Modeling 3D Cardiac Contraction and Relaxation With Point Cloud Deformation Networks.

Global single-valued biomarkers, such as ejection fraction, are widely used in clinical practice to assess cardiac function. However, they only approximate the heart's true 3D deformation process, thus limiting diagnostic accuracy and the understanding of cardiac mechanics. Metrics based on 3D shape have been proposed to alleviate these shortcomings. In this work, we present the Point Cloud Deformation Network (PCD-Net) as a novel geometric deep learning approach for direct modeling of 3D cardiac mechanics of the biventricular anatomy between the extreme ends of the cardiac cycle. Its encoder-decoder architecture combines a low-dimensional latent space with recent advances in point cloud deep learning for effective multi-scale feature learning directly on flexible and memory-efficient point cloud representations of the cardiac anatomy. We first evaluate the PCD-Net's predictive ability for both cardiac contraction and relaxation on a large U.K. Biobank dataset of over 10,000 subjects and find average Chamfer distances between the predicted and ground truth anatomies below the pixel resolution of the underlying image acquisition. We then show the PCD-Net's suitability to act as a normality model of 3D cardiac mechanics and capture subpopulation-specific differences between normal subjects and myocardial infarction (MI) patients. Next, we highlight the PCD-Net's interpretability by visualizing abnormal phenotypes between predicted normal 3D shapes and corresponding observed ones. Finally, we demonstrate that the PCD-Net's learned 3D deformation encodings outperform multiple clinical and machine learning benchmarks by 11% in terms of area under the receiver operating characteristic curve for the tasks of prevalent MI detection and incident MI prediction and by 7% in terms of Harrell's concordance index for MI survival analysis.

Comprehensive characterization of cardiac contraction for improved post-infarction risk assessment.

This study aims at identifying risk-related patterns of left ventricular contraction dynamics via novel volume transient characterization. A multicenter cohort of AMI survivors (n = 1021) who underwent Cardiac Magnetic Resonance (CMR) after infarction was considered for the study. The clinical endpoint was the 12-month rate of major adverse cardiac events (MACE, n = 73), consisting of all-cause death, reinfarction, and new congestive heart failure. Cardiac function was characterized from CMR in 3 potential directions: by (1) volume temporal transients (i.e. contraction dynamics); (2) feature tracking strain analysis (i.e. bulk tissue peak contraction); and (3) 3D shape analysis (i.e. 3D contraction morphology). A fully automated pipeline was developed to extract conventional and novel artificial-intelligence-derived metrics of cardiac contraction, and their relationship with MACE was investigated. Any of the 3 proposed directions demonstrated its additional prognostic value on top of established CMR indexes, myocardial injury markers, basic characteristics, and cardiovascular risk factors (P < 0.001). The combination of these 3 directions of enhancement towards a final CMR risk model improved MACE prediction by 13% compared to clinical baseline (0.774 (0.771-0.777) vs. 0.683 (0.681-0.685) cross-validated AUC, P < 0.001). The study evidences the contribution of the novel contraction characterization, enabled by a fully automated pipeline, to post-infarction assessment.

Digital twinning of the human ventricular activation sequence to Clinical 12-lead ECGs and magnetic resonance imaging using realistic Purkinje networks for in silico clinical trials.

