Automatic segmentation of the right ventricle from cardiac MRI using a learning-based approach: Automatic Segmentation Using a Learning-Based Approach

Artificial intelligence: improving the efficiency of cardiovascular imaging

INTRODUCTION

Artificial intelligence (AI) describes the use of computational techniques to mimic human intelligence. In healthcare, this typically involves large medical datasets being used to predict a diagnosis, identify new disease genotypes or phenotypes, or guide treatment strategies. Noninvasive imaging remains a cornerstone for the diagnosis, risk stratification, and management of patients with cardiovascular disease. AI can facilitate every stage of the imaging process, from acquisition and reconstruction, to segmentation, measurement, interpretation, and subsequent clinical pathways.

AREAS COVERED

In this paper, we review state-of-the-art AI techniques and their current applications in cardiac imaging, and discuss the future role of AI as a precision medicine tool.

EXPERT OPINION

Cardiovascular medicine is primed for scalable AI applications which can interpret vast amounts of clinical and imaging data in greater depth than ever before. AI-augmented medical systems have the potential to improve workflow and provide reproducible and objective quantitative results which can inform clinical decisions. In the foreseeable future, AI may work in the background of cardiac image analysis software and routine clinical reporting, automatically collecting data and enabling real-time diagnosis and risk stratification.

Mini Review: Deep Learning for Atrial Segmentation From Late Gadolinium-Enhanced MRIs

Segmentation and 3D reconstruction of the human atria is of crucial importance for precise diagnosis and treatment of atrial fibrillation, the most common cardiac arrhythmia. However, the current manual segmentation of the atria from medical images is a time-consuming, labor-intensive, and error-prone process. The recent emergence of artificial intelligence, particularly deep learning, provides an alternative solution to the traditional methods that fail to accurately segment atrial structures from clinical images. This has been illustrated during the recent 2018 Atrial Segmentation Challenge for which most of the challengers developed deep learning approaches for atrial segmentation, reaching high accuracy (>90% Dice score). However, as significant discrepancies exist between the approaches developed, many important questions remain unanswered, such as which deep learning architectures and methods to ensure reliability while achieving the best performance. In this paper, we conduct an in-depth review of the current state-of-the-art of deep learning approaches for atrial segmentation from late gadolinium-enhanced MRIs, and provide critical insights for overcoming the main hindrances faced in this task.

Reference Ranges for Left Ventricular Curvedness and Curvedness-Based Functional Indices Using Cardiovascular Magnetic Resonance in Healthy Asian Subjects

Curvature-based three-dimensional cardiovascular magnetic resonance (CMR) allows regional function characterization without an external spatial frame of reference. However, introduction of this modality into clinical practice is hampered by lack of reference values. We aim to establish normal ranges for 3D left ventricular (LV) regional parameters in relation to age and gender for 171 healthy subjects. LV geometrical reconstruction and automatic calculation of regional parameters were implemented by in-house software (CardioWerkz) using stacks of short-axis cine slices. Parameter normal ranges were stratified by gender and age categories (≤44, 45-64, 65-74 and 75-84 years). Our software had excellent intra- and inter-observer agreement. Ageing was significantly associated with increases in end-systolic (ES) curvedness (C_ES) and area strain (AS) with higher rates of increase in males, end-diastolic (ED) and ES wall thickness (WT_ED, WT_ES) with higher rates of increase in females, and reductions in ED and ES wall stress indices (σ_i,ED) with higher rates of increase in females. Females exhibited greater ED curvedness, C_ES, σ_i,ED and AS than males, but smaller WT_ED and WT_ES. Age × gender interaction was not observed for any parameter. This study establishes age and gender specific reference values for 3D LV regional parameters using CMR without additional image acquisition.

Deep Learning for Cardiac Image Segmentation: A Review

Deep learning has become the most widely used approach for cardiac image segmentation in recent years. In this paper, we provide a review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound and major anatomical structures of interest (ventricles, atria, and vessels). In addition, a summary of publicly available cardiac image datasets and code repositories are included to provide a base for encouraging reproducible research. Finally, we discuss the challenges and limitations with current deep learning-based approaches (scarcity of labels, model generalizability across different domains, interpretability) and suggest potential directions for future research.

