Heart Segmentation Research Articles

A cascaded framework with cross-modality transfer learning for whole heart segmentation

Automatic and accurate segmentation of the whole heart structure from 3D cardiac images plays an important role in helping physicians diagnose and treat cardiovascular disease. However, the time-consuming and laborious manual labeling of the heart images results in the inefficiency of utilizing the existing CT or MRI for training the deep learning network, which decrease the accuracy of whole heart segmentation. However, multi-modality data contains multi-level information of cardiac images due to different imaging mechanisms, which is beneficial to improve the segmentation accuracy. Therefore, this paper proposes a cascaded framework with cross-modality transfer learning for whole heart segmentation (CM-TranCaF), which consists of three key modules: modality transfer network (MTN), U-shaped multi-attention network (MAUNet) and spatial configuration network (SCN). In MTN, MRI images are transferred from MRI domain to CT domain, to increase the data volume by adopting the idea of adversarial training. The MAUNet is designed based on UNet, while the attention gates (AGs) are integrated into the skip connection to reduce the weight of background pixels. Moreover, to solve the problem of boundary blur, the position attention block (PAB) is also integrated into the bottom layer to aggregate similar features. Finally, the SCN is used to finetune the segmentation results by utilizing the anatomical information between different cardiac substructures. By evaluating the proposed method on the dataset of the MM-WHS challenge, CM-TranCaF achieves a Dice score of 91.1% on the testing dataset. The extensive experimental results prove the effectiveness of the proposed method compared to other state-of-the-art methods.

Automatic measurement of Cardiothoracic Ratio in chest X-ray images with ProGAN-Generated dataset

CT Cardiomegaly could be identified using the CTR (Cardiothoracic Ratio), which could be assessed on a chest image or X-ray. It is determined using the link between the size of the heart and chest’s transverse dimension. When the ratio exceeds a certain threshold, cardiomegaly is diagnosed. The objective of the study is to offer an approach for calculating the ratio for categorizing cardiomegaly within chest X-ray pictures. The suggested method begins by building heart and lung segmentation models on the basis of U-Net design utilizing publicly accessible datasets containing lung and heart mask ground truth. The segmented lung and heart portion sizes are then used to calculate the ratio. Additionally, chest X-ray images from 3 classes-cardiomegaly, female,and male normal - are created using a novel dataset using PGAN (Progressive Growing of GANs). This dataset is then utilized to evaluate the suggested solution. The suggested approach is also utilized to assess the quality of PGAN-generated chest X-ray pictures. In the trials, lung and heart areas in chest images of X-rays are segmented using trained models and a self-gathered dataset. The computed values of CTR are contrasted with those that were manually assessed by specialists. The average inaccuracy is 3.08 percent. The models are then used to segment areas of the lung and heart for CTR computation on the PGAN dataset. The cardiomegaly is then measured utilizing multiple attempts with varying cut-off threshold values. The proposed approach yields 94.20 percent specificity,88.31% sensitivity, and 94.61% accuracy with the usual cut-off of 0.50. The suggested approach is shown to be resilient across hitherto unexplored datasets for computation of CTR, segmentation, as well as cardiomegaly classification, such as the PGAN dataset. To increase sensitivity, modify the cut-off value to be less than 0.50. The proposed solution is then assessed from a variety of angles, such as lung and heart segmentation, CTR computation, as well as cardiomegaly classification. Tests are also carried out on publicly available datasets, self-collected datasets, as well as ProGAN- reconstructed datasets.

MWG-UNet: Hybrid Deep Learning Framework for Lung Fields and Heart Segmentation in Chest X-ray Images.

Deep learning technology has achieved breakthrough research results in the fields of medical computer vision and image processing. Generative adversarial networks (GANs) have demonstrated a capacity for image generation and expression ability. This paper proposes a new method called MWG-UNet (multiple tasking Wasserstein generative adversarial network U-shape network) as a lung field and heart segmentation model, which takes advantages of the attention mechanism to enhance the segmentation accuracy of the generator so as to improve the performance. In particular, the Dice similarity, precision, and F1 score of the proposed method outperform other models, reaching 95.28%, 96.41%, and 95.90%, respectively, and the specificity surpasses the sub-optimal models by 0.28%, 0.90%, 0.24%, and 0.90%. However, the value of the IoU is inferior to the optimal model by 0.69%. The results show the proposed method has considerable ability in lung field segmentation. Our multi-organ segmentation results for the heart achieve Dice similarity and IoU values of 71.16% and 74.56%. The segmentation results on lung fields achieve Dice similarity and IoU values of 85.18% and 81.36%.

