Left Ventricular Segmentation Research Articles

Automatic left ventricular cavity segmentation via deep spatial sequential network in 4D computed tomography.

Automated segmentation of left ventricular cavity (LVC) in temporal cardiac image sequences (consisting of multiple time-points) is a fundamental requirement for quantitative analysis of cardiac structural and functional changes. Deep learning methods for segmentation are the state-of-the-art in performance; however, these methods are generally formulated to work on a single time-point, and thus disregard the complementary information available from the temporal image sequences that can aid in segmentation accuracy and consistency across the time-points. In particular, single time-point segmentation methods perform poorly in segmenting the end-systole (ES) phase image in the cardiac sequence, where the left ventricle deforms to the smallest irregular shape, and the boundary between the blood chamber and the myocardium becomes inconspicuous and ambiguous. To overcome these limitations in automatically segmenting temporal LVCs, we present a spatial sequential network (SS-Net) to learn the deformation and motion characteristics of the LVCs in an unsupervised manner; these characteristics are then integrated with sequential context information derived from bi-directional learning (BL) where both chronological and reverse-chronological directions of the image sequence are used. Our experimental results on a cardiac computed tomography (CT) dataset demonstrate that our spatial-sequential network with bi-directional learning (SS-BL-Net) outperforms existing methods for spatiotemporal LVC segmentation.

SHAPE-REGULARIZED UNSUPERVISED LEFT VENTRICULAR MOTION NETWORK WITH SEGMENTATION CAPABILITY IN 3D+TIME ECHOCARDIOGRAPHY.

Accurate motion estimation and segmentation of the left ventricle from medical images are important tasks for quantitative evaluation of cardiovascular health. Echocardiography offers a cost-efficient and non-invasive modality for examining the heart, but provides additional challenges for automated analyses due to the low signal-to-noise ratio inherent in ultrasound imaging. In this work, we propose a shape regularized convolutional neural network for estimating dense displacement fields between sequential 3D B-mode echocardiography images with the capability of also predicting left ventricular segmentation masks. Manually traced segmentations are used as a guide to assist in the unsupervised estimation of displacement between a source and a target image while also serving as labels to train the network to additionally predict segmentations. To enforce realistic cardiac motion patterns, a flow incompressibility term is also incorporated to penalize divergence. Our proposed network is evaluated on an in vivo canine 3D+t B-mode echocardiographic dataset. It is shown that the shape regularizer improves the motion estimation performance of the network and our overall model performs favorably against competing methods.

Automated segmentation of left ventricular myocardium using cascading convolutional neural networks based on echocardiography

Quickly and accurately segmenting the left ventricular (LV) myocardium from ultrasound images and measuring the thickness of the interventricular septum and LV wall play an important role in hypertrophic cardiomyopathy. However, the segmentation of the LV myocardium is a challenging task due to image blurring and individual differences. We attempted to perform LV segmentation in ultrasound images using the encoder–decoder architecture of U-Net and other networks and found it to be not accurate enough. Therefore, we propose a novel multi-task cascaded convolutional neural network (called MTC-Net) to segment the LV myocardium from echocardiography. MTC-Net contains two parts: One is pre-trained Resnet-34 followed by two decoder branches for mask and boundary detection, and the other module is pre-trained with many improved novel encoder–decoder architectures for extracting more detailed features. Both parts of the network use the atrous spatial pyramid pooling module to capture high-level text information. A hybrid loss function is engaged for mask and contour prediction. The network is trained and evaluated with echocardiographic images, which are labeled manually by doctors. The comparison study with other networks shows that MTC-Net has better accuracy and performance. MTC-Net achieves state-of-the-art performance on the test set. The mean value of the dice coefficient is 0.9442 and the mean value of intersection over union is 0.8951.

Automated left and right ventricular chamber segmentation in cardiac magnetic resonance images using dense fully convolutional neural network

