Saak Transform-Based Machine Learning for Light-Sheet Imaging of Cardiac Trabeculation

Advanced Imaging Techniques for Atherosclerosis and Cardiovascular Calcification in Animal Models

The detection and assessment of atherosclerosis and cardiovascular calcification can inform risk stratification and therapies to reduce cardiovascular morbidity and mortality. In this review, we provide an overview of current and emerging imaging techniques for assessing atherosclerosis and cardiovascular calcification in animal models. Traditional imaging modalities, such as computed tomography (CT) and magnetic resonance imaging (MRI), offer non-invasive approaches of visualizing atherosclerotic calcification in vivo; integration of these techniques with positron emission tomography (PET) imaging adds molecular imaging capabilities, such as detection of metabolically active microcalcifications with 18F-sodium fluoride. Photoacoustic imaging provides high contrast that enables in vivo evaluation of plaque composition, yet this method is limited by optical penetration depth. Light-sheet fluorescence microscopy provides high-resolution, three-dimensional imaging of cardiovascular structures and has been used for ex vivo assessment of atherosclerotic calcification, but its limited tissue penetration and requisite complex sample preparation preclude its use in vivo to evaluate cardiac tissue. Overall, with these evolving imaging tools, our understanding of cardiovascular calcification development in animal models is improving, and the combination of traditional imaging techniques with emerging molecular imaging modalities will enhance our ability to investigate therapeutic strategies for atherosclerotic calcification.

Frontiers in artificial intelligence-directed light-sheet microscopy for uncovering biological phenomena and multi-organ imaging

Light-sheet fluorescence microscopy (LSFM) introduces fast scanning of biological phenomena with deep photon penetration and minimal phototoxicity. This advancement represents a significant shift in 3-D imaging of large-scale biological tissues and 4-D (space + time) imaging of small live animals. The large data associated with LSFM requires efficient imaging acquisition and analysis with the use of artificial intelligence (AI)/machine learning (ML) algorithms. To this end, AI/ML-directed LSFM is an emerging area for multi-organ imaging and tumor diagnostics. This review will present the development of LSFM and highlight various LSFM configurations and designs for multi-scale imaging. Optical clearance techniques will be compared for effective reduction in light scattering and optimal deep-tissue imaging. This review will further depict a diverse range of research and translational applications, from small live organisms to multi-organ imaging to tumor diagnosis. In addition, this review will address AI/ML-directed imaging reconstruction, including the application of convolutional neural networks (CNNs) and generative adversarial networks (GANs). In summary, the advancements of LSFM have enabled effective and efficient post-imaging reconstruction and data analyses, underscoring LSFM's contribution to advancing fundamental and translational research.

Development of a Machine Learning-Enabled Virtual Reality Tool for Preoperative Planning of Functional Endoscopic Sinus Surgery

Objectives  Virtual reality (VR) is an increasingly valuable teaching tool, but current simulators are not typically clinically scalable due to their reliance on inefficient manual segmentation. The objective of this project was to leverage a high-throughput and accurate machine learning method to automate data preparation for a patient-specific VR simulator used to explore preoperative sinus anatomy. Methods  An endoscopic VR simulator was designed in Unity to enable interactive exploration of sinus anatomy. The Saak transform, a data-efficient machine learning method, was adapted to accurately segment sinus computed tomography (CT) scans using minimal training data, and the resulting data were reconstructed into three-dimensional (3D) patient-specific models that could be explored in the simulator. Results  Using minimal training data, the Saak transform-based machine learning method offers accurate soft-tissue segmentation. When explored with an endoscope in the VR simulator, the anatomical models generated by the algorithm accurately capture key sinus structures and showcase patient-specific variability in anatomy. Conclusion  By offering an automatic means of preparing VR models from a patient's raw CT scans, this pipeline takes a key step toward clinical scalability. In addition to preoperative planning, this system also enables virtual endoscopy-a tool that is particularly useful in the COVID-19 era. As VR technology inevitably continues to develop, such a foundation will help ensure that future innovations remain clinically accessible.