Automated Myocardial T2 and Extracellular Volume Quantification in Cardiac MRI Using Transfer Learning-based Myocardium Segmentation

Purpose

To assess the performance of an automated myocardial T2 and extracellular volume (ECV) quantification method using transfer learning of a fully convolutional neural network (CNN) pretrained to segment the myocardium on T1 mapping images.

Materials and Methods

A single CNN previously trained and tested using 11 550 manually segmented native T1-weighted images was used to segment the myocardium for automated myocardial T2 and ECV quantification. Reference measurements from 1525 manually processed T2 maps and 1525 ECV maps (from 305 patients) were used to evaluate the performance of the pretrained network. Correlation coefficient (R) and Bland-Altman analysis were used to assess agreement between automated and reference values on per-patient, per-slice, and per-segment analyses. Furthermore, transfer learning effectiveness in the CNN was evaluated by comparing its performance to four CNNs trained using manually segmented T2-weighted and postcontrast T1-weighted images and initialized using random-weights or weights of the pretrained CNN.

Results

T2 and ECV measurements using the pretrained CNN strongly correlated with reference values in per-patient (T2: R = 0.88, 95% confidence interval [CI]: 0.85, 0.91; ECV: R = 0.91, 95% CI: 0.89, 0.93), per-slice (T2: R = 0.83, 95% CI: 0.81, 0.85; ECV: R = 0.84, 95% CI: 0.82, 0.86), and per-segment (T2: R = 0.75, 95% CI: 0.74, 0.77; ECV: R = 0.76, 95% CI: 0.75, 0.77) analyses. In Bland-Altman analysis, the automatic and reference values were in good agreement in per-patient (T2: 0.3 msec ± 2.9; ECV: -0.3% ± 1.7), per-slice (T2: 0.1 msec ± 4.6; ECV: -0.3% ± 2.5), and per-segment (T2: 0.0 msec ± 6.5; ECV: -0.4% ± 3.5) analyses. The performance of the pretrained network was comparable to networks refined or trained from scratch using additional manually segmented images.

Conclusion

Transfer learning extends the utility of pretrained CNN-based automated native T1 mapping analysis to T2 and ECV mapping without compromising performance. Supplemental material is available for this article. © RSNA, 2020.

A Persistent Homology-Based Topological Loss Function for Multi-class CNN Segmentation of Cardiac MRI

With respect to spatial overlap, CNN-based segmentation of short axis cardiovascular magnetic resonance (CMR) images has achieved a level of performance consistent with inter observer variation. However, conventional training procedures frequently depend on pixel-wise loss functions, limiting optimisation with respect to extended or global features. As a result, inferred segmentations can lack spatial coherence, including spurious connected components or holes. Such results are implausible, violating the anticipated topology of image segments, which is frequently known a priori. Addressing this challenge, published work has employed persistent homology, constructing topological loss functions for the evaluation of image segments against an explicit prior. Building a richer description of segmentation topology by considering all possible labels and label pairs, we extend these losses to the task of multi-class segmentation. These topological priors allow us to resolve all topological errors in a subset of 150 examples from the ACDC short axis CMR training data set, without sacrificing overlap performance.

