Fusing 2D and 3D molecular graphs as unambiguous molecular descriptors for conformational and chiral stereoisomers.

The rapid progress of machine learning (ML) in predicting molecular properties enables high-precision predictions being routinely achieved. However, many ML models, such as conventional molecular graph, cannot differentiate stereoisomers of certain types, particularly conformational and chiral ones that share the same bonding connectivity but differ in spatial arrangement. Here, we designed a hybrid molecular graph network, Chemical Feature Fusion Network (CFFN), to address the issue by integrating planar and stereo information of molecules in an interweaved fashion. The three-dimensional (3D, i.e., stereo) modality guarantees precision and completeness by providing unabridged information, while the two-dimensional (2D, i.e., planar) modality brings in chemical intuitions as prior knowledge for guidance. The zipper-like arrangement of 2D and 3D information processing promotes cooperativity between them, and their synergy is the key to our model's success. Experiments on various molecules or conformational datasets including a special newly created chiral molecule dataset comprised of various configurations and conformations demonstrate the superior performance of CFFN. The advantage of CFFN is even more significant in datasets made of small samples. Ablation experiments confirm that fusing 2D and 3D molecular graphs as unambiguous molecular descriptors can not only effectively distinguish molecules and their conformations, but also achieve more accurate and robust prediction of quantum chemical properties.

High-Performance 3D Stacked Micro All-Solid-State Thin-Film Lithium-Ion Batteries Based on the Stress-Compensation Effect.

A novel all-solid-state thin-film lithium-ion battery (LIB) is presented to address the trade-off issue between the specific capacity and stabilities in a conventional LIB. Different from the conventional one, this LIB device consists of two same LIB components located at the front and back surfaces of the substrate, respectively. These two LIB components form parallel connection by using the conductive through vias distributed in the substrate. Compared with the conventional one, this LIB device doubles the areal specific capacity. More importantly, due to the stress-compensation effect, this device effectively suppresses the stress induced by its volume changes resulting from the lithiation/delithiation processes and thermal expansion. Consequently, this device shows good cycling and thermal stabilities even when working at an industrial-grade high temperature of 125 °C. To further improve the specific capacity without sacrificing the stabilities, a 3D stacked LIB is successfully realized by using this LIB device as the cell, in which each cell is parallelly connected by using the above-mentioned conductive through vias. This 3D stacked LIB is experimentally demonstrated to obtain high specific capacity (79.9 µAh cm-2) and good stabilities (69.3% of retained capacity after 100 cycles at 125 °C) simultaneously.

Scaffold-based 3D cell culture models in cancer research.

Three-dimensional (3D) cell cultures have emerged as valuable tools in cancer research, offering significant advantages over traditional two-dimensional (2D) cell culture systems. In 3D cell cultures, cancer cells are grown in an environment that more closely mimics the 3D architecture and complexity of in vivo tumors. This approach has revolutionized cancer research by providing a more accurate representation of the tumor microenvironment (TME) and enabling the study of tumor behavior and response to therapies in a more physiologically relevant context. One of the key benefits of 3D cell culture in cancer research is the ability to recapitulate the complex interactions between cancer cells and their surrounding stroma. Tumors consist not only of cancer cells but also various other cell types, including stromal cells, immune cells, and blood vessels. These models bridge traditional 2D cell cultures and animal models, offering a cost-effective, scalable, and ethical alternative for preclinical research. As the field advances, 3D cell cultures are poised to play a pivotal role in understanding cancer biology and accelerating the development of effective anticancer therapies. This review article highlights the key advantages of 3D cell cultures, progress in the most common scaffold-based culturing techniques, pertinent literature on their applications in cancer research, and the ongoing challenges.

Cytotoxic and molecular differences of anticancer agents on 2D and 3D cell culture.