Cardiac in silico clinical trials can virtually assess the safety and efficacy of therapies using human-based modelling and simulation. These technologies can provide mechanistic explanations for clinically observed pathological behaviour. Designing virtual cohorts for in silico trials requires exploiting clinical data to capture the physiological variability in the human population. The clinical characterisation of ventricular activation and the Purkinje network is challenging, especially non-invasively. Our study aims to present a novel digital twinning pipeline that can efficiently generate and integrate Purkinje networks into human multiscale biventricular models based on subject-specific clinical 12-lead electrocardiogram and magnetic resonance recordings. Essential novel features of the pipeline are the human-based Purkinje network generation method, personalisation considering ECG R wave progression as well as QRS morphology, and translation from reduced-order Eikonal models to equivalent biophysically-detailed monodomain ones. We demonstrate ECG simulations in line with clinical data with clinical image-based multiscale models with Purkinje in four control subjects and two hypertrophic cardiomyopathy patients (simulated and clinical QRS complexes with Pearson's correlation coefficients > 0.7). Our methods also considered possible differences in the density of Purkinje myocardial junctions in the Eikonal-based inference as regional conduction velocities. These differences translated into regional coupling effects between Purkinje and myocardial models in the monodomain formulation. In summary, we demonstrate a digital twin pipeline enabling simulations yielding clinically consistent ECGs with clinical CMR image-based biventricular multiscale models, including personalised Purkinje in healthy and cardiac disease conditions.

Towards Enabling Cardiac Digital Twins of Myocardial Infarction Using Deep Computational Models for Inverse Inference.

Cardiac digital twins (CDTs) have the potential to offer individualized evaluation of cardiac function in a non-invasive manner, making them a promising approach for personalized diagnosis and treatment planning of myocardial infarction (MI). The inference of accurate myocardial tissue properties is crucial in creating a reliable CDT of MI. In this work, we investigate the feasibility of inferring myocardial tissue properties from the electrocardiogram (ECG) within a CDT platform. The platform integrates multi-modal data, such as cardiac MRI and ECG, to enhance the accuracy and reliability of the inferred tissue properties. We perform a sensitivity analysis based on computer simulations, systematically exploring the effects of infarct location, size, degree of transmurality, and electrical activity alteration on the simulated QRS complex of ECG, to establish the limits of the approach. We subsequently present a novel deep computational model, comprising a dual-branch variational autoencoder and an inference model, to infer infarct location and distribution from the simulated QRS. The proposed model achieves mean Dice scores of 0.457 ± 0.317 and 0.302 ± 0.273 for the inference of left ventricle scars and border zone, respectively. The sensitivity analysis enhances our understanding of the complex relationship between infarct characteristics and electrophysiological features. The in silico experimental results show that the model can effectively capture the relationship for the inverse inference, with promising potential for clinical application in the future. The code is available at https: //github.com/lileitech/MI_inverse_inference.

Segment anything model for medical images?

The Segment Anything Model (SAM) is the first foundation model for general image segmentation. It has achieved impressive results on various natural image segmentation tasks. However, medical image segmentation (MIS) is more challenging because of the complex modalities, fine anatomical structures, uncertain and complex object boundaries, and wide-range object scales. To fully validate SAM's performance on medical data, we collected and sorted 53 open-source datasets and built a large medical segmentation dataset with 18 modalities, 84 objects, 125 object-modality paired targets, 1050K 2D images, and 6033K masks. We comprehensively analyzed different models and strategies on the so-called COSMOS 1050K dataset. Our findings mainly include the following: (1) SAM showed remarkable performance in some specific objects but was unstable, imperfect, or even totally failed in other situations. (2) SAM with the large ViT-H showed better overall performance than that with the small ViT-B. (3) SAM performed better with manual hints, especially box, than the Everything mode. (4) SAM could help human annotation with high labeling quality and less time. (5) SAM was sensitive to the randomness in the center point and tight box prompts, and may suffer from a serious performance drop. (6) SAM performed better than interactive methods with one or a few points, but will be outpaced as the number of points increases. (7) SAM's performance correlated to different factors, including boundary complexity, intensity differences, etc. (8) Finetuning the SAM on specific medical tasks could improve its average DICE performance by 4.39% and 6.68% for ViT-B and ViT-H, respectively. Codes and models are available at: https://github.com/yuhoo0302/Segment-Anything-Model-for-Medical-Images. We hope that this comprehensive report can help researchers explore the potential of SAM applications in MIS, and guide how to appropriately use and develop SAM.