DW-Net: A cascaded convolutional neural network for apical four-chamber view segmentation in fetal echocardiography

Fetal echocardiography (FE) is a widely used medical examination for early diagnosis of congenital heart disease (CHD). The apical four-chamber view (A4C) is an important view among early FE images. Accurate segmentation of crucial anatomical structures in the A4C view is a useful and important step for early diagnosis and timely treatment of CHDs. However, it is a challenging task due to several unfavorable factors: (a) artifacts and speckle noise produced by ultrasound imaging. (b) category confusion caused by the similarity of anatomical structures and variations of scanning angles. (c) missing boundaries. In this paper, we propose an end-to-end DW-Net for accurate segmentation of seven important anatomical structures in the A4C view. The network comprises two components: 1) a Dilated Convolutional Chain (DCC) for "gridding issue" reduction, multi-scale contextual information aggregation and accurate localization of cardiac chambers. 2) a W-Net for gaining more precise boundaries and yielding refined segmentation results. Extensive experiments of the proposed method on a dataset of 895 A4C views have demonstrated that DW-Net can achieve good segmentation results, including the Dice Similarity Coefficient (DSC) of 0.827, the Pixel Accuracy (PA) of 0.933, the AUC of 0.990 and it substantially outperformed some well-known segmentation methods. Our work was highly valued by experienced clinicians. The accurate and automatic segmentation of the A4C view using the proposed DW-Net can benefit further extractions of useful clinical indicators in early FE and improve the prenatal diagnostic accuracy and efficiency of CHDs.

Evaluation of a Semi-automatic Right Ventricle Segmentation Method on Short-Axis MR Images

The purpose of this study was to evaluate a semi-automatic right ventricle segmentation method on short-axis cardiac cine MR images which segment all right ventricle contours in a cardiac phase using one seed contour. Twenty-eight consecutive short-axis, four-chamber, and tricuspid valve view cardiac cine MRI examinations of healthy volunteers were used. Two independent observers performed the manual and automatic segmentations of the right ventricles. Analyses were based on the ventricular volume and ejection fraction of the right heart chamber. Reproducibility of the manual and semi-automatic segmentations was assessed using intra- and inter-observer variability. Validity of the semi-automatic segmentations was analyzed with reference to the manual segmentations. The inter- and intra-observer variability of manual segmentations were between 0.8 and 3.2%. The semi-automatic segmentations were highly correlated with the manual segmentations (R² 0.79-0.98), with median difference of 0.9-4.8% and of 3.3% for volume and ejection fraction parameters, respectively. In comparison to the manual segmentation, the semi-automatic segmentation produced contours with median dice metrics of 0.95 and 0.87 and median Hausdorff distance of 5.05 and 7.35 mm for contours at end-diastolic and end-systolic phases, respectively. The inter- and intra-observer variability of the semi-automatic segmentations were lower than observed in the manual segmentations. Both manual and semi-automatic segmentations performed better at the end-diastolic phase than at the end-systolic phase. The investigated semi-automatic segmentation method managed to produce a valid and reproducible alternative to manual right ventricle segmentation.

Computational Platform Based on Deep Learning for Segmenting Ventricular Endocardium in Long-axis Cardiac MR Imaging

This paper presents an automated computational platform based on deep learning (DL) approach for left ventricular (LV) and right ventricular (RV) endocardium segmentation in long-axis cine cardiovascular magnetic resonance (CMR). The proposed method uses modified deep U-Net convolutional networks. We trained our model using 4800 images from 40 human subjects (20 healthy volunteers, 20 patients with various cardiac diseases) and validated the technique in 6000 images from 50 subjects (10 healthy volunteers, 40 patients). An average Dice metric of 0.929 ± 0.036 along with an average Jaccard index of 0.869 ± 0.059 were achieved for all the studied subjects. In addition, a high level of correlation and agreement with the ground truth contours for LV ejection fraction (R=0.975), LV fractional area change (R=0.959 to 0.971), and RV fractional area change (R=0.927) were observed. The proposed DL-based segmentation process took less than 3 seconds per subject (or < 30 milliseconds per image over 120 images for each subject). Therefore, our proposed framework offers a promising means to achieve fully automated and rapid segmentation for both LV and RV endocardium in long-axis cine CMR images using an appropriately trained deep convolutional neural network.

Novel imaging techniques in pulmonary hypertension

PURPOSE OF REVIEW

Pulmonary hypertension is a life-shortening condition, which may be idiopathic but is more frequently seen in association with other conditions. Current guidelines recommend cardiac catheterization to confirm the diagnosis of pulmonary hypertension. Evidence suggests an increasing role for noninvasive imaging modalities in the initial diagnostic and prognostic assessment and evaluation of treatment response.