BACKGROUND: Cancer and multidrug resistance are regarded as concerns related to poor health outcomes. It was found that the monolayer of 2D cancer cell cultures lacks many important features compared to Multicellular Tumor Spheroids (MCTS) or 3D cell cultures which instead have the ability to mimic more closely the in vivo tumor microenvironment. This study aimed to produce 3D cell cultures from different cancer cell lines and to examine the cytotoxic activity of anticancer medications on both 2D and 3D systems, as well as to detect alterations in the expression of certain genes levels. METHOD: 3D cell culture was produced using 3D microtissue molds. The cytotoxic activities of colchicine, cisplatin, doxorubicin, and paclitaxel were tested on 2D and 3D cell culture systems obtained from different cell lines (A549, H1299, MCF-7, and DU-145). IC50 values were determined by MTT assay. In addition, gene expression levels of PIK3CA, AKT1, and PTEN were evaluated by qPCR. RESULTS: Similar cytotoxic activities were observed on both 3D and 2D cell cultures, however, higher concentrations of anticancer medications were needed for the 3D system. For instance, paclitaxel showed an IC50 of 6.234 µM and of 13.87 µM on 2D and 3D H1299 cell cultures, respectively. Gene expression of PIK3CA in H1299 cells also showed a higher fold change in 3D cell culture compared to 2D system upon treatment with doxorubicin. CONCLUSION: When compared to 2D cell cultures, the behavior of cells in the 3D system showed to be more resistant to anticancer treatments. Due to their shape, growth pattern, hypoxic core features, interaction between cells, biomarkers synthesis, and resistance to treatment penetration, the MCTS have the advantage of better simulating the in vivo tumor conditions. As a result, it is reasonable to conclude that 3D cell cultures may be a more promising model than the traditional 2D system, offering a better understanding of the in vivo molecular changes in response to different potential treatments and multidrug resistance development.

Exposure to emissions generated by 3-dimensional printing with polycarbonate: effects on peripheral vascular function, cardiac vascular morphology and expression of markers of oxidative stress in male rat cardiac tissue.

Three-dimensional (3D) printing with polycarbonate (PC) plastic occurs in manufacturing settings, homes, and schools. Emissions generated during printing with PC stock and bisphenol-A (BPA), an endocrine disrupter in PC, may induce adverse health effects. Inhalation of 3D printer emissions, and changes in endocrine function may lead to cardiovascular dysfunction. The goal of this study was to determine whether there were any changes in markers of peripheral or cardiovascular dysfunction in animals exposed to PC-emissions. Male Sprague Dawley rats were exposed to PC-emissions generated by 3D printing for 1, 4, 8, 15 or 30 d. Exposure induced a reduction in the expression of the antioxidant catalase (Cat) and endothelial nitric oxide synthase (eNos). Endothelin and hypoxia-induced factor 1α transcripts increased after 30 d. Alterations in transcription were associated with elevations in immunostaining for estrogen and androgen receptors, nitrotyrosine, and vascular endothelial growth factor in cardiac arteries of PC-emission exposed animals. There was also a reduction eNOS immunostaining in cardiac arteries from rats exposed to PC-emissions. Histological analyses of heart sections revealed that exposure to PC-emissions resulted in vasoconstriction of cardiac arteries and thickening of the vascular smooth muscle wall, suggesting there was a prolonged vasoconstriction. These findings are consistent with studies showing that inhalation 3D-printer emissions affect cardiovascular function. Although BPA levels in animals were relatively low, exposure-induced changes in immunostaining for estrogen and androgen receptors in cardiac arteries suggest that changes in the action of steroid hormones may have contributed to the alterations in morphology and markers of cardiac function.

The influence of patient positioning and immobilization equipment on MR image quality and image registration in radiation therapy.