Background and objectiveSegmentation of the left ventricular (LV) myocardium (Myo) and RV endocardium on cine cardiac magnetic resonance (CMR) images represents an essential step for cardiac-function evaluation and diagnosis. In order to have a common reference for comparing segmentation algorithms, several CMR image datasets were made available, but in general they do not include the most apical and basal slices, and/or gold standard tracing is limited to only one of the two ventricles, thus not fully corresponding to real clinical practice. Our aim was to develop a deep learning (DL) approach for automated segmentation of both RV and LV chambers from short-axis (SAX) CMR images, reporting separately the performance for basal slices, together with the applied criterion of choice. MethodA retrospectively selected database (DB1) of 210 cine sequences (3 pathology groups) was considered: images (GE, 1.5 T) were acquired at Centro Cardiologico Monzino (Milan, Italy), and end-diastolic (ED) and end-systolic frames (ES) were manually segmented (gold standard, GS). Automatic ED and ES RV and LV segmentation were performed with a U-Net inspired architecture, where skip connections were redesigned introducing dense blocks to alleviate the semantic gap between the U-Net encoder and decoder. The proposed architecture was trained including: A) the basal slices where the Myo surrounded the LV for at least the 50% and all the other slice; B) all the slices where the Myo completely surrounded the LV. To evaluate the clinical relevance of the proposed architecture in a practical use case scenario, a graphical user interface was developed to allow clinicians to revise, and correct when needed, the automatic segmentation. Additionally, to assess generalizability, analysis of CMR images obtained in 12 healthy volunteers (DB2) with different equipment (Siemens, 3T) and settings was performed. ResultsThe proposed architecture outperformed the original U-Net. Comparing the performance on DB1 between the two criteria, no significant differences were measured when considering all slices together, but were present when only basal slices were examined. Automatic and manually-adjusted segmentation performed similarly compared to the GS (bias±95%LoA): LVEDV -1±12 ml, LVESV -1±14 ml, RVEDV 6±12 ml, RVESV 6±14 ml, ED LV mass 6±26 g, ES LV mass 5±26 g). Also, generalizability showed very similar performance, with Dice scores of 0.944 (LV), 0.908 (RV) and 0.852 (Myo) on DB1, and 0.940 (LV), 0.880 (RV), and 0.856 (Myo) on DB2. ConclusionsOur results support the potential of DL methods for accurate LV and RV contours segmentation and the advantages of dense skip connections in alleviating the semantic gap generated when high level features are concatenated with lower level feature. The evaluation on our dataset, considering separately the performance on basal and apical slices, reveals the potential of DL approaches for fast, accurate and reliable automated cardiac segmentation in a real clinical setting.

An Improved Level Set Algorithm Based on Prior Information for Left Ventricular MRI Segmentation

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.

Cardiovascular magnetic resonance detects microvascular dysfunction in a mouse model of hypertrophic cardiomyopathy

BackgroundHypertrophic cardiomyopathy (HCM) related myocardial vascular remodelling may lead to the reduction of myocardial blood supply and a subsequent progressive loss of cardiac function. This process has been difficult to observe and thus their connection remains unclear. Here we used non-invasive myocardial blood flow sensitive CMR to show an impairment of resting myocardial perfusion in a mouse model of naturally occurring HCM.MethodsWe used a mouse model (DBA/2 J; D2 mouse strain) that spontaneously carries variants in the two most susceptible HCM genes—Mybpc3 and Myh7 and bears the key features of human HCM. The C57BL/6 J (B6) was used as a reference strain. Mice with either B6 or D2 backgrounds (male: n = 4, female: n = 4) underwent cine-CMR for functional assessment at 9.4 T. Left ventricular (LV) wall thickness was measured in end diastolic phase by cine-CMR. Quantitative myocardial perfusion maps (male: n = 5, female: n = 5 in each group) were acquired from arterial spin labelling (cine ASL-CMR) at rest. Myocardial perfusion values were measured by delineating different regions of interest based on the LV segmentation model in the mid ventricle of the LV myocardium. Directly after the CMR, the mouse hearts were removed for histological assessments to confirm the incidence of myocardial interstitial fibrosis (n = 8 in each group) and small vessel remodelling such as vessel density (n = 6 in each group) and perivascular fibrosis (n = 8 in each group).ResultsLV hypertrophy was more pronounced in D2 than in B6 mice (male: D2 LV wall thickness = 1.3 ± 0.1 mm vs B6 LV wall thickness = 1.0 ± 0.0 mm, p < 0.001; female: D2 LV wall thickness = 1.0 ± 0.1 mm vs B6 LV wall thickness = 0.8 ± 0.1 mm, p < 0.01). The resting global myocardial perfusion (myocardial blood flow; MBF) was lower in D2 than in B6 mice (end-diastole: D2 MBFglobal = 7.5 ± 0.6 vs B6 MBFglobal = 9.3 ± 1.6 ml/g/min, p < 0.05; end-systole: D2 MBFglobal = 6.6 ± 0.8 vs B6 MBFglobal = 8.2 ± 2.6 ml/g/min, p < 0.01). This myocardial microvascular dysfunction was observed and associated with a reduction in regional MBF, mainly in the interventricular septal and inferior areas of the myocardium. Immunofluorescence revealed a lower number of vessel densities in D2 than in B6 (D2 capillary = 31.0 ± 3.8% vs B6 capillary = 40.7 ± 4.6%, p < 0.05). Myocardial collagen volume fraction (CVF) was significantly higher in D2 LV versus B6 LV mice (D2 CVF = 3.7 ± 1.4% vs B6 CVF = 1.7 ± 0.7%, p < 0.01). Furthermore, a higher ratio of perivascular fibrosis (PFR) was found in D2 than in B6 mice (D2 PFR = 2.3 ± 1.0%, B6 PFR = 0.8 ± 0.4%, p < 0.01).ConclusionsOur work describes an imaging marker using cine ASL-CMR with a potential to monitor vascular and myocardial remodelling in HCM.