RECENT FINDINGS

In this review we examine the evidence for current noninvasive imaging methodologies: echocardiography computed tomography and MRI in the diagnostic and prognostic assessment of suspected pulmonary hypertension and explore the potential utility of modeling and machine-learning approaches.

SUMMARY

Noninvasive imaging allows a comprehensive assessment of patients with suspected pulmonary hypertension. It plays a key part in the initial diagnostic and prognostic assessment and machine-learning approaches show promise in the diagnosis of pulmonary hypertension.

Artificial intelligence in pediatric and adult congenital cardiac MRI: an unmet clinical need

Cardiac MRI (CMR) allows non-invasive, non-ionizing assessment of cardiac function and anatomy in patients with congenital heart disease (CHD). The utility of CMR as a non-invasive imaging tool for evaluation of CHD have been growing exponentially over the past decade. The algorithms based on artificial intelligence (AI), and in particular, deep learning, have rapidly become a methodology of choice for analyzing CMR. A wide range of applications for AI have been developed to tackle challenges in various aspects of CMR, and significant advances have also been made from image acquisition to image analysis and diagnosis. We include an overview of AI definitions, different architectures, and details on well-known methods. This paper reviews the major deep learning concepts used for analyses of patients with CHD. In the end, we have summarized a list of open challenges and concerns to be considered for future studies.

SUSAN: segment unannotated image structure using adversarial network

PURPOSE

To describe and evaluate a segmentation method using joint adversarial and segmentation convolutional neural network to achieve accurate segmentation using unannotated MR image datasets.

THEORY AND METHODS

A segmentation pipeline was built using joint adversarial and segmentation network. A convolutional neural network technique called cycle-consistent generative adversarial network (CycleGAN) was applied as the core of the method to perform unpaired image-to-image translation between different MR image datasets. A joint segmentation network was incorporated into the adversarial network to obtain additional functionality for semantic segmentation. The fully automated segmentation method termed as SUSAN was tested for segmenting bone and cartilage on 2 clinical knee MR image datasets using images and annotated segmentation masks from an online publicly available knee MR image dataset. The segmentation results were compared using quantitative segmentation metrics with the results from a supervised U-Net segmentation method and 2 registration methods. The Wilcoxon signed-rank test was used to evaluate the value difference of quantitative metrics between different methods.

RESULTS

The proposed method SUSAN provided high segmentation accuracy with results comparable to the supervised U-Net segmentation method (most quantitative metrics having P > 0.05) and significantly better than a multiatlas registration method (all quantitative metrics having P < 0.001) and a direct registration method (all quantitative metrics having P< 0.0001) for the clinical knee image datasets. SUSAN also demonstrated the applicability for segmenting knee MR images with different tissue contrasts.

CONCLUSION

SUSAN performed rapid and accurate tissue segmentation for multiple MR image datasets without the need for sequence specific segmentation annotation. The joint adversarial and segmentation network and training strategy have promising potential applications in medical image segmentation.

