ABSTRACT
Background: Eczema is a common inflammatory skin disease with a significant global health burden. Eczema has a significant impact on quality of life. Objective: We aimed to estimate the prevalence, severity, and risk factors associated with eczema among schoolchildren in Saudi Arabia. Methods: The standardized Global Asthma Network questionnaires and methodology were used to conduct a nationwide cross-sectional study across 20 regions in Saudi Arabia between March and April 2019. Data were collected from 137 primary schools and 140 intermediate schools by using a multistage stratified cluster sampling method. Results: The study included 3614 young children aged 6 to 7 years and 4068 adolescents aged 13 to 14 years. Current eczema was prevalent among 4.5% of the children and 5.1% of the adolescents. Severe eczema was reported in 0.8% and 0.9% of the young children and adolescents, respectively. Several factors showed significant association with eczema. Among the children, eczema was linked positively to having a history of chest infections and wheezing in early life, as well as to ever attending day care and current exposure to cats. Among the adolescents, the main potential risk factors included paracetamol use in the previous year, adherence to a lifestyle of vigorous physical activity, and current exposure to cats. Conversely, high consumption of nuts was found to be negatively associated with eczema. Conclusion: The prevalence of eczema in schoolchildren in Saudi Arabia is lower than the global average but within the average range for the Eastern Mediterranean region. Further studies in Saudi Arabia should be conducted to identify variation among different regions.
ABSTRACT
The conversion of CO2 into liquid fuels, using only sunlight and water, offers a promising path to carbon neutrality. An outstanding challenge is to achieve high efficiency and product selectivity. Here, we introduce a wireless photocatalytic architecture for conversion of CO2 and water into methanol and oxygen. The catalytic material consists of semiconducting nanowires decorated with core-shell nanoparticles, with a copper-rhodium core and a chromium oxide shell. The Rh/CrOOH interface provides a unidirectional channel for proton reduction, enabling hydrogen spillover at the core-shell interface. The vectorial transfer of protons, electrons, and hydrogen atoms allows for switching the mechanism of CO2 reduction from a proton-coupled electron transfer pathway in aqueous solution to hydrogenation of CO2 with a solar-to-methanol efficiency of 0.22%. The reported findings demonstrate a highly efficient, stable, and scalable wireless system for synthesis of methanol from CO2 that could provide a viable path toward carbon neutrality and environmental sustainability.
ABSTRACT
CONTEXT: The aim of this work is to use first principles calculations to examine the effects of different mechanical strains on the optoelectronic and photocatalytic capabilities of the 2D/2D nanoheterostructure of AlN/GaN. By utilizing the lmBJ (Meta-GGA) and PBEsol (GGA) functional, the bandgap of the nanoheterostructure is calculated and found to be 4.89 eV and 3.24 eV. Simulated 2D AlN/GaN nanoheterostructure exhibits exceptional optical and electronic characteristics under applied biaxial tensile and compressive strains. The band gap changes from 4.89 to 3.77 eV, while the energy gap nature transitions from direct to indirect during tensile strain fluctuations of 0% to 8%. Strain is also found to have a significant effect on the optical absorption peaks. And a 0-8% rise in tensile strain causes the initial absorption peak of the 2D AlN/GaN nanoheterostructure to shift from 4.88 to 4.20 eV, which results in a 14% red shift in photon energy for every 2% change in strain. Furthermore, the optimum bandgap and band edge positions of the 2D AlN/GaN nanoheterostructure enable the water redox process to produce hydrogen and oxygen for wide range of pH. Thus, modification via strain may be an effective method for altering the optical as well as electronic characteristics of a 2D AlN/GaN nanoheterostructure, and this study may pave the way for new applications of this material in optoelectronic devices in the future. METHODS: In the current work, density functional theory is used to explore every attribute of the 2D AlN/GaN nanoheterostructure. To characterize the electronic exchange-correlation, we used the PBEsol functional. In order to prevent any interlayer contact between periodicity of images, a vacuum is produced along the z-direction of approximately 10 Å. To increase the precision of bandgap prediction, the electronic and optical characteristics were computed using the meta-GGA lmBJ functional. To account for interlayer van der Waals interactions, nanoheterostructure computations were performed using the DFT-D3 functional.