Functional Impairment in Small Airways Associated With the Breathlessness Symptoms in Long-Coronavirus Disease.

PURPOSE: This study aimed to determine the association between functional impairment in small airways and symptoms of dyspnea in patients with Long-coronavirus disease (COVID), using imaging and computational modeling analysis. PATIENTS AND METHODS: Thirty-four patients with Long-COVID underwent thoracic computed tomography and hyperpolarized Xenon-129 magnetic resonance imaging (HP Xe MRI) scans. Twenty-two answered dyspnea-12 questionnaires. We used a computed tomography-based full-scale airway network (FAN) flow model to simulate pulmonary ventilation. The ventilation distribution projected on a coronal plane and the percentage lobar ventilation modeled in the FAN model were compared with the HP Xe MRI data. To assess the ventilation heterogeneity in small airways, we calculated the fractal dimensions of the impaired ventilation regions in the HP Xe MRI and FAN models. RESULTS: The ventilation distribution projected on a coronal plane showed an excellent resemblance between HP Xe MRI scans and FAN models (structure similarity index: 0.87 ± 0.04). In both the image and the model, the existence of large clustered ventilation defects was not identifiable regardless of dyspnea severity. The percentage lobar ventilation of the HP Xe MRI and FAN model showed a strong correlation (ρ = 0.63, P < 0.001). The difference in the fractal dimension of impaired ventilation zones between the low and high dyspnea-12 score groups was significant (HP Xe MRI: 1.97 [1.89 to 2.04] and 2.08 [2.06 to 2.14], P = 0.005; FAN: 2.60 [2.59 to 2.64] and 2.64 [2.63 to 2.65], P = 0.056). CONCLUSIONS: This study has identified a potential association of small airway functional impairment with breathlessness in Long-COVID, using fractal analysis of HP Xe MRI scans and FAN models.

3D Shape-Based Myocardial Infarction Prediction Using Point Cloud Classification Networks.

Myocardial infarction (MI) is one of the most prevalent cardiovascular diseases with associated clinical decision-making typically based on single-valued imaging biomarkers. However, such metrics only approximate the complex 3D structure and physiology of the heart and hence hinder a better understanding and prediction of MI outcomes. In this work, we investigate the utility of complete 3D cardiac shapes in the form of point clouds for an improved detection of MI events. To this end, we propose a fully automatic multi-step pipeline consisting of a 3D cardiac surface reconstruction step followed by a point cloud classification network. Our method utilizes recent advances in geometric deep learning on point clouds to enable direct and efficient multi-scale learning on high-resolution surface models of the cardiac anatomy. We evaluate our approach on 1068 UK Biobank subjects for the tasks of prevalent MI detection and incident MI prediction and find improvements of ∼13% and ∼5% respectively over clinical benchmarks. Furthermore, we analyze the role of each ventricle and cardiac phase for 3D shape-based MI detection and conduct a visual analysis of the morphological and physiological patterns typically associated with MI outcomes.Clinical relevance- The presented approach enables the fast and fully automatic pathology-specific analysis of full 3D cardiac shapes. It can thus be employed as a real-time diagnostic tool in clinical practice to discover and visualize more intricate biomarkers than currently used single-valued metrics and improve predictive accuracy of myocardial infarction.

Multi-class point cloud completion networks for 3D cardiac anatomy reconstruction from cine magnetic resonance images.