Machine Learning and Deep Neural Networks in Thoracic and Cardiovascular Imaging

Advances in technology have always had the potential and opportunity to shape the practice of medicine, and in no medical specialty has technology been more rapidly embraced and adopted than radiology. Machine learning and deep neural networks promise to transform the practice of medicine, and, in particular, the practice of diagnostic radiology. These technologies are evolving at a rapid pace due to innovations in computational hardware and novel neural network architectures. Several cutting-edge postprocessing analysis applications are actively being developed in the fields of thoracic and cardiovascular imaging, including applications for lesion detection and characterization, lung parenchymal characterization, coronary artery assessment, cardiac volumetry and function, and anatomic localization. Cardiothoracic and cardiovascular imaging lies at the technological forefront of radiology due to a confluence of technical advances. Enhanced equipment has enabled computed tomography and magnetic resonance imaging scanners that can safely capture images that freeze the motion of the heart to exquisitely delineate fine anatomic structures. Computing hardware developments have enabled an explosion in computational capabilities and in data storage. Progress in software and fluid mechanical models is enabling complex 3D and 4D reconstructions to not only visualize and assess the dynamic motion of the heart, but also quantify its blood flow and hemodynamics. And now, innovations in machine learning, particularly in the form of deep neural networks, are enabling us to leverage the increasingly massive data repositories that are prevalent in the field. Here, we discuss developments in machine learning techniques and deep neural networks to highlight their likely role in future radiologic practice, both in and outside of image interpretation and analysis. We discuss the concepts of validation, generalizability, and clinical utility, as they pertain to this and other new technologies, and we reflect upon the opportunities and challenges of bringing these into daily use.

Fully automated quantification of biventricular volumes and function in cardiovascular magnetic resonance: applicability to clinical routine settings

BACKGROUND

Cardiovascular magnetic resonance (CMR) represents the clinical gold standard for the assessment of biventricular morphology and function. Since manual post-processing is time-consuming and prone to observer variability, efforts have been directed towards automated volumetric quantification. In this study, we sought to validate the accuracy of a novel approach providing fully automated quantification of biventricular volumes and function in a "real-world" clinical setting.

METHODS

Three-hundred CMR examinations were randomly selected from the local data base. Fully automated quantification of left ventricular (LV) mass, LV and right ventricular (RV) end-diastolic and end-systolic volumes (EDV/ESV), stroke volume (SV) and ejection fraction (EF) were performed overnight using commercially available software (suiteHEART®, Neosoft, Pewaukee, Wisconsin, USA). Parameters were compared to manual assessments (QMass®, Medis Medical Imaging Systems, Leiden, Netherlands). Sub-group analyses were further performed according to image quality, scanner field strength, the presence of implanted aortic valves and repaired Tetralogy of Fallot (ToF).

RESULTS

Biventricular automated segmentation was feasible in all 300 cases. Overall agreement between fully automated and manually derived LV parameters was good (LV-EF: intra-class correlation coefficient [ICC] 0.95; bias - 2.5% [SD 5.9%]), whilst RV agreement was lower (RV-EF: ICC 0.72; bias 5.8% [SD 9.6%]). Lowest agreement was observed in case of severely altered anatomy, e.g. marked RV dilation but normal LV dimensions in repaired ToF (LV parameters ICC 0.73-0.91; RV parameters ICC 0.41-0.94) and/or reduced image quality (LV parameters ICC 0.86-0.95; RV parameters ICC 0.56-0.91), which was more common on 3.0 T than on 1.5 T.

CONCLUSIONS

Fully automated assessments of biventricular morphology and function is robust and accurate in a clinical routine setting with good image quality and can be performed without any user interaction. However, in case of demanding anatomy (e.g. repaired ToF, severe LV hypertrophy) or reduced image quality, quality check and manual re-contouring are still required.

Dilated-Inception Net: Multi-Scale Feature Aggregation for Cardiac Right Ventricle Segmentation

Segmentation of cardiac ventricle from magnetic resonance images is significant for cardiac disease diagnosis, progression assessment, and monitoring cardiac conditions. Manual segmentation is so time consuming, tedious, and subjective that automated segmentation methods are highly desired in practice. However, conventional segmentation methods performed poorly in cardiac ventricle, especially in the right ventricle. Compared with the left ventricle, whose shape is a simple thick-walled circle, the structure of the right ventricle is more complex due to ambiguous boundary, irregular cavity, and variable crescent shape. Hence, effective feature extractors and segmentation models are preferred. In this paper, we propose a dilated-inception net (DIN) to extract and aggregate multi-scale features for right ventricle segmentation. The DIN outperforms many state-of-the-art models on the benchmark database of right ventricle segmentation challenge. In addition, the experimental results indicate that the proposed model has potential to reach expert-level performance in right ventricular epicardium segmentation. More importantly, DIN behaves similarly to clinical expert with high correlation coefficients in four clinical cardiac indices. Therefore, the proposed DIN is promising for automated cardiac right ventricle segmentation in clinical applications.

