) time frames respectively on ACDC outperforming other published methods measurements at ED. For LV blood pool segmentation, mean dice index was 97% and 92.3% for the ED and ES time frames using ACDC, outperforming other methods’ ED measurements.

Clinical indications of heart disease are shown from left ventricle (LV) or right ventricle (RV) volume measurements of cardiac MRI images. LV and RV segmentation of cardiac MRI images can detect and measure image volume. Public dataset MICCAI, ACDC, Kaggle, and SCD provide data on MRI images of cardiac that have been widely used by researchers. The deep learning method approach can optimally solve problems in analyzing heart disease from cardiac MRI images. The aim of this paper is to determine the availability of public datasets that are appropriate for the research objectives. It can support the optimization of the segmentation method for LV and RV images of cardiac as the contribution of this paper. The results of the study are that the public dataset (MICCAI, ACDC, Kaggle, and SCD) provides sufficient data for the identification, classification, and measurement of LV and RV volumes. Furthermore, a deep learning approach with convolutional neural networks can detect and classify heart diseases with high accuracy.

In clinical practice, cardiac magnetic resonance imaging (CMR) is considered the gold-standard imaging modality for the evaluation of function and structure of the left ventricle (LV). However, the quantification of LV parameters in all frames, even when performed by experienced radiologists, is very time consuming mainly due to the inhomogeneity of cardiac structures within each image, the variability of the cardiac structures across subjects and the complicated global/regional temporal deformation of the myocardium during the cardiac cycle. In this work, we employed a combination of two convolutional neural networks (CNN) to develop a fully automatic LV segmentation method for Short Axis CMR datasets. The first CNN defines the region of interest (ROI) of the cardiac chambers based on You Only Look Once (YOLO) network. The output of YOLO net is used to filter the image and feed the second CNN, based on UNet network, which segments the myocardium and the blood pool. The method was validated in CMR exams of 59 individuals from an institutional clinical protocol. Segmentation results, evaluated by metrics Percentage of Good Contours, Dice Index and Average Perpendicular distance, were 98,59% ± 4,28%, 0,93 ± 0,06 and 0,72 mm ± 0,62 mm, respectively, for the LV epicardium, and 94,98% ± 14,04%, 0,86 ± 0,13 and 1,19 mm ± 1,29 mm, respectively, for the LV endocardium. The combination of two CNNs demonstrated good performance in terms of the evaluated metrics when compared to literature results.

Early prediction of myocarditis clinical course still remains one of the actual tasks of cardiological science, which has a significant practical value. The purpose of the study was to determine the predictors of unfavorable course of myocarditis with reduced ejection fraction (EF) of the left ventricle (LV) on the basis of follow-up during 24 months. The study included 90 patients with acute myocarditis and reduced LV EF, who were examined in the first month after the disease onset, after 6, 12 and 24 months of follow-up. All patients underwent for echocardiography, Holter monitoring of the electrocardiogram and cardiac magnetic resonance imaging. Statistical processing of the results was performed using the Excel XP software (Місrosoft Office, USA) and Statistica for Windows v. 6.0 (Statsoft, USA). It was found that restoration of cardiac contractility in patients with myocarditis and reduced LV EF began with an increase in the index of LV longitudinal global systolic strain, which occurred 6 months after the debut of the disease and was associated with a decrease in the number of LV segments affected by the inflammatory process, and a significant increase of LV EF and a decrease of LV end-diastolic volume were observed only 1 year after the disease onset. The predictors of cardiovascular events in patients with acute myocarditis during the next 24 months from the onset of the disease, were detected in the 1st month from the debut of the disease and included following pathological changes: value of the LV EF ≤ 30%; reduction of LV longitudinal global systolic strain ≤ 7.0%; evidence of non-sustained ventricular tachycardia, presence of inflammatory changes in ≥6 LV segments, presence of delayed enhancement in ≥ 5 LV segments. Prospects for further research are the creation of registries of patients with myocarditis on the basis of multicenter clinical trial results on a large number of patients surveyed in order to improve diagnosis, prediction of clinical course and identification of early diagnostic markers of cardiovascular events and quantitative risk assessment of their development.