Cine magnetic resonance imaging (MRI) is the current gold standard for the assessment of cardiac anatomy and function. However, it typically only acquires a set of two-dimensional (2D) slices of the underlying three-dimensional (3D) anatomy of the heart, thus limiting the understanding and analysis of both healthy and pathological cardiac morphology and physiology. In this paper, we propose a novel fully automatic surface reconstruction pipeline capable of reconstructing multi-class 3D cardiac anatomy meshes from raw cine MRI acquisitions. Its key component is a multi-class point cloud completion network (PCCN) capable of correcting both the sparsity and misalignment issues of the 3D reconstruction task in a unified model. We first evaluate the PCCN on a large synthetic dataset of biventricular anatomies and observe Chamfer distances between reconstructed and gold standard anatomies below or similar to the underlying image resolution for multiple levels of slice misalignment. Furthermore, we find a reduction in reconstruction error compared to a benchmark 3D U-Net by 32% and 24% in terms of Hausdorff distance and mean surface distance, respectively. We then apply the PCCN as part of our automated reconstruction pipeline to 1000 subjects from the UK Biobank study in a cross-domain transfer setting and demonstrate its ability to reconstruct accurate and topologically plausible biventricular heart meshes with clinical metrics comparable to the previous literature. Finally, we investigate the robustness of our proposed approach and observe its capacity to successfully handle multiple common outlier conditions.

Multi-modality cardiac image computing: A survey.

Multi-modality cardiac imaging plays a key role in the management of patients with cardiovascular diseases. It allows a combination of complementary anatomical, morphological and functional information, increases diagnosis accuracy, and improves the efficacy of cardiovascular interventions and clinical outcomes. Fully-automated processing and quantitative analysis of multi-modality cardiac images could have a direct impact on clinical research and evidence-based patient management. However, these require overcoming significant challenges including inter-modality misalignment and finding optimal methods to integrate information from different modalities. This paper aims to provide a comprehensive review of multi-modality imaging in cardiology, the computing methods, the validation strategies, the related clinical workflows and future perspectives. For the computing methodologies, we have a favored focus on the three tasks, i.e., registration, fusion and segmentation, which generally involve multi-modality imaging data, either combining information from different modalities or transferring information across modalities. The review highlights that multi-modality cardiac imaging data has the potential of wide applicability in the clinic, such as trans-aortic valve implantation guidance, myocardial viability assessment, and catheter ablation therapy and its patient selection. Nevertheless, many challenges remain unsolved, such as missing modality, modality selection, combination of imaging and non-imaging data, and uniform analysis and representation of different modalities. There is also work to do in defining how the well-developed techniques fit in clinical workflows and how much additional and relevant information they introduce. These problems are likely to continue to be an active field of research and the questions to be answered in the future.

Deep Learning Segmentation of the Right Ventricle in Cardiac MRI: The M&Ms Challenge.

In recent years, several deep learning models have been proposed to accurately quantify and diagnose cardiac pathologies. These automated tools heavily rely on the accurate segmentation of cardiac structures in MRI images. However, segmentation of the right ventricle is challenging due to its highly complex shape and ill-defined borders. Hence, there is a need for new methods to handle such structure's geometrical and textural complexities, notably in the presence of pathologies such as Dilated Right Ventricle, Tricuspid Regurgitation, Arrhythmogenesis, Tetralogy of Fallot, and Inter-atrial Communication. The last MICCAI challenge on right ventricle segmentation was held in 2012 and included only 48 cases from a single clinical center. As part of the 12th Workshop on Statistical Atlases and Computational Models of the Heart (STACOM 2021), the M&Ms-2 challenge was organized to promote the interest of the research community around right ventricle segmentation in multi-disease, multi-view, and multi-center cardiac MRI. Three hundred sixty CMR cases, including short-axis and long-axis 4-chamber views, were collected from three Spanish hospitals using nine different scanners from three different vendors, and included a diverse set of right and left ventricle pathologies. The solutions provided by the participants show that nnU-Net achieved the best results overall. However, multi-view approaches were able to capture additional information, highlighting the need to integrate multiple cardiac diseases, views, scanners, and acquisition protocols to produce reliable automatic cardiac segmentation algorithms.

A Deep Learning Approach to Visualize Aortic Aneurysm Morphology Without the Use of Intravenous Contrast Agents.