EXPRESS: Statement on imaging and pulmonary hypertension from the Pulmonary Vascular Research Institute (PVRI)

Pulmonary hypertension (PH) is highly heterogeneous and despite treatment advances it remains a life-shortening condition. There have been significant advances in imaging technologies, but despite evidence of their potential clinical utility, practice remains variable, dependent in part on imaging availability and expertise. This statement summarizes current and emerging imaging modalities and their potential role in the diagnosis and assessment of suspected PH. It also includes a review of commonly encountered clinical and radiological scenarios, and imaging and modeling-based biomarkers. An expert panel was formed including clinicians, radiologists, imaging scientists, and computational modelers. Section editors generated a series of summary statements based on a review of the literature and professional experience and, following consensus review, a diagnostic algorithm and 55 statements were agreed. The diagnostic algorithm and summary statements emphasize the key role and added value of imaging in the diagnosis and assessment of PH and highlight areas requiring further research.

Heart beat but not respiration is the main driving force of the systemic venous return in the Fontan circulation

The Fontan procedure provides relief from cyanosis in patients with univentricular hearts. A major clinical unmet need is to understand whether the venous flow patterns of the Fontan circulation lead to the development of congestive hepatopathy and other life-threatening complications. Currently, there is no consensus on whether heart beat or respiration is the main driving force of venous return and which one affects the periodic flow changes for the most (i. e., pulsatility). The present study, for the first time, quantified respiratory and cardiac components of the venous flow in the inferior vena cava (IVC) of 14 Fontan patients and 11 normal controls using a novel approach (“physio-matrix”). We found that in contrast to the normal controls, respiration in Fontan patients had a significant effect on venous flow pulsatility, and the ratio of respiration-dependent to the cardiac-dependent pulsatility was positively associated with the retrograde flow. Nevertheless, the main driving force of net IVC flow was the heart beat and not respiration. The separate analysis of the effects of respiration and heart beat provides new insights into the abnormal venous return patterns that may be responsible for adverse effects on liver and bowel of the patients with Fontan circulation.

Automated analysis of cardiovascular magnetic resonance myocardial native T1 mapping images using fully convolutional neural networks

BACKGROUND

Cardiovascular magnetic resonance (CMR) myocardial native T1 mapping allows assessment of interstitial diffuse fibrosis. In this technique, the global and regional T1 are measured manually by drawing region of interest in motion-corrected T1 maps. The manual analysis contributes to an already lengthy CMR analysis workflow and impacts measurements reproducibility. In this study, we propose an automated method for combined myocardium segmentation, alignment, and T1 calculation for myocardial T1 mapping.

METHODS

A deep fully convolutional neural network (FCN) was used for myocardium segmentation in T1 weighted images. The segmented myocardium was then resampled on a polar grid, whose origin is located at the center-of-mass of the segmented myocardium. Myocardium T1 maps were reconstructed from the resampled T1 weighted images using curve fitting. The FCN was trained and tested using manually segmented images for 210 patients (5 slices, 11 inversion times per patient). An additional image dataset for 455 patients (5 slices and 11 inversion times per patient), analyzed by an expert reader using a semi-automatic tool, was used to validate the automatically calculated global and regional T1 values. Bland-Altman analysis, Pearson correlation coefficient, r, and the Dice similarity coefficient (DSC) were used to evaluate the performance of the FCN-based analysis on per-patient and per-slice basis. Inter-observer variability was assessed using intraclass correlation coefficient (ICC) of the T1 values calculated by the FCN-based automatic method and two readers.