Automated left ventricular segmentation from cardiac magnetic resonance images via adversarial learning with multi-stage pose estimation network and co-discriminator.

Left ventricular (LV) segmentation is essential for the early diagnosis of cardiovascular diseases, which has been reported as the leading cause of death all over the world. However, automated LV segmentation from cardiac magnetic resonance images (CMRI) using the traditional convolutional neural networks (CNNs) is still a challenging task due to the limited labeled CMRI data and low tolerances to irregular scales, shapes and deformations of LV. In this paper, we propose an automated LV segmentation method based on adversarial learning by integrating a multi-stage pose estimation network (MSPN) and a co-discrimination network. Different from existing CNNs, we use a MSPN with multi-scale dilated convolution (MDC) modules to enhance the ranges of receptive field for deep feature extraction. To fully utilize both labeled and unlabeled CMRI data, we propose a novel generative adversarial network (GAN) framework for LV segmentation by combining MSPN with co-discrimination networks. Specifically, the labeled CMRI are first used to initialize our segmentation network (MSPN) and co-discrimination network. Our GAN training includes two different kinds of epochs fed with both labeled and unlabeled CMRI data alternatively, which are different from the traditional CNNs only relied on the limited labeled samples to train the segmentation networks. As both ground truth and unlabeled samples are involved in guiding training, our method not only can converge faster but also obtain a better performance in LV segmentation. Our method is evaluated using MICCAI 2009 and 2017 challenge databases. Experimental results show that our method has obtained promising performance in LV segmentation, which also outperforms the state-of-the-art methods in terms of LV segmentation accuracy from the comparison results.

Smart Health of Ultrasound Telemedicine Based on Deeply Represented Semantic Segmentation

The development of the Internet of Things (IoT) plays an important role in smart health. The combination of IoT and ultrasound has great potential applications in telemedicine. The medical information in the echocardiogram stimulates the image analysis of ultrasound IoT devices. Medical image segmentation is a fundamental step in medical image analysis for providing help to the subsequent tasks. However, accurate left ventricular (LV) segmentation in echocardiography is a challenging task due to the cross-vendor and cross-center, multiview ultrasound image characteristics. We introduce an intermediate supervision deep neural networks method in this article, named as deep atrous pyramid intermediate supervision (DAPIS). The SAD block is used as a fixed feature extractor, pyramid pooling module is used to extract context semantic information, global attention upsampling is used for feature fusion module, and intermediate supervision is used to learn a better semantic representation. The performance of the model is evaluated using two echocardiographic data: 1) public data set (CAMUS) and 2) self-made data set (total 18906 images from 160 patients). Sufficient experiments show that DAPIS is prominent generalization and robustness, surpassing other state-of-the-art methods. The correlation graph and Bland–Altman analysis show good clinical correlation, proving the clinical potential of the model.

A Topological Loss Function for Deep-Learning Based Image Segmentation Using Persistent Homology.

We introduce a method for training neural networks to perform image or volume segmentation in which prior knowledge about the topology of the segmented object can be explicitly provided and then incorporated into the training process. By using the differentiable properties of persistent homology, a concept used in topological data analysis, we can specify the desired topology of segmented objects in terms of their Betti numbers and then drive the proposed segmentations to contain the specified topological features. Importantly this process does not require any ground-truth labels, just prior knowledge of the topology of the structure being segmented. We demonstrate our approach in four experiments: one on MNIST image denoising and digit recognition, one on left ventricular myocardium segmentation from magnetic resonance imaging data from the UK Biobank, one on the ACDC public challenge dataset and one on placenta segmentation from 3-D ultrasound. We find that embedding explicit prior knowledge in neural network segmentation tasks is most beneficial when the segmentation task is especially challenging and that it can be used in either a semi-supervised or post-processing context to extract a useful training gradient from images without pixelwise labels.