INTRODUCTION: MRI is preferred for brain tumor assessment, while CT is used for radiotherapy simulation. This study evaluated immobilization equipment's impact on CT-MRI registration accuracy and MR image quality in RT setup. METHODS: We included CT and MR images from 11 patients with high-grade glioma, all of whom were immobilized with a thermoplastic mask and headrest. T1- and T2-weighted MR images were acquired using an MR head coil in a diagnostic setup (DS) and a body matrix coil in RT setup. To assess MR image quality, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were considered in some dedicated regions of interest. We also evaluated the impact of immobilization equipment on CT-MRI rigid registration using line profile and external contour methods. RESULTS: The CNR and SNR reduction was in the RT setup of imaging. This was more evident in T1-weighted images than in T2-weighted ones. The SNR decreased by 14.91% and 12.09%, while CNR decreased by 25.12% and 20.15% in T1- and T2-weighted images, respectively. The immobilization equipment in the RT setup decreased the mean error in rigid registration by 1.02 mm. The external contour method yielded Dice similarity coefficients (DSC) of 0.84 and 0.92 for CT-DS MRI and CT-RT MRI registration, respectively. CONCLUSION: The image quality reduction in the RT setup was due to the imaged region's anatomy and its position relative to the applied coil. Furthermore, optimizing the pulse sequence is crucial for MR imaging in RT applications. Although the use of immobilization equipment may decrease the image quality in the RT setup, it does not affect organ delineation, and the image quality is still satisfactory for this purpose. Also, the use of immobilization equipment in the RT setup has increased registration accuracy.

PP-ISEA: An Efficient Algorithm for High-Resolution Three-Dimensional Geometry Reconstruction of Space Targets Using Limited Inverse Synthetic Aperture Radar Images.

As the variety of space targets expands, two-dimensional (2D) ISAR images prove insufficient for target recognition, necessitating the extraction of three-dimensional (3D) information. The 3D geometry reconstruction method utilizing energy accumulation of ISAR image sequence (ISEA) facilitates superior reconstruction while circumventing the laborious steps associated with factorization methods. Nevertheless, ISEA's neglect of valid information necessitates a high quantity of images and elongated operation times. This paper introduces a partitioned parallel 3D reconstruction method utilizing sorted-energy semi-accumulation with ISAR image sequences (PP-ISEA) to address these limitations. The PP-ISEA innovatively incorporates a two-step search pattern-coarse and fine-that enhances search efficiency and conserves computational resources. It introduces a novel objective function 'sorted-energy semi-accumulation' to discern genuine scatterers from spurious ones and establishes a redundant point exclusion module. Experiments on the scatterer model and simulated electromagnetic model demonstrate that the PP-ISEA reduces the minimum image requirement from ten to four for high-quality scatterer model reconstruction, thereby offering superior reconstruction quality in less time.

An Automatic Method for Elbow Joint Recognition, Segmentation and Reconstruction.

Elbow computerized tomography (CT) scans have been widely applied for describing elbow morphology. To enhance the objectivity and efficiency of clinical diagnosis, an automatic method to recognize, segment, and reconstruct elbow joint bones is proposed in this study. The method involves three steps: initially, the humerus, ulna, and radius are automatically recognized based on the anatomical features of the elbow joint, and the prompt boxes are generated. Subsequently, elbow MedSAM is obtained through transfer learning, which accurately segments the CT images by integrating the prompt boxes. After that, hole-filling and object reclassification steps are executed to refine the mask. Finally, three-dimensional (3D) reconstruction is conducted seamlessly using the marching cube algorithm. To validate the reliability and accuracy of the method, the images were compared to the masks labeled by senior surgeons. Quantitative evaluation of segmentation results revealed median intersection over union (IoU) values of 0.963, 0.959, and 0.950 for the humerus, ulna, and radius, respectively. Additionally, the reconstructed surface errors were measured at 1.127, 1.523, and 2.062 mm, respectively. Consequently, the automatic elbow reconstruction method demonstrates promising capabilities in clinical diagnosis, preoperative planning, and intraoperative navigation for elbow joint diseases.

Characterization of 3D Organotypic Culture of Mouse Adipose-Derived Stem Cells.