Shape-Aware Joint Distribution Alignment for Cross-Domain Image Segmentation.

We present an unsupervised domain adaptation method for image segmentation which aligns high-order statistics, computed for the source and target domains, encoding domain-invariant spatial relationships between segmentation classes. Our method first estimates the joint distribution of predictions for pairs of pixels whose relative position corresponds to a given spatial displacement. Domain adaptation is then achieved by aligning the joint distributions of source and target images, computed for a set of displacements. Two enhancements of this method are proposed. The first one uses an efficient multi-scale strategy that enables capturing long-range relationships in the statistics. The second one extends the joint distribution alignment loss to features in intermediate layers of the network by computing their cross-correlation. We test our method on the task of unpaired multi-modal cardiac segmentation using the Multi-Modality Whole Heart Segmentation Challenge dataset and prostate segmentation task where images from two datasets are taken as data in different domains. Our results show the advantages of our method compared to recent approaches for cross-domain image segmentation. Code is available at https://github.com/WangPing521/Domain_adaptation_shape_prior.

An Improved Combination of Faster R-CNN and U-Net Network for Accurate Multi-Modality Whole Heart Segmentation.

Detailed information of substructures of the whole heart is usually vital in the diagnosis of cardiovascular diseases and in 3D modeling of the heart. Deep convolutional neural networks have been demonstrated to achieve state-ofthe-art performance in 3D cardiac structures segmentation. However, when dealing with high-resolution 3D data, current methods employing tiling strategies usually degrade segmentation performances due to GPU memory constraints. This work develops a two-stage multi-modality whole heart segmentation strategy, which adopts an improved Combination of Faster R-CNN and 3D U-Net (CFUN+). More specifically, the bounding box of the heart is first detected by Faster R-CNN, and then the original Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) images of the heart aligned with the bounding box are input into 3D U-Net for segmentation. The proposed CFUN+ method redefines the bounding box loss function by replacing the previous Intersection over Union (IoU) loss with Complete Intersection over Union (CIoU) loss. Meanwhile, the integration of the edge loss makes the segmentation results more accurate, and also improves the convergence speed. The proposed method achieves an average Dice score of 91.1% on the Multi-Modality Whole Heart Segmentation (MM-WHS) 2017 challenge CT dataset, which is 5.2% higher than the baseline CFUN model, and achieves state-of-the-art segmentation results. In addition, the segmentation speed of a single heart has been dramatically improved from a few minutes to less than 6 seconds.

A New Framework of Swarm Learning Consolidating Knowledge From Multi-Center Non-IID Data for Medical Image Segmentation

Large training datasets are important for deep learning-based methods. For medical image segmentation, it could be however difficult to obtain large number of labeled training images solely from one center. Distributed learning, such as swarm learning, has the potential to use multi-center data without breaching data privacy. However, data distributions across centers can vary a lot due to the diverse imaging protocols and vendors (known as feature skew). Also, the regions of interest to be segmented could be different, leading to inhomogeneous label distributions (referred to as label skew). With such non-independently and identically distributed (Non-IID) data, the distributed learning could result in degraded models. In this work, we propose a novel swarm learning approach, which assembles local knowledge from each center while at the same time overcomes forgetting of global knowledge during local training. Specifically, the approach first leverages a label skew-awared loss to preserve the global label knowledge, and then aligns local feature distributions to consolidate global knowledge against local feature skew. We validated our method in three Non-IID scenarios using four public datasets, including the Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation (M&Ms) dataset, the Federated Tumor Segmentation (FeTS) dataset, the Multi-Modality Whole Heart Segmentation (MMWHS) dataset and the Multi-Site Prostate T2-weighted MRI segmentation (MSProsMRI) dataset. Results show that our method could achieve superior performance over existing methods. Code will be released via https://zmiclab.github.io/projects.html once the paper gets accepted.