Segmentation of the left ventricle in cardiac MRI based on convolutional neural network and level set function

Left ventricular segmentation in cardiac magnetic resonance images is considered as the most critical method to evaluate the cardiac function. In this paper, a hybrid method has been proposed to segment the left ventricle(endocardium). In this study, first, a new method has been proposed based on deep Convolutional Neural Network (CNN) to localize the LV in cardiac MRI. Then, the segmentation is completed through the localized LV by level set function. After segmentation, for each patient end-systole volume, end-diastole volume and ejection fraction are calculated to evaluate the left ventricle function. The evaluation of segmentation is done by specificity, sensitivity, accuracy, Average Perpendicular Distance (APD), and Dice indexes. According to obtain results for the proposed method, the mean specificity, sensitivity, and accuracy were 99.35, 94.11, and 94. Based on the results, the presented method is very reliable for the segmentation of the left ventricles and evaluation of the cardiac function.

Automatic ventricular nuclear magnetic resonance image processing with deep learning

Cardiovascular diseases (CVD) seriously threaten the health of human beings, and they have caused widespread concern in recent years. At present, the diagnosis of CVD is mainly conducted by computed tomography (CT), echocardiography and nuclear magnetic resonance (NMR) technologies. NMR imaging technology is widely used in medical applications owing to its characteristics of high resolution and very low radiation. However, manual NMR image segmentation is time-consuming and error-prone, which has led to the research on automatic NMR image segmentation technologies. Researchers tend to explore the ventricular NRM image segmentation to improve the accuracy of CVD diagnosis. In this study, based on deep learning technology, we propose a layered Mask R-CNN segmentation method to segment ventricular NMR images. The experimental results show that the mean dice metrics (DM) of left ventricular segmentation and right ventricular segmentation are 0.92 and 0.89, and the Hausdorff distance (HD) metrics are 4.78 mm and 7.03 mm. Our research indicates that the proposed novel method has great potential to automate the ventricular NMR image segmentation. We also discuss the automatic abnormal ventricular systolic function detection method based on the proposed layered segmentation model.

Left ventricle automatic segmentation in cardiac MRI using a combined CNN and U-net approach

Cardiovascular diseases can be effectively prevented from worsening through early diagnosis. To this end, various methods have been proposed to detect the disease source by analyzing cardiac magnetic resonance images (MRI), wherein left ventricular segmentation plays an indispensable role. However, since the left ventricle (LV) is easily confused with other regions in cardiac MRI, segmentation of the LV is a challenging problem. To address this issue, we propose a composite model combining CNN and U-net to accurately segment the LV. In our model, CNN is used to locate the region of interest (ROI) and the U-net network achieve segmentation of LV. We used the cardiac MRI datasets of the MICCAI 2009 left ventricular segmentation challenge to train and test our model and demonstrated the accuracy and robustness of the proposed model. The proposed model achieved state-of-the-art results. The metrics are Dice metric (DM), volumetric overlap error (VOE) and Hausdorff distance (HD), in which DM reaches 0.951, VOE reaches 0.053 and HD reaches 3.641.

A SEMI-SUPERVISED JOINT LEARNING APPROACH TO LEFT VENTRICULAR SEGMENTATION AND MOTION TRACKING IN ECHOCARDIOGRAPHY.

Accurate interpretation and analysis of echocardiography is important in assessing cardiovascular health. However, motion tracking often relies on accurate segmentation of the myocardium, which can be difficult to obtain due to inherent ultrasound properties. In order to address this limitation, we propose a semi-supervised joint learning network that exploits overlapping features in motion tracking and segmentation. The network simultaneously trains two branches: one for motion tracking and one for segmentation. Each branch learns to extract features relevant to their respective tasks and shares them with the other. Learned motion estimations propagate a manually segmented mask through time, which is used to guide future segmentation predictions. Physiological constraints are introduced to enforce realistic cardiac behavior. Experimental results on synthetic and in vivo canine 2D+t echocardiographic sequences outperform some competing methods in both tasks.