Although stem cells are a promising avenue for harnessing the potential of adipose tissue, conventional two-dimensional (2D) culture methods have limitations. This study explored the use of three-dimensional (3D) cultures to preserve the regenerative potential of adipose-derived stem cells (ADSCs) and investigated their cellular properties. Flow cytometric analysis revealed significant variations in surface marker expressions between the two culture conditions. While 2D cultures showed robust surface marker expressions, 3D cultures exhibited reduced levels of CD44, CD90.2, and CD105. Adipogenic differentiation in 3D organotypic ADSCs faced challenges, with decreased organoid size and limited activation of adipogenesis-related genes. Key adipocyte markers, such as lipoprotein lipase (LPL) and adipoQ, were undetectable in 3D-cultured ADSCs, unlike positive controls in 2D-cultured mesenchymal stem cells (MSCs). Surprisingly, 3D-cultured ADSCs underwent mesenchymal-epithelial transition (MET), evidenced by increased E-cadherin and EpCAM expression and decreased mesenchymal markers. This study highlights successful ADSC organoid formation, notable MSC phenotype changes in 3D culture, adipogenic differentiation challenges, and a distinctive shift toward an epithelial-like state. These findings offer insights into the potential applications of 3D-cultured ADSCs in regenerative medicine, emphasizing the need for further exploration of underlying molecular mechanisms.

A Comprehensive Review of Hydrogel-Based Drug Delivery Systems: Classification, Properties, Recent Trends, and Applications.

As adaptable biomaterials, hydrogels have shown great promise in several industries, which include the delivery of drugs, engineering of tissues, biosensing, and regenerative medicine. These hydrophilic polymer three-dimensional networks have special qualities like increased content of water, soft, flexible nature, as well as biocompatibility, which makes it excellent candidates for simulating the extracellular matrix and promoting cell development and tissue regeneration. With an emphasis on their design concepts, synthesis processes, and characterization procedures, this review paper offers a thorough overview of hydrogels. It covers the various hydrogel material types, such as natural polymers, synthetic polymers, and hybrid hydrogels, as well as their unique characteristics and uses. The improvements in hydrogel-based platforms for controlled drug delivery are examined. It also looks at recent advances in bioprinting methods that use hydrogels to create intricate tissue constructions with exquisite spatial control. The performance of hydrogels is explored through several variables, including mechanical properties, degradation behaviour, and biological interactions, with a focus on the significance of customizing hydrogel qualities for particular applications. This review paper also offers insights into future directions in hydrogel research, including those that promise to advance the discipline, such as stimuli-responsive hydrogels, self-healing hydrogels, and bioactive hydrogels. Generally, the objective of this review paper is to provide readers with a detailed grasp of hydrogels and all of their potential uses, making it an invaluable tool for scientists and researchers studying biomaterials and tissue engineering.

3D Digital and Printed Hearts from Different Canine Breeds as an Educational Tool for Radiographic Interpretation.

Three-dimensional (3D) printing is a new method of creating anatomical models, which can enhance the training of students and health professionals. The large breed-variation in dogs means that interpretation of thoracic radiographs can be challenging for the inexperienced radiologist. The aim of this study was to develop digital and printed 3D cardiac models from six canine breeds and evaluate their use as a tool for studying breed variations in radiology. The printed and digital 3D cardiac models were used by postgraduate veterinary students in diagnostic imaging along with a theoretical class on the subject and students completed a pre- and post-test, assessing cardiac size on thoracic radiographs in order to verify the usefulness of the models. The students then completed a satisfaction questionnaire using a Likert scale. There was a significant difference between the pre-test and the post-test results, with greater accuracy after using the 3D models. More errors were made in pre-test interpretation of radiographs from English Cocker Spaniel, English Bulldog, and Yorkshire Terrier and there were a significantly higher number of correct answers after using the 3D models. The vast majority of responses to all questions in the satisfaction questionnaire were positive, with partial or total agreement of the participants. This study demonstrates that digitally printed cardiac models from different breeds of dogs are effective learning tools. They helped students to better understand the relevant spatial relationship and cardiac morphology and to compare this anatomy with the radiographic image. Models are provided in 3D PDF and STL files for download.

The effectiveness of three-dimensional printing in undergraduate and postgraduate anatomy education: A review of reviews.