Automatic measurement of cardiothoracic ratio in chest x-ray images with ProGAN-generated dataset

PurposeThe cardiomegaly can be determined by the cardiothoracic ratio (CTR) which can be measured in a chest x-ray image. It is calculated based on a relationship between a size of heart and a transverse dimension of chest. The cardiomegaly is identified when the ratio is larger than a cut-off threshold. This paper aims to propose a solution to calculate the ratio for classifying the cardiomegaly in chest x-ray images.Design/methodology/approachThe proposed method begins with constructing lung and heart segmentation models based on U-Net architecture using the publicly available datasets with the groundtruth of heart and lung masks. The ratio is then calculated using the sizes of segmented lung and heart areas. In addition, Progressive Growing of GANs (PGAN) is adopted here for constructing the new dataset containing chest x-ray images of three classes including male normal, female normal and cardiomegaly classes. This dataset is then used for evaluating the proposed solution. Also, the proposed solution is used to evaluate the quality of chest x-ray images generated from PGAN.FindingsIn the experiments, the trained models are applied to segment regions of heart and lung in chest x-ray images on the self-collected dataset. The calculated CTR values are compared with the values that are manually measured by human experts. The average error is 3.08%. Then, the models are also applied to segment regions of heart and lung for the CTR calculation, on the dataset computed by PGAN. Then, the cardiomegaly is determined using various attempts of different cut-off threshold values. With the standard cut-off at 0.50, the proposed method achieves 94.61% accuracy, 88.31% sensitivity and 94.20% specificity.Originality/valueThe proposed solution is demonstrated to be robust across unseen datasets for the segmentation, CTR calculation and cardiomegaly classification, including the dataset generated from PGAN. The cut-off value can be adjusted to be lower than 0.50 for increasing the sensitivity. For example, the sensitivity of 97.04% can be achieved at the cut-off of 0.45. However, the specificity is decreased from 94.20% to 79.78%.

Deep learning-based image segmentation model using an MRI-based convolutional neural network for physiological evaluation of the heart.

Background and Objective: Cardiovascular disease is a high-fatality health issue. Accurate measurement of cardiovascular function depends on precise segmentation of physiological structure and accurate evaluation of functional parameters. Structural segmentation of heart images and calculation of the volume of different ventricular activity cycles form the basis for quantitative analysis of physiological function and can provide the necessary support for clinical physiological diagnosis, as well as the analysis of various cardiac diseases. Therefore, it is important to develop an efficient heart segmentation algorithm. Methods: A total of 275 nuclear magnetic resonance imaging (MRI) heart scans were collected, analyzed, and preprocessed from Huaqiao University Affiliated Strait Hospital, and the data were used in our improved deep learning model, which was designed based on the U-net network. The training set included 80% of the images, and the remaining 20% was the test set. Based on five time phases from end-diastole (ED) to end-systole (ES), the segmentation findings showed that it is possible to achieve improved segmentation accuracy and computational complexity by segmenting the left ventricle (LV), right ventricle (RV), and myocardium (myo). Results: We improved the Dice index of the LV to 0.965 and 0.921, and the Hausdorff index decreased to 5.4 and 6.9 in the ED and ES phases, respectively; RV Dice increased to 0.938 and 0.860, and the Hausdorff index decreased to 11.7 and 12.6 in the ED and ES, respectively; myo Dice increased to 0.889 and 0.901, and the Hausdorff index decreased to 8.3 and 9.2 in the ED and ES, respectively. Conclusion: The model obtained in the final experiment provided more accurate segmentation of the left and right ventricles, as well as the myocardium, from cardiac MRI. The data from this model facilitate the prediction of cardiovascular disease in real-time, thereby providing potential clinical utility.

Acoustic HMMs to Detect Abnormal Respiration with Limited Training Data

In many situations, abnormal sounds, called adventitious sounds, are included with the lung sounds of a subject suffering from pulmonary diseases. Thus, a method to automatically detect abnormal sounds in auscultation was proposed. The acoustic features of normal lung sounds for control subjects and abnormal lung sounds for patients are expressed using hidden markov models (HMMs) to distinguish between normal and abnormal lung sounds. Furthermore, abnormal sounds were detected in a noisy environment, including heart sounds, using a heart-sound model. However, the F1-score obtained in detecting abnormal respiration was low (0.8493). Moreover, the duration and acoustic properties of segments of respiratory, heart, and adventitious sounds varied. In our previous method, the appropriate HMMs for the heart and adventitious sound segments were constructed. Although the properties of the types of adventitious sounds varied, an appropriate topology for each type was not considered. In this study, appropriate HMMs for the segments of each type of adventitious sound and other segments were constructed. The F1-score was increased (0.8726) by selecting a suitable topology for each segment. The results demonstrate the effectiveness of the proposed method.