RESULTS

The FCN achieved fast segmentation (< 0.3 s/image) with high DSC (0.85 ± 0.07). The automatically and manually calculated T1 values (1091 ± 59 ms and 1089 ± 59 ms, respectively) were highly correlated in per-patient (r = 0.82; slope = 1.01; p < 0.0001) and per-slice (r = 0.72; slope = 1.01; p < 0.0001) analyses. Bland-Altman analysis showed good agreement between the automated and manual measurements with 95% of measurements within the limits-of-agreement in both per-patient and per-slice analyses. The intraclass correllation of the T1 calculations by the automatic method vs reader 1 and reader 2 was respectively 0.86/0.56 and 0.74/0.49 in the per-patient/per-slice analyses, which were comparable to that between two expert readers (=0.72/0.58 in per-patient/per-slice analyses).

CONCLUSION

The proposed FCN-based image processing platform allows fast and automatic analysis of myocardial native T1 mapping images mitigating the burden and observer-related variability of manual analysis.

Deep learning in medical imaging and radiation therapy

The goals of this review paper on deep learning (DL) in medical imaging and radiation therapy are to (a) summarize what has been achieved to date; (b) identify common and unique challenges, and strategies that researchers have taken to address these challenges; and (c) identify some of the promising avenues for the future both in terms of applications as well as technical innovations. We introduce the general principles of DL and convolutional neural networks, survey five major areas of application of DL in medical imaging and radiation therapy, identify common themes, discuss methods for dataset expansion, and conclude by summarizing lessons learned, remaining challenges, and future directions.

Fully automatic segmentation of 4D MRI for cardiac functional measurements

PURPOSE

Segmentation of cardiac medical images, an important step in measuring cardiac function, is usually performed either manually or semiautomatically. Fully automatic segmentation of the left ventricle (LV), the right ventricle (RV) as well as the myocardium of three-dimensional (3D) magnetic resonance (MR) images throughout the entire cardiac cycle (four-dimensional, 4D), remains challenging. This study proposes a deformable-based segmentation methodology for efficiently segmenting 4D (3D + t) cardiac MR images.

METHODS

The proposed methodology first used the Hough transform and the local Gaussian distribution method (LGD) to segment the LV endocardial contours from cardiac MR images. Following this, a novel level set-based shape prior method was applied to generate the LV epicardial contours and the RV boundary.

RESULTS

This automatic image segmentation approach has been applied to studies on 17 subjects. The results demonstrated that the proposed method was efficient compared to manual segmentation, achieving a segmentation accuracy with average Dice values of 88.62 ± 5.47%, 87.35 ± 7.26%, and 82.63 ± 6.22% for the LV endocardial, LV epicardial, and RV contours, respectively.

CONCLUSIONS

We have presented a method for accurate LV and RV segmentation. Compared to three existing methods, the proposed method can successfully segment the LV and yield the highest Dice value. This makes it an option for clinical assessment of the volume, size, and thickness of the ventricles.

Correlated Regression Feature Learning for Automated Right Ventricle Segmentation

Accurate segmentation of right ventricle (RV) from cardiac magnetic resonance (MR) images can help a doctor to robustly quantify the clinical indices including ejection fraction. In this paper, we develop one regression convolutional neural network (RegressionCNN) which combines a holistic regression model and a convolutional neural network (CNN) together to determine boundary points' coordinates of RV directly and simultaneously. In our approach, we take the fully connected layers of CNN as the holistic regression model to perform RV segmentation, and the feature maps extracted by convolutional layers of CNN are converted into 1-D vector to connect holistic regression model. Such connection allows us to make full use of the optimization algorithm to constantly optimize the convolutional layers to directly learn the holistic regression model in the training process rather than separate feature extraction and regression model learning. Therefore, RegressionCNN can achieve optimally convolutional feature learning for accurately catching the regression features that are more correlated to RV regression segmentation task in training process, and this can reduce the latent mismatch influence between the feature extraction and the following regression model learning. We evaluate the performance of RegressionCNN on cardiac MR images acquired of 145 human subjects from two clinical centers. The results have shown that RegressionCNN's results are highly correlated (average boundary correlation coefficient equals 0.9827) and consistent with the manual delineation (average dice metric equals 0.8351). Hence, RegressionCNN could be an effective way to segment RV from cardiac MR images accurately and automatically.