BACKGROUND: Intravenous contrast agents are routinely used in CT imaging to enable the visualization of intravascular pathology, such as with abdominal aortic aneurysms. However, the injection is contraindicated in patients with iodine allergy and is associated with renal complications. OBJECTIVES: In this study, we investigate if the raw data acquired from a noncontrast CT image contains sufficient information to differentiate blood and other soft tissue components. A deep learning pipeline underpinned by generative adversarial networks was developed to simulate contrast enhanced CTA images using noncontrast CTs. METHODS AND RESULTS: Two generative models (cycle- and conditional) are trained with paired noncontrast and contrast enhanced CTs from seventy-five patients (total of 11,243 pairs of images) with abdominal aortic aneurysms in a 3-fold cross-validation approach with a training/testing split of 50:25 patients. Subsequently, models were evaluated on an independent validation cohort of 200 patients (total of 29,468 pairs of images). Both deep learning generative models are able to perform this image transformation task with the Cycle-generative adversarial network (GAN) model outperforming the Conditional-GAN model as measured by aneurysm lumen segmentation accuracy (Cycle-GAN: 86.1% ± 12.2% vs Con-GAN: 85.7% ± 10.4%) and thrombus spatial morphology classification accuracy (Cycle-GAN: 93.5% vs Con-GAN: 85.7%). CONCLUSION: This pipeline implements deep learning methods to generate CTAs from noncontrast images, without the need of contrast injection, that bear strong concordance to the ground truth and enable the assessment ofimportant clinical metrics. Our pipeline is poised to disrupt clinical pathways requiring intravenous contrast.

Prediction of Abdominal Aortic Aneurysm Growth Using Geometric Assessment of Computerized Tomography Images Acquired During the Aneurysm Surveillance Period.

OBJECTIVE: We investigated the utility of geometric features for future AAA growth prediction. BACKGROUND: Novel methods for growth prediction of AAA are recognized as a research priority. Geometric feature have been used to predict cerebral aneurysm rupture, but not examined as predictor of AAA growth. METHODS: Computerized tomography (CT) scans from patients with infra-renal AAAs were analyzed. Aortic volumes were segmented using an automated pipeline to extract AAA diameter (APD), undulation index (UI), and radius of curvature (RC). Using a prospectively recruited cohort, we first examined the relation between these geometric measurements to patients' demographic features (n = 102). A separate 192 AAA patients with serial CT scans during AAA surveillance were identified from an ongoing clinical database. Multinomial logistic and multiple linear regression models were trained and optimized to predict future AAA growth in these patients. RESULTS: There was no correlation between the geometric measurements and patients' demographic features. APD (Spearman r = 0.25, P < 0.05), UI (Spearman r = 0.38, P < 0.001) and RC (Spearman r =-0.53, P < 0.001) significantly correlated with annual AAA growth. Using APD, UI, and RC as 3 input variables, the area under receiver operating characteristics curve for predicting slow growth (<2.5 mm/yr) or fast growth (>5 mm/yr) at 12 months are 0.80 and 0.79, respectively. The prediction or growth rate is within 2 mm error in 87% of cases. CONCLUSIONS: Geometric features of an AAA can predict its future growth. This method can be applied to routine clinical CT scans acquired from patients during their AAA surveillance pathway.

Automated Torso Contour Extraction from Clinical Cardiac MR Slices for 3D Torso Reconstruction.

Whilst the electrocardiogram (ECG) is an essential tool for diagnosing cardiac electrical abnormalities, its characteristics are dependent on anatomical variability. Specifically variation in torso geometry affects relative positions of the leads with respect to the heart. We propose a novel pipeline that uses standard cardiac magnetic resonance images to reconstruct the torso and heart, and recreate the ECG considering torso and cardiac anatomy. This requires automated extraction of the torso contours. Our method combines an initial u-net segmenter with a second network that refines contours and removes spurious segments. The networks were evaluated on a cross validation study dataset and an independent test set. The use of two-channel input, including both original image and initial segmentation, in the refinement network significantly improved performance on the independent test set, reducing the Hausdorff distance from 9.1 pixels to 4.3 pixels and increasing Dice coefficient from 0.75 to 0.93. Clinical Relevance- This method can be utilized to allow ECG simulations with personalized torso geometry which has previously been demonstrated to significantly effect QRS parameters. A clinical tool can be developed using this method that accounts for torso geometry in ECG interpretation.