Machine Learning Based on Computed Tomography Pulmonary Angiography in Evaluating Pulmonary Artery Pressure in Patients with Pulmonary Hypertension

Right heart catheterization is the gold standard for evaluating hemodynamic parameters of pulmonary circulation, especially pulmonary artery pressure (PAP) for diagnosis of pulmonary hypertension (PH). However, the invasive and costly nature of RHC limits its widespread application in daily practice. To develop a fully automatic framework for PAP assessment via machine learning based on computed tomography pulmonary angiography (CTPA). A machine learning model was developed to automatically extract morphological features of pulmonary artery and the heart on CTPA cases collected between June 2017 and July 2021 based on a single center experience. Patients with PH received CTPA and RHC examinations within 1 week. The eight substructures of pulmonary artery and heart were automatically segmented through our proposed segmentation framework. Eighty percent of patients were used for the training data set and twenty percent for the independent testing data set. PAP parameters, including mPAP, sPAP, dPAP, and TPR, were defined as ground-truth. A regression model was built to predict PAP parameters and a classification model to separate patients through mPAP and sPAP with cut-off values of 40 mm Hg and 55 mm Hg in PH patients, respectively. The performances of the regression model and the classification model were evaluated by analyzing the intraclass correlation coefficient (ICC) and the area under the receiver operating characteristic curve (AUC). Study participants included 55 patients with PH (men 13; age 47.75 ± 14.87 years). The average dice score for segmentation increased from 87.3% ± 2.9 to 88.2% ± 2.9 through proposed segmentation framework. After features extraction, some of the AI automatic extractions (AAd, RVd, LAd, and RPAd) achieved good consistency with the manual measurements. The differences between them were not statistically significant (t = 1.222, p = 0.227; t = -0.347, p = 0.730; t = 0.484, p = 0.630; t = -0.320, p = 0.750, respectively). The Spearman test was used to find key features which are highly correlated with PAP parameters. Correlations between pulmonary artery pressure and CTPA features show a high correlation between mPAP and LAd, LVd, LAa (r = 0.333, p = 0.012; r = -0.400, p = 0.002; r = -0.208, p = 0.123; r = -0.470, p = 0.000; respectively). The ICC between the output of the regression model and the ground-truth from RHC of mPAP, sPAP, and dPAP were 0.934, 0.903, and 0.981, respectively. The AUC of the receiver operating characteristic curve of the classification model of mPAP and sPAP were 0.911 and 0.833. The proposed machine learning framework on CTPA enables accurate segmentation of pulmonary artery and heart and automatic assessment of the PAP parameters and has the ability to accurately distinguish different PH patients with mPAP and sPAP. Results of this study may provide additional risk stratification indicators in the future with non-invasive CTPA data.

Combining generative modelling and semi-supervised domain adaptation for whole heart cardiovascular magnetic resonance angiography segmentation

BackgroundQuantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA), few methods exist for whole-heart cardiovascular magnetic resonance angiograms (CMRA) which are more challenging due to variable contrast, lower signal to noise ratio and a limited amount of labeled data. MethodsTwo state-of-the-art unsupervised generative deep learning domain adaptation architectures, generative adversarial networks and variational auto-encoders, were applied to 3D whole heart segmentation of both conventional (n = 20) and high-resolution (n = 45) CMRA (target) images, given segmented CTA (source) images for training. An additional supervised loss function was implemented to improve performance given 10%, 20% and 30% segmented CMRA cases. A fully supervised nn-UNet trained on the given CMRA segmentations was used as the benchmark. ResultsThe addition of a small number of segmented CMRA training cases substantially improved performance in both generative architectures in both standard and high-resolution datasets. Compared with the nn-UNet benchmark, the generative methods showed substantially better performance in the case of limited labelled cases. On the standard CMRA dataset, an average 12% (adversarial method) and 10% (variational method) improvement in Dice score was obtained. ConclusionsUnsupervised domain-adaptation methods for CMRA segmentation can be boosted by the addition of a small number of supervised target training cases. When only few labelled cases are available, semi-supervised generative modelling is superior to supervised methods.