The aim – to study heart rhythm and conduction disturbances in different localization and distribution of myocardial lesions in combatants with severe myocarditis based on the results of a 6-month follow-up.Materials and methods. 46 male military personnel with a severe course of acute myocarditis (AM) with a reduced ejection fraction (EF) of the left ventricle (LV) (≤ 40 %) with an average age of (35,1±2,4) years were examined. Examinations were carried out in the 1st month after the onset of symptoms of myocarditis and after 6 months of observation. The diagnosis of myocarditis and the severe course of the disease were established on the basis of the Recommendations for the diagnosis and treatment of myocarditis of the All-Ukrainian Association of Cardiologists of Ukraine. All patients underwent for 24-hour ECG monitoring with analysis of the frequency and spectrum of rhythm and conduction disturbances and cardiac magnetic resonance (CMR) imaging with contrast analysis of the topography of the lesion and counting the number of LV segments affected by inflammatory changes and LV segments with the presence of late gadolinium enhancement (LGE).Results and discussion. When comparing the results of heart MRI with the data of daily ECG monitoring, a clear association of the presence of frequent ventricular extrasystoles (VE) and paroxysms of non-sustained ventricular tachycardia (NSVT) with the localization of LGE in the interventricular septum (IS) was established – among patients with LGE lesions at the onset of AM more than in a third (37.0 %) had frequent VE, and NSVT paroxysms, which increase the risk of developing life-threatening ventricular arrhythmias, were detected in 25,9 % of cases. After 6 months of observation in the presence of LGE in the IS, the frequency of detection of frequent VE and NSVT paroxysms was also significantly higher compared to other localization of the lesion and amounted to 20,0 and 13,3 %, respectively. With the help of correlation analysis, an associative relationship was revealed between the presence of LGE in the IS and the presence of frequent VE and NSVT paroxysms in the debut of myocarditis – r=0.73 (р<0.01) and r=0.66 (р<0,01) respectively, and also after 6 months of observation – r=0.65 (р<0.01) and r=0.59 (р<0.05), respectively. According to the results of the multivariate regression analysis, predictors of frequent VE persistence after 6 months were: LVEF ≤30 %; LV end-diastolic volume index ≥105 ml/m2; presence of inflammatory changes in ≥5.0 LV segments; presence of LGE in ≥4.0 LV segments and its presence in the IS, determined in the 1st month from the onset of the disease. The predictors NSVT paroxysms persistence after 6 months were the same factors with the exception of LV EF, and, according to the value of the β coefficient (β=1.302; p<0.001), the most significant contribution was the presence of LGE in the IS.Conclusions. In combatants with severe myocarditis, the presence of late gadolinium enhancement in the interventricular septum is an additional risk factor for the persistence of frequent ventricular extrasystoles and paroxysms of non-sustained ventricular tachycardia during 6 months, while the presence of late gadolinium enhancement in the posterior and lateral walls of the left ventricle has no reliable relationship with the presence of rhythm and conduction disorders. On the basis of multivariate regression analysis, predictors of frequent ventricular extrasystoles and paroxysms of non-sustained ventricular tachycardia persistence were established in combatants with myocarditis.

Cardiac magnetic resonance (CMR) images play a growing role in the diagnostic imaging of cardiovascular diseases. Full coverage of the left ventricle (LV), from base to apex, is a basic criterion for CMR image quality and necessary for accurate measurement of cardiac volume and functional assessment. Incomplete coverage of the LV is identified through visual inspection, which is time-consuming and usually done retrospectively in the assessment of large imaging cohorts. This paper proposes a novel automatic method for determining LV coverage from CMR images by using Fisher-discriminative three-dimensional (FD3D) convolutional neural networks (CNNs). In contrast to our previous method employing 2D CNNs, this approach utilizes spatial contextual information in CMR volumes, extracts more representative high-level features and enhances the discriminative capacity of the baseline 2D CNN learning framework, thus achieving superior detection accuracy. A two-stage framework is proposed to identify missing basal and apical slices in measurements of CMR volume. First, the FD3D CNN extracts high-level features from the CMR stacks. These image representations are then used to detect the missing basal and apical slices. Compared to the traditional 3D CNN strategy, the proposed FD3D CNN minimizes within-class scatter and maximizes between-class scatter. We performed extensive experiments to validate the proposed method on more than 5,000 independent volumetric CMR scans from the UK Biobank study, achieving low error rates for missing basal/apical slice detection (4.9%/4.6%). The proposed method can also be adopted for assessing LV coverage for other types of CMR image data.

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.

Magnetic Resonance Imaging (MRI) has evolved as a clinical standard-of-care imaging modality for cardiac morphology, function assessment, and guidance of cardiac interventions. All these applications rely on accurate extraction of the myocardial tissue and blood pool from the imaging data. Here we propose a framework for left ventricle (LV) segmentation from cardiac cine MRI. First, we segment the LV blood pool using iterative graph cuts, and subsequently use this information to segment the myocardium. We formulate the segmentation procedure as an energy minimization problem in a graph subject to the shape prior obtained by label propagation from an average atlas using affine registration. The proposed framework has been validated on 30 patient cardiac cine MRI datasets available through the STACOM LV segmentation challenge and yielded fast, robust, and accurate segmentation results.

