Slide deep reinforcement learning networks: Application for left ventricle segmentation

Left ventricle segmentation combining deep learning and deformable models with anatomical constraints

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

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

Left ventricular ejection fraction is one of the important indices to evaluate cardiac function. Manual segmentation of the left ventricle (LV) in 2-D echocardiograms is tedious and time-consuming. We proposed a deep learning method called convolutional long-short-term-memory attention-gated U-Net (CLA-U-Net) for automatic segmentation of the LV in 2-D echocardiograms. The CLA-U-Net model was trained and tested using the EchoNet-Dynamic dataset. The dataset contained 9984 annotated echocardiogram videos (training set: 7456; validation set: 1296; test set 1232). The model was also tested on a private clinical dataset of 20 echocardiogram videos. U-Net was used as the basic encoder and decoder structure, and some very useful structures were designed. In the encoding part, we incorporated a convolutional long-short-term-memory (C-LSTM) block to guide the network to capture the temporal information between frames in the videos. In addition, we replaced the skip-connection structure of the original U-Net with a channel attention mechanism, which can amplify the desired feature signals and suppress the noise. With the proposed CLA-U-Net, the LV was segmented automatically on the EchoNet-Dynamic test set, and a Dice similarity coefficient (DSC) of 0.9311 was obtained. The DSC obtained by the DeepLabV3 network was 0.9236. The hyperparameters of CLA-U-Net were only 19.9 MB, reduced by ~91.6% as compared with DeepLabV3 network. For the private clinical dataset, a DSC of 0.9192 was obtained. Our CLA-U-Net achieved a desirable LV segmentation accuracy, with a lower amount of hyperparameters. The CLA-U-Net may be used as a new lightweight deep learning method for automatic LV segmentation in 2-D echocardiograms.

The left ventricle segmentation (LVS) is of great important for the evaluation of cardiac function. This study aimed to establish new segmentation algorithms that can enhance the accuracy and robustness of automatic LVS on magnetic resonance images. The datasets involved 45 subjects, including 12 heart failure patients with ischemia, 12 heart failure patients without ischemia, 12 hypertrophy patients and 9 normal individuals. The experiments consisted of three important steps. At first, deep learning was employed for the coarse LVS on myocardial images. Next, a double snake model was applied to assess the endo- and epi-cardial boundaries. Finally, the optimal epicardial boundary was obtained by adopting radial region growing method. Additionally, the performance of the developed LVS method was evaluated by the previously established software. Furthermore, the developed LVS method was validated by applying the datasets of 45 subjects. The results showed that the good contours, overlapping dice metric and average perpendicular distance of both epi- and endo-cardial contours were approximately 97%, 0.97 and 1.8 mm respectively. The regression coefficient and coefficient of determination between the proposed method and clinical experts were 0.96 and 1.039, respectively for ejection fraction, while 0.92 and 0.994 for left ventricle mass. These findings reveal that the developed method can enhance the accuracy and robustness of LVS. This novel LVS approach exhibits outstanding performance and possesses promising potential to increase the reliability of computer-aided imaging detection system for cardiovascular disease.

Reinforcement learning, as a branch of machine learning, has been gradually applied in the control field. However, in the practical application of the algorithm, the hyperparametric approach to network settings for deep reinforcement learning still follows the empirical attempts of traditional machine learning (supervised learning and unsupervised learning). This method ignores part of the information generated by agents exploring the environment contained in the updating of the reinforcement learning value function, which will affect the performance of the convergence and cumulative return of reinforcement learning. The reinforcement learning algorithm based on dynamic parameter adjustment is a new method for setting learning rate parameters of deep reinforcement learning. Based on the traditional method of setting parameters for reinforcement learning, this method analyzes the advantages of different learning rates at different stages of reinforcement learning and dynamically adjusts the learning rates in combination with the temporal-difference (TD) error values to achieve the advantages of different learning rates in different stages to improve the rationality of the algorithm in practical application. At the same time, by combining the Robbins–Monro approximation algorithm and deep reinforcement learning algorithm, it is proved that the algorithm of dynamic regulation learning rate can theoretically meet the convergence requirements of the intelligent control algorithm. In the experiment, the effect of this method is analyzed through the continuous control scenario in the standard experimental environment of ”Car-on-The-Hill” of reinforcement learning, and it is verified that the new method can achieve better results than the traditional reinforcement learning in practical application. According to the model characteristics of the deep reinforcement learning, a more suitable setting method for the learning rate of the deep reinforcement learning network proposed. At the same time, the feasibility of the method has been proved both in theory and in the application. Therefore, the method of setting the learning rate parameter is worthy of further development and research.