Automated 3D Whole-Heart Mesh Reconstruction From 2D Cine MR Slices Using Statistical Shape Model.

Cardiac magnetic resonance (CMR) imaging is the one of the gold standard imaging modalities for the diagnosis and characterization of cardiovascular diseases. The clinical cine protocol of the CMR typically generates high-resolution 2D images of heart tissues in a finite number of separated and independent 2D planes, which are appropriate for the 3D reconstruction of biventricular heart surfaces. However, they are usually inadequate for the whole-heart reconstruction, specifically for both atria. In this regard, the paper presents a novel approach for automated patient-specific 3D whole-heart mesh reconstruction from limited number of 2D cine CMR slices with the help of a statistical shape model (SSM). After extracting the heart contours from 2D cine slices, the SSM is first optimally fitted over the sparse heart contours in 3D space to provide the initial representation of the 3D whole-heart mesh, which is further deformed to minimize the distance from the heart contours for generating the final reconstructed mesh. The reconstruction performance of the proposed approach is evaluated on a cohort of 30 subjects randomly selected from the UK Biobank study, demonstrating the generation of high-quality 3D whole-heart meshes with average contours to surface distance less than the underlying image resolution and the clinical metrics within acceptable ranges reported in previous literature. Clinical Relevance- Automated patient-specific 3D whole-heart mesh reconstruction has numerous applications in car-diac diagnosis and multimodal visualization, including treatment planning, virtual surgery, and biomedical simulations.

Multi-Domain Variational Autoencoders for Combined Modeling of MRI-Based Biventricular Anatomy and ECG-Based Cardiac Electrophysiology.

Human cardiac function is characterized by a complex interplay of mechanical deformation and electrophysiological conduction. Similar to the underlying cardiac anatomy, these interconnected physiological patterns vary considerably across the human population with important implications for the effectiveness of clinical decision-making and the accuracy of computerized heart models. While many previous works have investigated this variability separately for either cardiac anatomy or physiology, this work aims to combine both aspects in a single data-driven approach and capture their intricate interdependencies in a multi-domain setting. To this end, we propose a novel multi-domain Variational Autoencoder (VAE) network to capture combined Electrocardiogram (ECG) and Magnetic Resonance Imaging (MRI)-based 3D anatomy information in a single model. Each VAE branch is specifically designed to address the particular challenges of the respective input domain, enabling efficient encoding, reconstruction, and synthesis of multi-domain cardiac signals. Our method achieves high reconstruction accuracy on a United Kingdom Biobank dataset, with Chamfer Distances between reconstructed and input anatomies below the underlying image resolution and ECG reconstructions outperforming multiple single-domain benchmarks by a considerable margin. The proposed VAE is capable of generating realistic virtual populations of arbitrary size with good alignment in clinical metrics between the synthesized and gold standard anatomies and Maximum Mean Discrepancy (MMD) scores of generated ECGs below those of comparable single-domain approaches. Furthermore, we observe the latent space of our VAE to be highly interpretable with separate components encoding different aspects of anatomical and ECG variability. Finally, we demonstrate that the combined anatomy and ECG representation improves the performance in a cardiac disease classification task by 3.9% in terms of Area Under the Receiver Operating Characteristic (AUROC) curve over the best corresponding single-domain modeling approach.

A deep learning pipeline to simulate fluorodeoxyglucose (FDG) uptake in head and neck cancers using non-contrast CT images without the administration of radioactive tracer.