PURPOSE: Several reviews and meta-analyses about the value of three-dimensional (3D) printing in anatomy education have been published in the last years, with variable-and sometimes confusing- outcomes. We performed a review of those reviews, in order to shed light on the results concerning the effectiveness of 3D printing in anatomy education, compared to specific traditional methods and other technologies. METHODS: The electronic databases PubMed, ERIC and Cochrane library were searched for reviews or meta-analyses with purpose to investigate the effectiveness of 3D printing in undergraduate and postgraduate anatomy education. RESULTS: Seven papers were included: four systematic reviews with meta-analysis, one narrative, one scoping and one systematic review. Overall, it has been shown that 3D printing is more effective than two-dimensional (2D) images for undergraduate health science students, but not for medical residents. Also, it seems to be more effective than 2D methods for teaching anatomy of some relatively complex structures, such as the nervous system. However, there is generally lack of evidence about the effectiveness of 3D printing in comparison with other 3D visualization methods. CONCLUSIONS: For students, the effectiveness of 3D printing in anatomy education is higher than 2D methods. There is need for studies to investigate the effectiveness of 3D printing in comparison with other 3D visualization methods, such as cadaveric dissection, prosection and virtual reality. There is also need for research to explore if 3D printing is effective as a supplementary tool in a blended anatomy learning approach.

Trends and future perspectives of 3D printing in prosthodontics.

The three-dimensional (3D) printing technology has led to transformative shift in prosthodontics. This review summarizes the evolution, processing techniques, materials, integration of digital plan, challenges, clinical applications and future directions of 3D printing in prosthodontics. It appraises from the launch of 3D printing to its current applications in prosthodontics. The convergence of printing technology with digital dentistry has facilitated the creation of accurate, customized prostheses, redefining treatment planning, design, and manufacturing processes. The progression of this technology is from generating models to prosthesis like-fixed dental prosthesis (FDP), implants, and splints. Additionally, it exhibits more wide capabilities. The exploration of materials for 3D printing provides various options like polymers, ceramics, metals, and hybrids, each with distinctive properties that are applicable to different clinical scenarios. The combination of 3D-printing technology and digital workflow simplifies the processes of data transfer, computer-aided design (CAD) design to fabrication, decreasing errors and chairside time. The clinical benefits include enhanced accuracy, comfort, conservative lab procedures, and economics. Challenges in the technology involve significant aspects like initial investment, material availability, and skill requirements. Future trends emphasize on research for improved materials, bioprinting integration, artificial intelligence (AI) application, regularization efforts to ensure safe and common use of the technology. 3D printing offers promise in prosthodontics, addressing challenges through research. The material improvements will promote its broader adoption and revolutionize the future of dental rehabilitation.

Three-dimensional electrical impedance tomography to study regional ventilation/perfusion ratios in anesthetized pigs.

This study aimed to develop a three-dimensional (3-D) method for assessing ventilation/perfusion (V/Q̇) ratios in a pig model of hemodynamic perturbations using electrical impedance tomography (EIT). To evaluate the physiological coherence of changes in EIT-derived V/Q̇ ratios, global EIT-derived V/Q̇ mismatches were compared with global gold standards. The study found regional heterogeneity in the distribution of V/Q̇ ratios in both the ventrodorsal and craniocaudal directions. Although global EIT-derived indices of V/Q̇ mismatch consistently underestimated both low and high V/Q̇ mismatch compared with global gold standards, the direction of the change was similar. We made the software available at no cost for other researchers to use. Future studies should compare regional V/Q̇ ratios determined by our method against other regional, high-resolution methods.NEW & NOTEWORTHY In this study, we introduce a novel 3-D method for assessing ventilation-perfusion (V/Q̇) ratios using electrical impedance tomography (EIT). Heterogeneity in V/Q̇ distribution showcases the significant potential for enhanced understanding of pulmonary conditions. This work signifies a substantial step forward in the application of EIT for monitoring and managing lung diseases.

The role of three-dimensional in vitro models in modelling the inflammatory microenvironment associated with obesity in breast cancer.

Obesity is an established risk factor for breast cancer in postmenopausal women. However, the underlying biological mechanisms of how obesity contributes to breast cancer remains unclear. The inflammatory adipose microenvironment is central to breast cancer progression and has been shown to favour breast cancer cell growth and to reduce efficacy of anti-cancer treatments. Thus, it is imperative to further our understanding of the inflammatory microenvironment seen in breast cancer patients with obesity. Three-dimensional (3D) in vitro models offer a key tool in increasing our understanding of such complex interactions within the adipose microenvironment. This review discusses some of the approaches utilised to recapitulate the breast tumour microenvironment, including various co-culture and 3D in vitro models. We consider how these model systems contribute to the understanding of breast cancer research, with particular focus on the inflammatory tumour microenvironment. This review aims to provide insight and prospective future directions on the utility of such model systems for breast cancer research.