Automated left ventricular myocardium segmentation using 3D deeply supervised attention U-net for coronary computed tomography angiography; CT myocardium segmentation.

Segmentation of left ventricular myocardium (LVM) in coronary computed tomography angiography (CCTA) is important for diagnosis of cardiovascular diseases. Due to poor image contrast and large variation in intensity and shapes, LVM segmentation for CCTA is a challenging task. The purpose of this work is to develop a region-based deep learning method to automatically detect and segment the LVM solely based on CCTA images. We developed a 3D deeply supervised U-Net, which incorporates attention gates (AGs) to focus on the myocardial boundary structures, to segment LVM contours from CCTA. The deep attention U-Net (DAU-Net) was trained on the patients' CCTA images, with a manual contour-derived binary mask used as the learning-based target. The network was supervised by a hybrid loss function, which combined logistic loss and Dice loss to simultaneously measure the similarities and discrepancies between the prediction and training datasets. To evaluate the accuracy of the segmentation, we retrospectively investigated 100 patients with suspected or confirmed coronary artery disease (CAD). The LVM volume was segmented by the proposed method and compared with physician-approved clinical contours. Quantitative metrics used were Dice similarity coefficient (DSC), Hausdorff distance (HD), mean surface distance (MSD), residual mean square distance (RMSD), the center of mass distance (CMD), and volume difference (VOD). The proposed method created contours with very good agreement to the ground truth contours. Our proposed segmentation approach is benchmarked primarily using fivefold cross validation. Model prediction correlated and agreed well with manual contour. The mean DSC of the contours delineated by our method was 91.6% among all patients. The resultant HD was 6.840±4.410mm. The proposed method also resulted in a small CMD (1.058±1.245mm) and VOD (1.640±1.777cc). Among all patients, the MSD and RMSD were 0.433±0.209mm and 0.724±0.375mm, respectively, between ground truth and LVM volume resulting from the proposed method. We developed a novel deep learning-based approach for the automated segmentation of the LVM on CCTA images. We demonstrated the high accuracy of the proposed learning-based segmentation method through comparison with ground truth contour of 100 clinical patient cases using six quantitative metrics. These results show the potential of using automated LVM segmentation for computer-aided delineation of CADs in the clinical setting.

Automated segmentation of the left ventricle from MR cine imaging based on deep learning architecture

Background: Magnetic resonance cine imaging is the accepted standard for cardiac functional assessment. Left ventricular (LV) segmentation plays a key role in volumetric functional quantification of the heart. Conventional manual analysis is time-consuming and observer-dependent. Automated segmentation approaches are needed to improve the clinical workflow of cardiac functional quantification. Recently, deep-learning networks have shown promise for efficient LV segmentation. PURPOSE: The routinely used V-Net is a convolutional network that segments images by passing features from encoder to decoder. In this study, this method was advanced as DenseV-Net by replacing the convolutional block with a densely connected algorithm and dense calculations to alleviate the vanishing-gradient problem, prevent exploding gradients, and to strengthen feature propagation. Thirty patients were scanned with a 3 Tesla MR imager. ECG-free, free-breathing, real-time cines were acquired with a balanced steady-state free precession technique. Linear regression and the dice similarity coefficient (DSC) were performed to evaluate LV segmentation performance of the classic neural networks FCN, UNet, V-Net, and the proposed DenseV-net methods, using manual analysis as the reference. Slice-based LV function was compared among the four methods. Results: Thirty slices from eleven patients were randomly selected (each slice contained 73 images), and the LVs were segmented using manual analysis, UNet, FCN, V-Net, and the proposed DenseV-Net methods. A strong correlation of the left ventricular areas was observed between the proposed DenseV-Net network and manual segmentation (R = 0.92), with a mean DSC of 0.90 ± 0.12. A weaker correlation was found between the routine V-Net, UNet, FCN, and manual segmentation methods (R = 0.77, 0.74, 0.76, respectively) with a lower mean DSC (0.85 ± 0.13, 0.84 ± 0.16, 0.79 ± 0.17, respectively). Additionally, the proposed DenseV-Net method was strongly correlated with the manual analysis in slice-based LV function quantification compared with the state-of-art neural network methods V-Net, UNet, and FCN. Conclusion: The proposed DenseV-Net method outperforms the classic convolutional networks V-Net, UNet, and FCN in automated LV segmentation, providing a novel way for efficient heart functional quantification and the diagnosis of cardiac diseases using cine MRI.