OBJECTIVES: Positron emission tomography (PET) imaging is a costly tracer-based imaging modality used to visualise abnormal metabolic activity for the management of malignancies. The objective of this study is to demonstrate that non-contrast CTs alone can be used to differentiate regions with different Fluorodeoxyglucose (FDG) uptake and simulate PET images to guide clinical management. METHODS: Paired FDG-PET and CT images (n = 298 patients) with diagnosed head and neck squamous cell carcinoma (HNSCC) were obtained from The cancer imaging archive. Random forest (RF) classification of CT-derived radiomic features was used to differentiate metabolically active (tumour) and inactive tissues (ex. thyroid tissue). Subsequently, a deep learning generative adversarial network (GAN) was trained for this CT to PET transformation task without tracer injection. The simulated PET images were evaluated for technical accuracy (PERCIST v.1 criteria) and their ability to predict clinical outcome [(1) locoregional recurrence, (2) distant metastasis and (3) patient survival]. RESULTS: From 298 patients, 683 hot spots of elevated FDG uptake (elevated SUV, 6.03 ± 1.71) were identified. RF models of intensity-based CT-derived radiomic features were able to differentiate regions of negligible, low and elevated FDG uptake within and surrounding the tumour. Using the GAN-simulated PET image alone, we were able to predict clinical outcome to the same accuracy as that achieved using FDG-PET images. CONCLUSION: This pipeline demonstrates a deep learning methodology to simulate PET images from CT images in HNSCC without the use of radioactive tracer. The same pipeline can be applied to other pathologies that require PET imaging.

Understanding and Improving Risk Assessment After Myocardial Infarction Using Automated Left Ventricular Shape Analysis.

BACKGROUND: Left ventricular ejection fraction (LVEF) and end-systolic volume (ESV) remain the main imaging biomarkers for post-acute myocardial infarction (AMI) risk stratification. However, they are limited to global systolic function and fail to capture functional and anatomical regional abnormalities, hindering their performance in risk stratification. OBJECTIVES: This study aimed to identify novel 3-dimensional (3D) imaging end-systolic (ES) shape and contraction descriptors toward risk-related features and superior prognosis in AMI. METHODS: A multicenter cohort of AMI survivors (n = 1,021; median age 63 years; 74.5% male) who underwent cardiac magnetic resonance (CMR) at a median of 3 days after infarction were considered for this study. The clinical endpoint was the 12-month rate of major adverse cardiac events (MACE; n = 73), consisting of all-cause death, reinfarction, and new congestive heart failure. A fully automated pipeline was developed to segment CMR images, build 3D statistical models of shape and contraction in AMI, and find the 3D patterns related to MACE occurrence. RESULTS: The novel ES shape markers proved to be superior to ESV (median cross-validated area under the receiver-operating characteristic curve 0.681 [IQR: 0.679-0.684] vs 0.600 [IQR: 0.598-0.602]; P < 0.001); and 3D contraction to LVEF (0.716 [IQR: 0.714-0.718] vs 0.681 [IQR: 0.679-0.684]; P < 0.001) in MACE occurrence prediction. They also contributed to a significant improvement in a multivariable setting including CMR markers, cardiovascular risk factors, and basic patient characteristics (0.747 [IQR: 0.745-0.749]; P < 0.001). Based on these novel 3D descriptors, 3 impairments caused by AMI were identified: global, anterior, and basal, the latter being the most complementary signature to already known predictors. CONCLUSIONS: The quantification of 3D differences in ES shape and contraction, enabled by a fully automated pipeline, improves post-AMI risk prediction and identifies shape and contraction patterns related to MACE occurrence.

A Deep Learning Pipeline to Automate High-Resolution Arterial Segmentation With or Without Intravenous Contrast.