ABSTRACT
The role of sediment oxygen demand (SOD) in causing dissolved oxygen (DO) depletion is widely acknowledged, with previous studies mainly focusing on chemical and biological SOD separately. However, the relationship between the putative functions of sediment microbes and SOD, and their impact on DO depletion in overlying water, remains unclear. In this study, DO depletion was observed in the downstream of the Gan River during the summer. Sediments were sampled from three downstream sites (YZ, Down1, and Down2) and one upstream site (CK) as a control. Aquatic physicochemical parameters and SOD levels were measured, and microbial functions were inferred from taxonomic genes through analyses of the 16S rRNA gene. The results showed that DO depletion sites exhibited a higher SOD rate compared to CK. The microbial community structure was influenced by the spatial variation of Proteobacteria, Chloroflexi, and Bacteroidota, with total organic carbon (TOC) content acting as a significant environmental driver. A negative correlation was observed between microbial diversity and DO concentration (p < 0.05). Aerobic microbes were more abundant in DO depletion sites, particularly Proteobacteria. Microbes involved in various biogeochemical cycles, such as carbon (methane oxidation, methanotrophs, and methylotrophs), nitrogen (nitrification and denitrification), sulfur (sulfide and sulfur compound oxidation), and manganese cycles (manganese oxidation), exhibited higher abundance in DO depletion sites, except for the iron cycle (iron oxidation). These processes were negatively correlated with DO concentration and positively with SOD (p < 0.05). Overall, the results highlight that aerobic bacteria's metabolic processes consume oxygen, increasing the SOD rate and contributing to DO depletion in the overlying water. Additionally, the study underscores the importance of targeting the removal of in situ microbial molecular mechanisms associated with toxic H2S and CH4 to support reoxygenation efforts in rehabilitating DO depletion sites in the Gan River, aiding in identifying factors controlling DO consumption and offering practical value for the river's restoration and management.
ABSTRACT
BACKGROUND: The current mainstream multi-modal medical image-to-image translation methods face a contradiction. Supervised methods with outstanding performance rely on pixel-wise aligned training data to constrain the model optimization. However, obtaining pixel-wise aligned multi-modal medical image datasets is challenging. Unsupervised methods can be trained without paired data, but their reliability cannot be guaranteed. At present, there is no ideal multi-modal medical image-to-image translation method that can generate reliable translation results without the need for pixel-wise aligned data. PURPOSE: This work aims to develop a novel medical image-to-image translation model that is independent of pixel-wise aligned data (MITIA), enabling reliable multi-modal medical image-to-image translation under the condition of misaligned training data. METHODS: The proposed MITIA model utilizes a prior extraction network composed of a multi-modal medical image registration module and a multi-modal misalignment error detection module to extract pixel-level prior information from training data with misalignment errors to the largest extent. The extracted prior information is then used to construct a regularization term to constrain the optimization of the unsupervised cycle-consistent Generative Adversarial Network model, restricting its solution space and thereby improving the performance and reliability of the generator. We trained the MITIA model using six datasets containing different misalignment errors and two well-aligned datasets. Subsequently, we conducted quantitative analysis using peak signal-to-noise ratio and structural similarity as metrics. Moreover, we compared the proposed method with six other state-of-the-art image-to-image translation methods. RESULTS: The results of both quantitative analysis and qualitative visual inspection indicate that MITIA achieves superior performance compared to the competing state-of-the-art methods, both on misaligned data and aligned data. Furthermore, MITIA shows more stability in the presence of misalignment errors in the training data, regardless of their severity or type. CONCLUSIONS: The proposed method achieves outstanding performance in multi-modal medical image-to-image translation tasks without aligned training data. Due to the difficulty in obtaining pixel-wise aligned data for medical image translation tasks, MITIA is expected to generate significant application value in this scenario compared to existing methods.