Dilated convolution network with edge fusion block and directional feature maps for cardiac MRI segmentation.

Cardiac magnetic resonance imaging (MRI) segmentation task refers to the accurate segmentation of ventricle and myocardium, which is a prerequisite for evaluating the soundness of cardiac function. With the development of deep learning in medical imaging, more and more heart segmentation methods based on deep learning have been proposed. Due to the fuzzy boundary and uneven intensity distribution of cardiac MRI, some existing methods do not make full use of multi-scale characteristic information and have the problem of ambiguity between classes. In this paper, we propose a dilated convolution network with edge fusion block and directional feature maps for cardiac MRI segmentation. The network uses feature fusion module to preserve boundary information, and adopts the direction field module to obtain the feature maps to improve the original segmentation features. Firstly, multi-scale feature information is obtained and fused through dilated convolutional layers of different scales while downsampling. Secondly, in the decoding stage, the edge fusion block integrates the edge features into the side output of the encoder and concatenates them with the upsampled features. Finally, the concatenated features utilize the direction field to improve the original segmentation features and generate the final result. Our propose method conducts comprehensive comparative experiments on the automated cardiac diagnosis challenge (ACDC) and myocardial pathological segmentation (MyoPS) datasets. The results show that the proposed cardiac MRI segmentation method has better performance compared to other existing methods.

Three-Dimensional-Enabled Surgical Planning for the Correction of Right Partial Anomalous Pulmonary Venous Return.

Objectives: The surgical technique for right partial anomalous pulmonary venous return (PAPVR) depends on the location of the anomalous pulmonary veins (PVs). With this in mind, we sought to evaluate the impact of 3D heart segmentation and reconstruction on preoperative surgical planning. Methods: A retrospective study was conducted on all patients who underwent PAPVR repair at our institution between January 2018 and October 2021; three-dimensional segmentations and reconstructions of all the heart anatomies were performed. A score (the PAPVR score) was established and calculated using two anatomical parameters (the distance between the most cranial anomalous PV and the superior rim of the sinus venosus defect/the sum of the latter and the distance between the PV and the azygos vein) to predict the type of correction. Results: A total of 30 patients were included in the study. The PAPVR score was found to be a good predictor of the type of surgery performed. A value > 0.68 was significantly associated with a Warden procedure (p < 0.001) versus single/double patch repair. Conclusions: Three-dimensional heart segmentations and reconstructions improve the quality of surgical planning in the case of PAPVR and allow for the introduction of a score that may facilitate surgical decisions on the type of repair required.

GUDU: Geometrically-constrained Ultrasound Data augmentation in U-Net for echocardiography semantic segmentation

Echocardiography is a very important medical examination that helps in the computation of critical heart functions. Boundary identification, segmentation and estimation of the volume of key parts of the heart, especially the left ventricle, is a difficult and time-consuming process, even for the most experienced cardiologists. In recent years, research has focused on the automatic segmentation of heart through artificial intelligence techniques and especially with the use of deep learning. Our work is part of this framework.We implemented an ensemble of convolutional neural networks based on the U-net architecture, trained it using a public dataset of cardiac ultrasound images, and combined the outcomes to extract the areas of the left ventricle, myocardium and left atrium. In order to optimize the training process, we have developed a significant data augmentation method based on medical practice. Furthermore, we extended the Dice loss function by imposing additional mandatory anatomical constraints. An ablation study highlights the contribution of each of our proposed modules.The evaluation of our method showed an overall improvement in segmentation accuracy but also in the estimation of clinical metrics. Specifically, using the Dice coefficient for geometric metrics, we achieved for the epicardium a score of 0.96 and 0.955 for the end-diastolic and end-systolic phase respectively. For the clinical metrics of the left ventricle volume, the Pearson correlation coefficient was used where our method gave 0.977, 0.981, 0.897 for the end-diastolic, end-systolic phase and ejection fraction respectively. Scores which up until the writing of this article outperform competitive methods.

Three-Dimensional Heart Segmentation and Absolute Quantitation of Cardiac 123I-metaiodobenzylguanidine Sympathetic Imaging Using SPECT/CT.