Multicolor 3D Orbital Tracking.

Feedback-based single-particle tracking (SPT) is a powerful technique for investigating particle behavior with very high spatiotemporal resolution. The ability to follow different species and their interactions independently adds a new dimension to the information available from SPT. However, only a few approaches have been expanded to multiple colors and no method is currently available that can follow two differently labeled biomolecules in 4 dimensions independently. In this proof-of-concept paper, the new modalities available when performing 3D orbital tracking with a second detection channel are demonstrated. First, dual-color tracking experiments are described studying independently diffusing particles of different types. For interacting particles where their motion is correlated, a second modality is implemented where a particle is tracked in one channel and the position of the second fluorescence species is monitored in the other channel. As a third modality, 3D orbital tracking is performed in one channel while monitoring its spectral signature in a second channel. This last modality is used to successfully readout accurate Förster Resonance Energy Transfer (FRET) values over time while tracking a mobile particle.

Forecasting Heliospheric CME Solar-Wind Parameters Using the UCSD Time-Dependent Tomography and ISEE Interplanetary Scintillation Data: The 10 March 2022 CME.

Remotely sensed interplanetary scintillation (IPS) data from the Institute for Space-Earth Environmental Research (ISEE), Japan, allows a determination of solar-wind parameters throughout the inner heliosphere. We show the 3D analysis technique developed for these data sets that forecast plasma velocity, density, and component magnetic fields at Earth, as well at the other inner heliospheric planets and spacecraft. One excellent coronal mass ejection (CME) example that occurred on the 10 March 2022 was viewed not only in the ISEE IPS analyses, but also by the spacecraft near Earth that measured the CME arrival at one AU. Solar Orbiter, that was nearly aligned along the Earth radial at 0.45 AU, also measured the CME in plasma density, velocity, and magnetic field. BepiColombo at 0.42 AU was also aligned with the STEREO A spacecraft, and viewed this CME. The instruments used here from BepiColombo include: 1) the European-Space-Agency Mercury-Planetary-Orbiter magnetic field measurements; 2) the Japan Aerospace Exploration Agency Mio spacecraft Solar Particle Monitor that viewed the CME Forbush decrease, and the Mercury Plasma Experiment/Mercury Electron Analyzer instruments that measured particles and solar-wind density from below the spacecraft protective sunshield covering. This article summarizes the analysis using ISEE, Japan real-time data for these forecasts: it provides a synopsis of the results and confirmation of the CME event morphology after its arrival, and discusses how future IPS analyses can augment these results.

Fabrication of 3D-Printed Contact Lens Composed of Polyethylene Glycol Diacrylate for Controlled Release of Azithromycin.

Since three-dimensional (3D)-printed tablets were approved by the United States Food and Drug Administration (FDA), 3D printing technology has garnered increasing interest for the fabrication of medical and pharmaceutical devices. With various dosing devices being designed for manufacture by 3D printing, 3D-printed ophthalmic formulations to release drugs have been one such target of investigation. In the current study, 3D-printed contact lenses designed for the controlled release of the antibiotic azithromycin were produced by vat photopolymerization, and the effect of the printer ink composition and a second curing process was investigated. The azithromycin-loaded contact lenses were composed of the cross-linking reagent polyethylene glycol diacrylate (PEGDA), PEG 400 as a solvent, a photoinitiator, and azithromycin. The 3D-printed contact lenses were fabricated successfully, and formulations with lower PEGDA concentrations produced thicker lenses. The mechanical strength of the PEGDA-based contact lenses was dependent on the amount of PEGDA and was improved by a second curing process. Drug release from 3D-printed contact lenses was reduced in the samples with a second curing process. The azithromycin-loaded contact lenses exhibited antimicrobial effects in vitro for both Gram-positive and -negative bacteria. These results suggest that 3D-printed contact lenses containing antibiotics are an effective model for treating eye infections by controlling drug release.