FULLY AUTOMATIC SEGMENTATION OF THE RIGHT VENTRICLE VIA MULTI-TASK DEEP NEURAL NETWORKS

Segmentation of ventricles from cardiac magnetic resonance (MR) images is a key step to obtaining clinical parameters useful for prognosis of cardiac pathologies. To improve upon the performance of existing fully convolutional network (FCN) based automatic right ventricle (RV) segmentation approaches, a multi-task deep neural network (DNN) architecture is proposed. The multi-task model can employ any FCN as a building block, allows for leveraging shared features between different tasks, and can be efficiently trained end-to-end. Specifically, a multi-task U-net is developed and implemented using the Tensorflow framework. Numerical tests on real datasets showcase the merits of the proposed approach and in particular its ability to offer improved segmentation performance for small-size RVs.

Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation

Incorporation of prior knowledge about organ shape and location is key to improve performance of image analysis approaches. In particular, priors can be useful in cases where images are corrupted and contain artefacts due to limitations in image acquisition. The highly constrained nature of anatomical objects can be well captured with learning-based techniques. However, in most recent and promising techniques such as CNN-based segmentation it is not obvious how to incorporate such prior knowledge. State-of-the-art methods operate as pixel-wise classifiers where the training objectives do not incorporate the structure and inter-dependencies of the output. To overcome this limitation, we propose a generic training strategy that incorporates anatomical prior knowledge into CNNs through a new regularisation model, which is trained end-to-end. The new framework encourages models to follow the global anatomical properties of the underlying anatomy (e.g. shape, label structure) via learnt non-linear representations of the shape. We show that the proposed approach can be easily adapted to different analysis tasks (e.g. image enhancement, segmentation) and improve the prediction accuracy of the state-of-the-art models. The applicability of our approach is shown on multi-modal cardiac data sets and public benchmarks. In addition, we demonstrate how the learnt deep models of 3-D shapes can be interpreted and used as biomarkers for classification of cardiac pathologies.

Atlas-Based Computational Analysis of Heart Shape and Function in Congenital Heart Disease

Approximately 1% of all babies are born with some form of congenital heart defect. Many serious forms of CHD can now be surgically corrected after birth, which has led to improved survival into adulthood. However, many patients require serial monitoring to evaluate progression of heart failure and determine timing of interventions. Accurate multidimensional quantification of regional heart shape and function is required for characterizing these patients. A computational atlas of single ventricle and biventricular heart shape and function enables quantification of remodeling in terms of z scores in relation to specific reference populations. Progression of disease can then be monitored effectively by longitudinal evaluation of z scores. A biomechanical analysis of cardiac function in relation to population variation enables investigation of the underlying mechanisms for developing pathology. Here, we summarize recent progress in this field, with examples in single ventricle and biventricular congenital pathologies.

Multimodality Imaging of the Right Ventricle

OPINION STATEMENT

Right ventricular (RV) structure and function is clinically important in a wide range of conditions. While conventional echocardiography (echo) methods are widely used, its limitations in RV assessment due its complex geometry are well recognized. New applications of traditional echo methods as well as emerging echo techniques including 3-dimensional (3D) echo and speckle tracking strain have the potential to overcome limitations of conventional echo, though widespread clinical use remains to be seen. Volumetric methods using cardiac magnetic resonance (CMR) and computed tomography (CT) provide accurate assessment of RV function without geometric assumptions. In addition, tissue characterization imaging for myocardial scar and fat using CMR and CT provides important information regarding the RV beyond structure and function alone and has clinical applications for diagnosis and prognosis in a broad range of pathologies. Limitations also exist for these two advanced modalities including availability and patient suitability for CMR and need for contrast and radiation exposure for CT. The complementary role of each modality for the RV as well as emerging evidence for the use of each imaging method in diagnosis and management of RV pathologies is outlined in this study.