Background: A three-dimensional (3D) approach to absolute quantitation of 123I-metaiodobenzylguanidine (MIBG) sympathetic nerve imaging using single-photon emission tomography (SPECT) / computed tomography (CT) is not available. Therefore, we calculated absolute cardiac counts and standardized uptake values (SUVs) from images of 72 consecutive patients with cardiac and neurological diseases using 123I-MIBG SPECT/CT and compared them with conventional planar quantitation. We aimed to develop new methods for 3D heart segmentation and the quantitation of these diseases. Methods: We manually segmented early and late SPECT/CT images of the heart in 3D, then calculated mean (SUVmean) and maximum (SUVmax) SUVs. We analyzed correlations between SUVs and planar heart-to-mediastinum ratios (HMRs), and between washout rates (WRs) derived from the SUVs and planar data. We also categorized WRs as normal or abnormal using linear regression lines determined by the relationship between SPECT/CT and planar WRs, and assessed agreement between them. Results: We calculated SUVmean and SUVmax from all early and late 123I-MIBG SPECT/CT images. Planar HMRs correlated with early and late SUVmean (R2=0.59 and 0.73, respectively) and SUVmax (R2=0.46 and 0.60, respectively; both p<0.0001). The SPECT/CT WRs determined based on SUVmean and SUVmax (R2=0.79 and 0.45, p<0.0001) closely correlated with planar WRs. Agreement of high and low WRs between planar WRs and SPECT/CT WRs calculated using SUVmax and SUVmean reached 88.1% and 94.4% respectively. Conclusions: We found that sympathetic nervous activity could be absolutely quantified in 3D from 123I-MIBG SPECT/CT images. Therefore, we propose a new method for quantifying sympathetic innervation on SPECT/CT images.

MRDFF: A deep forest based framework for CT whole heart segmentation.

Automatic whole heart segmentation plays an important role in the treatment and research of cardiovascular diseases. In this paper, we propose an improved Deep Forest framework, named Multi-Resolution Deep Forest Framework (MRDFF), which accomplishes whole heart segmentation in two stages. We extract the heart region by binary classification in the first stage, thus avoiding the class imbalance problem caused by too much background. The results of the first stage are then subdivided in the second stage to obtain accurate cardiac substructures. In addition, we also propose hybrid feature fusion, multi-resolution fusion and multi-scale fusion to further improve the segmentation accuracy. Experiments on the public dataset MM-WHS show that our model can achieve comparable accuracy in about half the training time of neural network models.

LMISA: A lightweight multi-modality image segmentation network via domain adaptation using gradient magnitude and shape constraint.

In medical image segmentation, supervised machine learning models trained using one image modality (e.g. computed tomography (CT)) are often prone to failure when applied to another image modality (e.g. magnetic resonance imaging (MRI)) even for the same organ. This is due to the significant intensity variations of different image modalities. In this paper, we propose a novel end-to-end deep neural network to achieve multi-modality image segmentation, where image labels of only one modality (source domain) are available for model training and the image labels for the other modality (target domain) are not available. In our method, a multi-resolution locally normalized gradient magnitude approach is firstly applied to images of both domains for minimizing the intensity discrepancy. Subsequently, a dual task encoder-decoder network including image segmentation and reconstruction is utilized to effectively adapt a segmentation network to the unlabeled target domain. Additionally, a shape constraint is imposed by leveraging adversarial learning. Finally, images from the target domain are segmented, as the network learns a consistent latent feature representation with shape awareness from both domains. We implement both 2D and 3D versions of our method, in which we evaluate CT and MRI images for kidney and cardiac tissue segmentation. For kidney, a public CT dataset (KiTS19, MICCAI 2019) and a local MRI dataset were utilized. The cardiac dataset was from the Multi-Modality Whole Heart Segmentation (MMWHS) challenge 2017. Experimental results reveal that our proposed method achieves significantly higher performance with a much lower model complexity in comparison with other state-of-the-art methods. More importantly, our method is also capable of producing superior segmentation results than other methods for images of an unseen target domain without model retraining. The code is available at GitHub (https://github.com/MinaJf/LMISA) to encourage method comparison and further research.

Two-Stage CNN Whole Heart Segmentation Combining Image Enhanced Attention Mechanism and Metric Classification.