Light-Sheet Imaging to Reveal Cardiac Structure in Rodent Hearts

Light-sheet microscopy (LSM) plays a pivotal role in comprehending the intricate three-dimensional (3D) structure of the heart, providing crucial insights into fundamental cardiac physiology and pathologic responses. We hereby delve into the development and implementation of the LSM technique to elucidate the micro-architecture of the heart in mouse models. The methodology integrates a customized LSM system with tissue clearing techniques, mitigating light scattering within cardiac tissues for volumetric imaging. The combination of conventional LSM with image stitching and multiview deconvolution approaches allows for the capture of the entire heart. To address the inherent trade-off between axial resolution and field of view (FOV), we further introduce an axially swept light-sheet microscopy (ASLM) method to minimize out-of-focus light and uniformly illuminate the heart across the propagation direction. In the meanwhile, tissue clearing methods such as iDISCO enhance light penetration, facilitating the visualization of deep structures and ensuring a comprehensive examination of the myocardium throughout the entire heart. The combination of the proposed LSM and tissue clearing methods presents a promising platform for researchers in resolving cardiac structures in rodent hearts, holding great potential for the understanding of cardiac morphogenesis and remodeling.

Computational approaches for mechanobiology in cardiovascular development and diseases

The cardiovascular development in vertebrates evolves in response to genetic and mechanical cues. The dynamic interplay among mechanics, cell biology, and anatomy continually shapes the hydraulic networks, characterized by complex, non-linear changes in anatomical structure and blood flow dynamics. To better understand this interplay, a diverse set of molecular and computational tools has been used to comprehensively study cardiovascular mechanobiology. With the continual advancement of computational capacity and numerical techniques, cardiovascular simulation is increasingly vital in both basic science research for understanding developmental mechanisms and disease etiologies, as well as in clinical studies aimed at enhancing treatment outcomes. This review provides an overview of computational cardiovascular modeling. Beginning with the fundamental concepts of computational cardiovascular modeling, it navigates through the applications of computational modeling in investigating mechanobiology during cardiac development. Second, the article illustrates the utility of computational hemodynamic modeling in the context of treatment planning for congenital heart diseases. It then delves into the predictive potential of computational models for elucidating tissue growth and remodeling processes. In closing, we outline prevailing challenges and future prospects, underscoring the transformative impact of computational cardiovascular modeling in reshaping cardiovascular science and clinical practice.

4D Light-sheet imaging and interactive analysis of cardiac contractility in zebrafish larvae

Despite ongoing efforts in cardiovascular research, the acquisition of high-resolution and high-speed images for the purpose of assessing cardiac contraction remains challenging. Light-sheet fluorescence microscopy (LSFM) offers superior spatiotemporal resolution and minimal photodamage, providing an indispensable opportunity for the in vivo study of cardiac micro-structure and contractile function in zebrafish larvae. To track the myocardial architecture and contractility, we have developed an imaging strategy ranging from LSFM system construction, retrospective synchronization, single cell tracking, to user-directed virtual reality (VR) analysis. Our system enables the four-dimensional (4D) investigation of individual cardiomyocytes across the entire atrium and ventricle during multiple cardiac cycles in a zebrafish larva at the cellular resolution. To enhance the throughput of our model reconstruction and assessment, we have developed a parallel computing-assisted algorithm for 4D synchronization, resulting in a nearly tenfold enhancement of reconstruction efficiency. The machine learning-based nuclei segmentation and VR-based interaction further allow us to quantify cellular dynamics in the myocardium from end-systole to end-diastole. Collectively, our strategy facilitates noninvasive cardiac imaging and user-directed data interpretation with improved efficiency and accuracy, holding great promise to characterize functional changes and regional mechanics at the single cell level during cardiac development and regeneration.

Light sheet imaging and interactive analysis of the cardiac structure in neonatal mice

Light-sheet microscopy (LSM) enables us to strengthen the understanding of cardiac development, injury, and regeneration in mammalian models. This emerging technique decouples laser illumination and fluorescence detection to investigate cardiac micro-structure and function with a high spatial resolution while minimizing photodamage and maximizing penetration depth. To unravel the potential of volumetric imaging in cardiac development and repair, we sought to integrate our in-house LSM, Adipo-Clear, and virtual reality (VR) with neonatal mouse hearts. We demonstrate the use of Adipo-Clear to render mouse hearts transparent, the development of our in-house LSM to capture the myocardial architecture within the intact heart, and the integration of VR to explore, measure, and assess regions of interests in an interactive manner. Collectively, we have established an innovative and holistic strategy for image acquisition and interpretation, providing an entry point to assess myocardial micro-architecture throughout the entire mammalian heart for the understanding of cardiac morphogenesis.