Left ventricular segmentation based on a parallel watershed transformation towards an accurate heart function evaluation

Magnetic resonance imaging (MRI) has emerged as the golden reference for cardiac examination. This modality allows the assessment of human cardiovascular morphology, functioning, and perfusion. Although a couple of challenging issues, such as the cardiac magnetic resonance (MR) image's features and the large variability of images among several patients, still influences the cardiac cavities’ segmentation and needs to be carried out. In this study, the authors have profoundly reviewed and fully compared semi-automated segmentation methods performed on cardiac cine-MR short-axis images for the evaluation of the left ventricular functions. However, the number of parameters handled by the synthesised works is limited if not null. For the sake of ensuring the highest coverage of the left ventricle parameters computing, they have introduced a parallel watershed-based approach to segment the left ventricular allowing hence the computation of six parameters (end-diastolic volume, end-systolic volume, ejection fraction, cardiac output, stroke volume, and left ventricular mass). An algorithm is associated with the main considered measurements. The experimental results that were obtained through studying 20 patients’ MRI data base demonstrate their approach's accuracy in estimating real values of the parameters’ set thanks to a faithful segmentation of the myocardium.

3D Hermite Transform Optical Flow Estimation inLeft Ventricle CT Sequences.

Heart diseases are the most important causes of death in the world and over the years, the study of cardiac movement has been carried out mainly in two dimensions, however, it is important to consider that the deformations due to the movement of the heart occur in a three-dimensional space. The analysis allows to describe most of the motions of the heart, for example, the twisting motion that takes place on every beat cycle that allows us identifying abnormalities of the heart walls. Therefore, it is necessary to develop algorithms that help specialists understand the cardiac movement. In this work, we developed a new approach to determine the cardiac movement in three dimensions using a differential optical flow approach in which we use the steered Hermite transform (SHT) which allows us to decompose cardiac volumes taking advantage of it as a model of the human vision system (HVS). Our proposal was tested in complete cardiac computed tomography (CT) volumes ( ), as well as its respective left ventricular segmentation. The robustness to noise was tested with good results. The evaluation of the results was carried out through errors in forwarding reconstruction, from the volume at time t to time using the optical flow obtained (interpolation errors). The parameters were tuned extensively. In the case of the 2D algorithm, the interpolation errors and normalized interpolation errors are very close and below the values reported in ground truth flows. In the case of the 3D algorithm, the results were compared with another similar method in 3D and the interpolation errors remained below 0.1. These results of interpolation errors for complete cardiac volumes and the left ventricle are shown graphically for clarity. Finally, a series of graphs are observed where the characteristic of contraction and dilation of the left ventricle is evident through the representation of the 3D optical flow.

A Semi-supervised Joint Network for Simultaneous Left Ventricular Motion Tracking and Segmentation in 4D Echocardiography.

This work presents a novel deep learning method to combine segmentation and motion tracking in 4D echocardiography. The network iteratively trains a motion branch and a segmentation branch. The motion branch is initially trained entirely unsupervised and learns to roughly map the displacements between a source and a target frame. The estimated displacement maps are then used to generate pseudo-ground truth labels to train the segmentation branch. The labels predicted by the trained segmentation branch are fed back into the motion branch and act as landmarks to help retrain the branch to produce smoother displacement estimations. These smoothed out displacements are then used to obtain smoother pseudo-labels to retrain the segmentation branch. Additionally, a biomechanically-inspired incompressibility constraint is implemented in order to encourage more realistic cardiac motion. The proposed method is evaluated against other approaches using synthetic and in-vivo canine studies. Both the segmentation and motion tracking results of our model perform favorably against competing methods.

P1590 Regional differences in longitudinal strain and response to adenosine stress in patients with myocardial infarction and ST-segment elevation. Results from Extreme trial