Accurate segmentation of multiple tissues and organs in cardiac medical imaging is of great value in computer-aided cardiovascular diagnosis. However, it is challenging due to the complex distribution of various tissues and organs in cardiac MRI (magnetic resonance imaging) slices, low discriminative and large spanning organs. To handle these problems, a two-stage CNN (convolutional neural network) segmentation method based on the combination of Log-Gabor filter attention mechanism and metric classification is proposed. The Log-Gabor filterbank is applied to selectively enhance the texture information and contour information of each tissue and organ, and the spatial and channel attention mechanism jointly with the varying kernel size of Log-Gabor filterbank is incorporated into the codec structure to adaptively extract target features of different sizes and focus on the discriminative features in the network. To solve the problem of insufficient segmentation on subtle and adherent edges involving different tissues, a metric classification network is incorporated to finely optimize the hard-to-be-segmented boundaries. The proposed method was tested on cardiac MRI data set to segment 7 cardiac tissues, and the rationality and effectiveness of the method were verified. In comparison to a series of deep learning-based segmentation models, the proposed method achieves competitive performance.

Fully automatic cardiac four chamber and great vessel segmentation on CT pulmonary angiography using deep learning.

IntroductionComputed tomography pulmonary angiography (CTPA) is an essential test in the work-up of suspected pulmonary vascular disease including pulmonary hypertension and pulmonary embolism. Cardiac and great vessel assessments on CTPA are based on visual assessment and manual measurements which are known to have poor reproducibility. The primary aim of this study was to develop an automated whole heart segmentation (four chamber and great vessels) model for CTPA.MethodsA nine structure semantic segmentation model of the heart and great vessels was developed using 200 patients (80/20/100 training/validation/internal testing) with testing in 20 external patients. Ground truth segmentations were performed by consultant cardiothoracic radiologists. Failure analysis was conducted in 1,333 patients with mixed pulmonary vascular disease. Segmentation was achieved using deep learning via a convolutional neural network. Volumetric imaging biomarkers were correlated with invasive haemodynamics in the test cohort.ResultsDice similarity coefficients (DSC) for segmented structures were in the range 0.58–0.93 for both the internal and external test cohorts. The left and right ventricle myocardium segmentations had lower DSC of 0.83 and 0.58 respectively while all other structures had DSC >0.89 in the internal test cohort and >0.87 in the external test cohort. Interobserver comparison found that the left and right ventricle myocardium segmentations showed the most variation between observers: mean DSC (range) of 0.795 (0.785–0.801) and 0.520 (0.482–0.542) respectively. Right ventricle myocardial volume had strong correlation with mean pulmonary artery pressure (Spearman's correlation coefficient = 0.7). The volume of segmented cardiac structures by deep learning had higher or equivalent correlation with invasive haemodynamics than by manual segmentations. The model demonstrated good generalisability to different vendors and hospitals with similar performance in the external test cohort. The failure rates in mixed pulmonary vascular disease were low (<3.9%) indicating good generalisability of the model to different diseases.ConclusionFully automated segmentation of the four cardiac chambers and great vessels has been achieved in CTPA with high accuracy and low rates of failure. DL volumetric biomarkers can potentially improve CTPA cardiac assessment and invasive haemodynamic prediction.

The Effect of Segmentation Variability in Forward ECG Simulation.

Segmentation of patient-specific anatomical models is one of the first steps in Electrocardiographic imaging (ECGI). However, the effect of segmentation variability on ECGI remains unexplored. In this study, we assess the effect of heart segmentation variability on ECG simulation. We generated a statistical shape model from segmentations of the same patient and generated 262 cardiac geometries to run in an ECG forward computation of body surface potentials (BSPs) using an equivalent dipole layer cardiac source model and 5 ventricular stimulation protocols. Variability between simulated BSPs for all models and protocols was assessed using Pearson's correlation coefficient (CC). Compared to the BSPs of the mean cardiac shape model, the lowest variability (average CC = 0.98 ± 0.03) was found for apical pacing whereas the highest variability (average CC = 0.90 ± 0.23) was found for right ventricular free wall pacing. Furthermore, low amplitude BSPs show a larger variation in QRS morphology compared to high amplitude signals. The results indicate that the uncertainty in cardiac shape has a significant impact on ECGI.