Recent advances in quantifying the mechanobiology of cardiac development via computational modeling

Mechanical forces are essential for coordinating cardiac morphogenesis, but much remains to be discovered about the interactions between mechanical forces and the mechanotransduction pathways they activate. Due to the elaborate and fundamentally multi-physics and multi-scale nature of cardiac mechanobiology, a complete understanding requires multiple experimental and analytical techniques. We identify three fundamental tools used in the field to probe these interactions: high resolution imaging, genetic and molecular analysis, and computational modeling. In this review, we focus on computational modeling and present recent studies employing this tool to investigate the mechanobiological pathways involved with cardiac development. These works demonstrate that understanding the detailed spatial and temporal patterns of biomechanical forces is crucial to building a comprehensive understanding of mechanobiology during cardiac development, and that computational modeling is an effective and efficient tool for obtaining such detail. In this context, multidisciplinary studies combining all three tools present the most compelling results.

Fast detection of dam zone boundary based on Otsu thresholding optimized by enhanced harris hawks optimization

Earth-rock dams are among the most important and expensive infrastructure projects. A key safety issue is dam zone boundary detection to prevent the intrusion of materials from different zones. However, existing detection methods strongly highly depend on human judgement, which is time consuming and labor intensive. To solve this problem, this work proposes a fast boundary detection method based on the Otsu algorithm optimized by enhanced Harris hawks optimization (HHO). Compared with the original Otsu algorithm, the proposed method has a higher computation speed to meet the time requirements of engineering projects. Particle swarm optimization is adopted to enhance the exploration stage of HHO. In addition, a tangent function and chaotic sine map are used to improve the convergence speed and robustness. The application of the proposed method to a real-life project shows that the calculation time can be reduced to 20 s, which is approximately 18.8% of the original calculation time.

Artificial Intelligence in Pediatric Cardiology: A Scoping Review

The evolution of AI and data science has aided in mechanizing several aspects of medical care requiring critical thinking: diagnosis, risk stratification, and management, thus mitigating the burden of physicians and reducing the likelihood of human error. AI modalities have expanded feet to the specialty of pediatric cardiology as well. We conducted a scoping review searching the Scopus, Embase, and PubMed databases covering the recent literature between 2002-2022. We found that the use of neural networks and machine learning has significantly improved the diagnostic value of cardiac magnetic resonance imaging, echocardiograms, computer tomography scans, and electrocardiographs, thus augmenting the clinicians' diagnostic accuracy of pediatric heart diseases. The use of AI-based prediction algorithms in pediatric cardiac surgeries improves postoperative outcomes and prognosis to a great extent. Risk stratification and the prediction of treatment outcomes are feasible using the key clinical findings of each CHD with appropriate computational algorithms. Notably, AI can revolutionize prenatal prediction as well as the diagnosis of CHD using the EMR (electronic medical records) data on maternal risk factors. The use of AI in the diagnostics, risk stratification, and management of CHD in the near future is a promising possibility with current advancements in machine learning and neural networks. However, the challenges posed by the dearth of appropriate algorithms and their nascent nature, limited physician training, fear of over-mechanization, and apprehension of missing the 'human touch' limit the acceptability. Still, AI proposes to aid the clinician tomorrow with precision cardiology, paving a way for extremely efficient human-error-free health care.

Virtual Reality for Interactive Medical Analysis

Molecular imaging along with 3-dimensional (3-D) or 4-D (3-D spatial + 1-D temporal) visualization is widely used in clinical diagnosis and surgical planning. However, the pre-defined perspective and confined manipulation limit the in-depth exploration and analysis in 3-D / 4-D. To overcome this obstacle, we utilized virtual reality (VR) to interact with CT images of the cardiopulmonary system in a 3-D immersive environment. We implemented manipulative functionalities into the VR environment that altered the cardiopulmonary models to interactively generate new data analysis perspectives. We successfully sliced a CT cardiac model showing in-depth surface visualizations of the ventricles and atria. Our customized framework enables enhanced data interpretation interactivity of CT images and establishes a user-directed manipulative VR platform derived from imaging results for remote medical practices including training, education, and investigation.