BACKGROUND: Existing methods to reconstruct vascular structures from a computerized tomography (CT) angiogram rely on contrast injection to enhance the radio-density within the vessel lumen. However, pathological changes in the vasculature may be present that prevent accurate reconstruction. In aortic aneurysmal disease, a thrombus adherent to the aortic wall within the expanding aneurysmal sac is present in >90% of cases. These deformations prevent the automatic extraction of vital clinical information by existing image reconstruction methods. AIM: In this study, a deep learning architecture consisting of a modified U-Net with attention-gating was implemented to establish a high-throughput and automated segmentation pipeline of pathological blood vessels in CT images acquired with or without the use of a contrast agent. METHODS AND RESULTS: Seventy-Five patients with paired noncontrast and contrast-enhanced CT images were randomly selected from an ongoing study (Ethics Ref 13/SC/0250), manually annotated and used for model training and evaluation. Data augmentation was implemented to diversify the training data set in a ratio of 10:1. The performance of our Attention-based U-Net in extracting both the inner (blood flow) lumen and the wall structure of the aortic aneurysm from CT angiograms was compared against a generic 3-D U-Net and displayed superior results. Implementation of this network within the aortic segmentation pipeline for both contrast and noncontrast CT images has allowed for accurate and efficient extraction of the morphological and pathological features of the entire aortic volume. CONCLUSIONS: This extraction method can be used to standardize aneurysmal disease management and sets the foundation for complex geometric and morphological analysis. Furthermore, this pipeline can be extended to other vascular pathologies.

Interpretable cardiac anatomy modeling using variational mesh autoencoders.

Cardiac anatomy and function vary considerably across the human population with important implications for clinical diagnosis and treatment planning. Consequently, many computer-based approaches have been developed to capture this variability for a wide range of applications, including explainable cardiac disease detection and prediction, dimensionality reduction, cardiac shape analysis, and the generation of virtual heart populations. In this work, we propose a variational mesh autoencoder (mesh VAE) as a novel geometric deep learning approach to model such population-wide variations in cardiac shapes. It embeds multi-scale graph convolutions and mesh pooling layers in a hierarchical VAE framework to enable direct processing of surface mesh representations of the cardiac anatomy in an efficient manner. The proposed mesh VAE achieves low reconstruction errors on a dataset of 3D cardiac meshes from over 1,000 patients with acute myocardial infarction, with mean surface distances between input and reconstructed meshes below the underlying image resolution. We also find that it outperforms a voxelgrid-based deep learning benchmark in terms of both mean surface distance and Hausdorff distance while requiring considerably less memory. Furthermore, we explore the quality and interpretability of the mesh VAE's latent space and showcase its ability to improve the prediction of major adverse cardiac events over a clinical benchmark. Finally, we investigate the method's ability to generate realistic virtual populations of cardiac anatomies and find good alignment between the synthesized and gold standard mesh populations in terms of multiple clinical metrics.

Emerging artificial intelligence applications in liver magnetic resonance imaging.

Chronic liver diseases (CLDs) are becoming increasingly more prevalent in modern society. The use of imaging techniques for early detection, such as magnetic resonance imaging (MRI), is crucial in reducing the impact of these diseases on healthcare systems. Artificial intelligence (AI) algorithms have been shown over the past decade to excel at image-based analysis tasks such as detection and segmentation. When applied to liver MRI, they have the potential to improve clinical decision making, and increase throughput by automating analyses. With Liver diseases becoming more prevalent in society, the need to implement these techniques to utilize liver MRI to its full potential, is paramount. In this review, we report on the current methods and applications of AI methods in liver MRI, with a focus on machine learning and deep learning methods. We assess four main themes of segmentation, classification, image synthesis and artefact detection, and their respective potential in liver MRI and the wider clinic. We provide a brief explanation of some of the algorithms used and explore the current challenges affecting the field. Though there are many hurdles to overcome in implementing AI methods in the clinic, we conclude that AI methods have the potential to positively aid healthcare professionals for years to come.