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.

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.

Segmentation of echocardiographic images is an essential step for assessing the cardiac functionality and providing indicative clinical measures, and all further heart analysis relies on the accuracy of this process. However, the fuzzy nature of echocardiographic images degraded by distortion and speckle noise poses some challenges on the manual segmentation task. In this paper, we propose a fully automated left ventricle segmentation method that can overcome those challenges. Our method performs accurate delineation for the ventricle boundaries despite the ill-defined borders and shape variability of the left ventricle. The well-known deep learning segmentation model, known as the U-net, has addressed some of these challenges with outstanding performance. However, it still ignores the contribution of all semantic information through the segmentation process. Here we propose a novel deep learning segmentation method based on U-net, named ResDUnet. It incorporates feature extraction at different scales through the integration of cascaded dilated convolution. To ease the training process, residual blocks are deployed instead of the basic U-net blocks. Each residual block is enriched with a squeeze and excitation unit for channel-wise attention and adaptive feature re-calibration. The performance of the method is evaluated on a dataset of 2000 images acquired from 500 patients with large variability in quality and patient pathology. ResDUnet outperforms state-of-the-art methods with a Dice similarity increase of 8.4% and 1.2% compared to deeplabv3 and U-net, respectively. Furthermore, to demonstrate the impact of each proposed sub-module, several experiments have been carried out with different designs and variations of the integrated sub-modules. We also describe and discuss all technical elements of a deep-learning model via a step-by-step explanation of parameters and methods, while using our left ventricle segmentation as a case study, to explain the application of AI to echocardiographic imaging.

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.

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.

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.

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.

Deep learning (DL) has been applied for automatic left ventricle (LV) ejection fraction (EF) measurement, but the diagnostic performance was rarely evaluated for various phenotypes of heart disease. This study aims to evaluate a new DL algorithm for automated LVEF measurement using two-dimensional echocardiography (2DE) images collected from three centers. The impact of three ultrasound machines and three phenotypes of heart diseases on the automatic LVEF measurement was evaluated. Using 36890 frames of 2DE from 340 patients, we developed a DL algorithm based on U-Net (DPS-Net) and the biplane Simpson's method was applied for LVEF calculation. Results showed a high performance in LV segmentation and LVEF measurement across phenotypes and echo systems by using DPS-Net. Good performance was obtained for LV segmentation when DPS-Net was tested on the CAMUS data set (Dice coefficient of 0.932 and 0.928 for ED and ES). Better performance of LV segmentation in study-wise evaluation was observed by comparing the DPS-Net v2 to the EchoNet-dynamic algorithm (P = 0.008). DPS-Net was associated with high correlations and good agreements for the LVEF measurement. High diagnostic performance was obtained that the area under receiver operator characteristic curve was 0.974, 0.948, 0.968, and 0.972 for normal hearts and disease phenotypes including atrial fibrillation, hypertrophic cardiomyopathy, dilated cardiomyopathy, respectively. High performance was obtained by using DPS-Net in LV detection and LVEF measurement for heart failure with several phenotypes. High performance was observed in a large-scale dataset, suggesting that the DPS-Net was highly adaptive across different echocardiographic systems.NEW & NOTEWORTHY A new strategy of feature extraction and fusion could enhance the accuracy of automatic LVEF assessment based on multiview 2-D echocardiographic sequences. High diagnostic performance for the determination of heart failure was obtained by using DPS-Net in cases with different phenotypes of heart diseases. High performance for left ventricle segmentation was obtained by using DPS-Net, suggesting the potential for a wider range of application in the interpretation of 2DE images.

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.