Deep Neural Network-Aided Histopathological Analysis of Myocardial Injury

Deep neural networks have become the mainstream approach for analyzing and interpreting histology images. In this study, we established and validated an interpretable DNN model to assess endomyocardial biopsy (EMB) data of patients with myocardial injury. Deep learning models were used to extract features and classify EMB histopathological images of heart failure cases diagnosed with either ischemic cardiomyopathy or idiopathic dilated cardiomyopathy and non-failing cases (organ donors without a history of heart failure). We utilized the gradient-weighted class activation mapping (Grad-CAM) technique to emphasize injured regions, providing an entry point to assess the dominant morphology in the process of a comprehensive evaluation. To visualize clustered regions of interest (ROI), we utilized uniform manifold approximation and projection (UMAP) embedding for dimension reduction. We further implemented a multi-model ensemble mechanism to improve the quantitative metric (area under the receiver operating characteristic curve, AUC) to 0.985 and 0.992 on ROI-level and case-level, respectively, outperforming the achievement of 0.971 ± 0.017 and 0.981 ± 0.020 based on the sub-models. Collectively, this new methodology provides a robust and interpretive framework to explore local histopathological patterns, facilitating the automatic and high-throughput quantification of cardiac EMB analysis.

Deep embeddings and logistic regression for rapid active learning in histopathological images

BACKGROUND AND OBJECTIVE

Recognizing different tissue components is one of the most fundamental and essential works in digital pathology. Current methods are often based on convolutional neural networks (CNNs), which need numerous annotated samples for training. Creating large-scale histopathological datasets is labor-intensive, where interactive data annotation is a potential solution.

METHODS

We propose DELR (Deep Embedding-based Logistic Regression) to enable rapid model training and inference for histopathological image analysis. DELR utilizes a pretrained CNN to encode images as compact embeddings with low computational cost. The embeddings are then used to train a Logistic Regression model efficiently. We implemented DELR in an active learning framework, and validated it on three histopathological problems (binary, 4-category, and 8-category classification challenge for lung, breast, and colorectal cancer, respectively). We also investigated the influence of active learning strategy and type of the encoder.

RESULTS

On all the three datasets, DELR can achieve an area under curve (AUC) metric higher than 0.95 with only 100 image patches per class. Although its AUC is slightly lower than a fine-tuned CNN counterpart, DELR can be 536, 316, and 1481 times faster after pre-encoding. Moreover, DELR is proved to be compatible with a variety of active learning strategies and encoders.

CONCLUSIONS

DELR can achieve comparable accuracy to CNN with rapid running speed. These advantages make it a potential solution for real-time interactive data annotation.

Tissue clearing and imaging methods for cardiovascular development

Tissue imaging in 3D using visible light is limited and various clearing techniques were developed to increase imaging depth, but none provides universal solution for all tissues at all developmental stages. In this review, we focus on different tissue clearing methods for 3D imaging of heart and vasculature, based on chemical composition (solvent-based, simple immersion, hyperhydration, and hydrogel embedding techniques). We discuss in detail compatibility of various tissue clearing techniques with visualization methods: fluorescence preservation, immunohistochemistry, nuclear staining, and fluorescent dyes vascular perfusion. We also discuss myocardium visualization using autofluorescence, tissue shrinking, and expansion. Then we overview imaging methods used to study cardiovascular system and live imaging. We discuss heart and vessels segmentation methods and image analysis. The review covers the whole process of cardiovascular system 3D imaging, starting from tissue clearing and its compatibility with various visualization methods to the types of imaging methods and resulting image analysis.

Endothelial mechanotransduction in cardiovascular development and regeneration: emerging approaches and animal models

Living cells are exposed to multiple mechanical stimuli from the extracellular matrix or from surrounding cells. Mechanoreceptors are molecules that display status changes in response to mechanical stimulation, transforming physical cues into biological responses to help the cells adapt to dynamic changes of the microenvironment. Mechanical stimuli are responsible for shaping the tridimensional development and patterning of the organs in early embryonic stages. The development of the heart is one of the first morphogenetic events that occur in embryos. As the circulation is established, the vascular system is exposed to constant shear stress, which is the force created by the movement of blood. Both spatial and temporal variations in shear stress differentially modulate critical steps in heart development, such as trabeculation and compaction of the ventricular wall and the formation of the heart valves. Zebrafish embryos are small, transparent, have a short developmental period and allow for real-time visualization of a variety of fluorescently labeled proteins to recapitulate developmental dynamics. In this review, we will highlight the application of zebrafish models as a genetically tractable model for investigating cardiovascular development and regeneration. We will introduce our approaches to manipulate mechanical forces during critical stages of zebrafish heart development and in a model of vascular regeneration, as well as advances in imaging technologies to capture these processes at high resolution. Finally, we will discuss the role of molecules of the Plexin family and Piezo cation channels as major mechanosensors recently implicated in cardiac morphogenesis.