In the development of treatments for cardiovascular diseases, short axis cardiac cine MRI is important for the assessment of various structural and functional properties of the heart. In short axis cardiac cine MRI, Cardiac properties including the ventricle dimensions, stroke volume, and ejection fraction can be extracted based on accurate segmentation of the left ventricle (LV) myocardium. One of the most advanced segmentation methods is based on fully convolutional neural networks (FCN) and can be successfully used to do segmentation in cardiac cine MRI slices. However, the temporal dependency between slices acquired at neighboring time points is not used. Here, based on our previously proposed FCN structure, we proposed a new algorithm to segment LV myocardium in porcine short axis cardiac cine MRI by incorporating convolutional long short-term memory (Conv-LSTM) to leverage the temporal dependency. In this approach, instead of processing each slice independently in a conventional CNN-based approach, the Conv-LSTM architecture captures the dynamics of cardiac motion over time. In a leave-one-out experiment on 8 porcine specimens (3,600 slices), the proposed approach was shown to be promising by achieving average mean Dice similarity coefficient (DSC) of 0.84, Hausdorff distance (HD) of 6.35 mm, and average perpendicular distance (APD) of 1.09 mm when compared with manual segmentations, which improved the performance of our previous FCN-based approach (average mean DSCe0.84, HDe6.78 mm, and APDe1.11 mm). Qualitatively, our model showed robustness against low image quality and complications in the surrounding anatomy due to its ability to capture the dynamics of cardiac motion.

Generation of parametric images of myocardial blood flow (MBF) from dynamic PET requires a reproducible and reliable method to obtain left and right ventricular time-activity curves. We propose the use of Independent Component Analysis (ICA) on PET temporal information to segment the image data into three categories: right ventricle (RV), left ventricle (LV) and myocardium. ICA is an established signal processing technique that assumes that the dynamic signal in each voxel is a linear mixture of signals from statistically independent sources. The mixing process is due to cardiac motion and partial volume effects. Due to its ability to find the intensity of the underlying sources, ICA generates a 3D map of the mixing coefficients that allows the segmentation of structures. Dynamic cardiac PET data were acquired with a Siemens Biograph mCT PET/CT scanner using Rb-82 and [15O]water in nonhuman primate and pigs with injections of different activities. The Dice similarity coefficient (DSC) was used to compare the segmentations between scans of different species with different tracers. The LV and RV regions were used to calculate input functions for kinetic analysis and MBF estimation. Pairwise comparisons of the segmentations between different [15O]water PET scans gave DSC of 0.91 ± 0.09 and 0.92±0.08 for the RV and LV segmentations, respectively. For Rb-82 PET scans, the DSC values were of 0.89 ± 0.09 and 0.85±0.10 for RV and LV. We used contrast CT as a gold standard for the LV and RV segmentations. Pairwise comparisons of the segmentations between different contrast CT and Rb-82 PET scans gave DSC of 0.86 ± 0.09 and 0.85±0.09 for the RV and LV, respectively. Our work shows the reliability and reproducibility of the results of the segmentation algorithm. High quality parametric images of MBF and the kinetic parameters were obtained. These results suggest that ICA may be useful to extract time-activity curves for kinetic MBF analysis. The effects of partial volume on input TAC determination were also evaluated.

Cardiac magnetic resonance imaging (CMRI) provides high resolution images ideal for assessing cardiac function and diagnosis of cardiovascular diseases. To assess cardiac function, estimation of ejection fraction, ventricular volume, mass and stroke volume are crucial, and the segmentation of left ventricle from CMRI is the first critical step. Fully convolutional neural network architectures have proved to be very efficient for medical image segmentation, with U-Net inspired architecture as the current state-of-the-art. Generative adversarial networks (GAN) inspired architectures have recently gained popularity in medical image segmentation with one of them being SegAN, a novel end-to-end adversarial neural network architecture. In this paper, we investigate SegAN with three different types of U-Net inspired architectures for left ventricle segmentation from cardiac MRI data. We performed our experiments on the 2017 ACDC segmentation challenge dataset. Our results show that the performance of U-Net architectures is better when trained in the SegAN framework than when trained stand-alone. The mean Dice scores achieved for three different U-Net architectures trained in the SegAN framework was on the order of 93.62%, 92.49% and 94.57%, showing a significant improvement over their Dice scores following stand-alone training - 92.58%), 91.46% and 93.81%, respectively.

IntroductionAlthough global deformation parameters have been increasingly used for myocardial function analysis, there are sparse data concerning segmental deformation of the left ventricle (LV). Moreover, some studies suggest heterogeneity of strain among LV segments, which may be especially significant during stress echocardiography. We assessed quantitatively regional LV function in the setting of dobutamine stress echocardiography (DSE), to examine differences of longitudinal strain between basal, mid and apical LV segments and to compare variability of regional deformation between rest and the peak stage of DSE.Material and methodsAmong 250 patients examined by DSE applied for diagnosis of ischemia, a subset of 111 patients without significant coronary stenoses in angiography was selected (68 females, mean age: 60 ±10 years). Systolic longitudinal strain (SLS) in individual LV segments at baseline and the peak stage of DSE was analyzed with speckle tracking echocardiography.ResultsInhomogeneity of SLS among the LV segments (p < 0.001) was observed at baseline and the peak stage. Dispersion indices were higher at the peak stage of DSE than at baseline (p < 0.001), and the lowest heterogeneity was observed among mid segments. The analysis of changes in SLS during DSE showed SLS reduction in basal and mid-ventricular segments and an increase in apical segments.ConclusionsSignificant heterogeneity of strain and the opposite direction of the longitudinal strain changes during DSE between apical and basal LV segments were observed. This variability among non-ischemic LV segments ought to be considered in quantification of LV function during DSE.