Abstract Background Global longitudinal strain (LS) is a sensitive marker of ischemic myocardial damage and predicts adverse left ventricular (LV) remodeling and outcome, independently of infarct size. In healthy subjects, regional LS increases from LV base to apex and enhances under physical or pharmacological stress, while in ST-elevation myocardial infarction (STEMI), response to dobutamine depends on transmurality of necrosis. It is known that coronary flow reserve during adenosine (ADN) is impaired both in ischemic and remote myocardium, but effect of ADN on strain reserve has never been investigated. Similarly, LS response to ADN in ischemic (iLS) and remote (rLS) myocardium and their relative contribution to LV function and remodeling are still unknown. Methods 61 consecutive patients with first STEMI (26 anterior, 29 inferior, 6 lateral), treated by successful primary percutaneous coronary intervention (PCI) followed by PCI of non-culprit coronary arteries, underwent rest and stress ADN (140 mcg/kg/minutes in 90 seconds) echocardiography at discharge (7 ± 2 days after admission). LV end-diastolic volume indexed for body surface area (EDV), ejection fraction (EF) and wall motion score index (WMSI) were measured at rest, while GLS, iLS and rLS analysis was performed both at rest and during stress. Ischemic and remote myocardium was allocated, by standard LV segmentation, basing on the culprit coronary artery. Results Significant differences existed among anterior, inferior and lateral STEMI in median (iQr) EDV [52 (45-59) vs 45 (36-51) vs 48 (45–56) ml, respectively, p=.034 overall], EF [47 (37-58) vs 58 (53–61) vs 56 (46-60)%, respectively, p=.002 overall], WMSI [1.63 (1.38–2) vs 1.25 (1.19-1.47) vs 1.41 (1.30-1.75), respectively, p=.001 overall]. GLS differed among anterior, inferior and lateral STEMI both at rest [13.75 (11.63-16.1) vs 19.5 (17.15-22.4) vs 17.85 (17.02-19), respectively, p&amp;lt;.001 overall] and during ADN [14 (12.35-16.15) vs 19.5 (17.9–22.05) vs 15.95 (14.40-19.48), respectively, p&amp;lt;.001], but did not change within groups. No differences were found between rest and stress iLS in any group. Similarly, rLS remained unchanged in anterior and inferior STEMI, and impaired after ADN in lateral STEMI [15.90 (11.45-18) at stress vs 16.8 (15.25-19.2) at rest, p=.043]. Inferior STEMI showed better iLS than anterior STEMI both at rest [17 (15.1–19.9) vs 13.75 (11.46-16.92), respectively, p=.001] and during stress [16.2 (15–20.4) vs 14.42 (12.67-15.83), respectively, p=.001]. Conclusions In the subacute phase of STEMI, GLS, iLS and rLS are heterogeneous and depend on infarct site. After ADN, there is no strain reserve in ischemic neither in remote myocardium. This may reflect regional differences in the response of microcirculation and myocardium to ischemia or may underlie pre-existing pathophysiological differences in the coronary circulation

Accuracy and Time-Efficiency of an Automated Software Tool to Assess Left Ventricular Parameters in Cardiac Magnetic Resonance Imaging.

Routine manual tracing of cardiac contours is time-consuming and subject to variability. A fully automated software tool may improve reading efficiency. This study was performed to assess the accuracy, reliability, and time-efficiency of a fully automated left ventricular (LV) segmentation software tool to calculate LV volumes and function compared with conventional manual contouring. Sixty-seven consecutive patients (53 male, mean age 62.5±10.9 y) underwent adenosine stress/rest perfusion cardiac magnetic resonance examination to rule out myocardial ischemia. Double-oblique short-axis 6-mm slice thickness steady-state free precession cine images were acquired to assess LV ejection fraction (EF), end-diastolic volume (EDV), end-systolic volume (ESV), and stroke volume (SV) using manual contour tracing and a recently developed fully automated software tool. The length of time needed to obtain LV volumes with each segmentation method was also compared. Compared with manual contouring, the fully automated software tool minimally underestimated LV-EF (mean difference of 2.9%±3.9%) and SV (mean difference of 4.4±8.5 mL) and slightly overestimated ESV (mean difference of -6.4±10.8 mL) and LV mass (mean difference of -14±20.4 g). EDV quantification did not statistically differ. Reliability for EF (concordance correlation coefficient [CCC]=0.92, 95% confidence interval [CI], 0.88-0.95), EDV (CCC=0.98, 95% CI, 0.97-0.99), ESV (CCC=0.96, 95% CI, 0.94-0.97), SV (CCC=0.93, 95% CI, 0.89-0.95), and LV mass (CCC=0.84, 95% CI, 0.76-0.89) was very good. The evaluated software allowed to quantify LV parameters with a 79% reduction in the time required for manual contouring (414.7±91 s vs. 85±16.1 s, respectively, P<0.001). Quantification of LV volumes using the evaluated fully automated segmentation software is accurate and time-efficient.