Weakly supervised video-based cardiac detection for hypertensive cardiomyopathy.

INTRODUCTION: Parameters, such as left ventricular ejection fraction, peak strain dispersion, global longitudinal strain, etc. are influential and clinically interpretable for detection of cardiac disease, while manual detection requires laborious steps and expertise. In this study, we evaluated a video-based deep learning method that merely depends on echocardiographic videos from four apical chamber views of hypertensive cardiomyopathy detection. METHODS: One hundred eighty-five hypertensive cardiomyopathy (HTCM) patients and 112 healthy normal controls (N) were enrolled in this diagnostic study. We collected 297 de-identified subjects' echo videos for training and testing of an end-to-end video-based pipeline of snippet proposal, snippet feature extraction by a three-dimensional (3-D) convolutional neural network (CNN), a weakly-supervised temporally correlated feature ensemble, and a final classification module. The snippet proposal step requires a preliminarily trained end-systole and end-diastole timing detection model to produce snippets that begin at end-diastole, and involve contraction and dilatation for a complete cardiac cycle. A domain adversarial neural network was introduced to systematically address the appearance variability of echo videos in terms of noise, blur, transducer depth, contrast, etc. to improve the generalization of deep learning algorithms. In contrast to previous image-based cardiac disease detection architectures, video-based approaches integrate spatial and temporal information better with a more powerful 3D convolutional operator. RESULTS: Our proposed model achieved accuracy (ACC) of 92%, area under receiver operating characteristic (ROC) curve (AUC) of 0.90, sensitivity(SEN) of 97%, and specificity (SPE) of 84% with respect to subjects for hypertensive cardiomyopathy detection in the test data set, and outperformed the corresponding 3D CNN (vanilla I3D: ACC (0.90), AUC (0.89), SEN (0.94), and SPE (0.84)). On the whole, the video-based methods remarkably appeared superior to the image-based methods, while few evaluation metrics of image-based methods exhibited to be more compelling (sensitivity of 93% and negative predictive value of 100% for the image-based methods (ES/ED and random)). CONCLUSION: The results supported the possibility of using end-to-end video-based deep learning method for the automated diagnosis of hypertensive cardiomyopathy in the field of echocardiography to augment and assist clinicians. TRIAL REGISTRATION: Current Controlled Trials ChiCTR1900025325, Aug, 24, 2019. Retrospectively registered.

Creating Virtual Models and 3D Movies Using DemoMaker for Anatomical Education.

Three-dimensional (3D) anatomy models have been used for education in health professional schools globally. Virtual technology has become more popular for online teaching since the COVID-19 pandemic. This chapter will describe a project in which a series of virtual anatomical models of organs and structures were developed for educational purposes, and it will describe in detail how to build three-dimensional (3D) movies using DemoMaker. Although setting up the 3D system was complicated and challenging, the process of reconstructing 3D models from radiographic images and the steps of creating animations and 3D movies are exponentially simpler. These efforts require minimal training, thus allowing most people to be able to engage in this modeling process and utilize the moviemaking steps. Amira® software and computed tomographic angiography (CTA) data were used to create 3D models of the lungs, heart, liver, stomach, kidney, etc. The anatomical locations of these structures within the body can be identified and visualized by recording information from multiple CTA slices using volume and surface segmentation. Ultimately, these virtual 3D models can be displayed via dual projectors onto a specialized silver screen and visualized stereoscopically by viewers as long as they wear 3D polarized glasses. Once these 3D movies are created, they can be played automatically on a computer screen, silver screen, 3D system playback screen, and video player, and they can be embedded into PowerPoint lecture slides. Both virtual models and movies are suitable for self-directed learning, face-to-face class teaching, and virtual anatomy education. Model animations and 3D movie displays offer students the opportunities to learn about anatomy and the anatomical positions of organs in the body and their 3D relationships to one another. By observing and studying these 3D models, students have the potential to be able to compartmentalize the anatomical information and retain it at a higher level than students learning corresponding anatomy without similar resources.