ABSTRACT
The transmission environment of underwater wireless sensor networks is open, and important transmission data can be easily intercepted, interfered with, and tampered with by malicious nodes. Malicious nodes can be mixed in the network and are difficult to distinguish, especially in time-varying underwater environments. To address this issue, this article proposes a GAN-based trusted routing algorithm (GTR). GTR defines the trust feature attributes and trust evaluation matrix of underwater network nodes, constructs the trust evaluation model based on a generative adversarial network (GAN), and achieves malicious node detection by establishing a trust feature profile of a trusted node, which improves the detection performance for malicious nodes in underwater networks under unlabeled and imbalanced training data conditions. GTR combines the trust evaluation algorithm with the adaptive routing algorithm based on Q-Learning to provide an optimal trusted data forwarding route for underwater network applications, improving the security, reliability, and efficiency of data forwarding in underwater networks. GTR relies on the trust feature profile of trusted nodes to distinguish malicious nodes and can adaptively select the forwarding route based on the status of trusted candidate next-hop nodes, which enables GTR to better cope with the changing underwater transmission environment and more accurately detect malicious nodes, especially unknown malicious node intrusions, compared to baseline algorithms. Simulation experiments showed that, compared to baseline algorithms, GTR can provide a better malicious node detection performance and data forwarding performance. Under the condition of 15% malicious nodes and 10% unknown malicious nodes mixed in, the detection rate of malicious nodes by the underwater network configured with GTR increased by 5.4%, the error detection rate decreased by 36.4%, the packet delivery rate increased by 11.0%, the energy tax decreased by 11.4%, and the network throughput increased by 20.4%.
ABSTRACT
Electroencephalography (EEG)-based applications in brain-computer interfaces (BCIs), neurological disease diagnosis, rehabilitation, etc., rely on supervised approaches such as classification that requires given labels. However, with the ever-increasing amount of EEG data, incomplete or incorrectly labeled or unlabeled EEG data are increasing. It likely degrades the performance of supervised approaches. In this work, we put forward a novel unsupervised exploratory EEG analysis solution by clustering based on low-dimensional prototypes in latent space that are associated with the respective clusters. Having the prototype as a baseline of each cluster, a compositive similarity is defined to act as the critic function in clustering, which incorporates similarities on three levels. The approach is implemented with a Generative Adversarial Network (GAN), termed W-SLOGAN, by extending the Stein Latent Optimization for GANs (SLOGAN). The Gaussian Mixture Model (GMM) is utilized as the latent distribution to adapt to the diversity of EEG signal patterns. The W-SLOGAN ensures that images generated from each Gaussian component belong to the associated cluster. The adaptively learned Gaussian mixing coefficients make the model remain effective in dealing with an imbalanced dataset. By applying the proposed approach to two public EEG or intracranial EEG (iEEG) epilepsy datasets, our experiments demonstrate that the clustering results are close to the classification of the data. Moreover, we present several findings that were discovered by intra-class clustering and cross-analysis of clustering and classification. They show that the approach is attractive in practice in the diagnosis of the epileptic subtype, multiple labelling of EEG data, etc.
Subject(s)
Brain-Computer Interfaces , Electroencephalography , Electroencephalography/methods , Humans , Cluster Analysis , Epilepsy/diagnosis , Epilepsy/physiopathology , Algorithms , Signal Processing, Computer-Assisted , Neural Networks, ComputerABSTRACT
Obtaining accurate distance or depth information in endoscopy is crucial for the effective utilization of navigation systems. However, due to space constraints, incorporating depth cameras into endoscopic systems is often impractical. Our goal is to estimate depth images directly from endoscopic images using deep learning. This study presents a three-step methodology for training a depth-estimation network model. Initially, simulated endoscopy images and corresponding depth maps are generated using Unity based on a colon surface model obtained from segmented computed tomography colonography data. Subsequently, a cycle generative adversarial network model is employed to enhance the realism of the simulated endoscopy images. Finally, a deep learning model is trained using the synthesized endoscopy images and depth maps to estimate depths accurately. The performance of the proposed approach is evaluated and compared against prior studies utilizing unsupervised training methods. The results demonstrate the superior precision of the proposed technique in estimating depth images within endoscopy. The proposed depth estimation method holds promise for advancing the field by enabling enhanced navigation, improved lesion marking capabilities, and ultimately leading to better clinical outcomes.
ABSTRACT
Synthetic tabular health data plays a crucial role in healthcare research, addressing privacy regulations and the scarcity of publicly available datasets. This is essential for diagnostic and treatment advancements. Among the most promising models are transformer-based Large Language Models (LLMs) and Generative Adversarial Networks (GANs). In this paper, we compare LLM models of the Pythia LLM Scaling Suite with varying model sizes ranging from 14M to 1B, against a reference GAN model (CTGAN). The generated synthetic data are used to train random forest estimators for classification tasks to make predictions on the real-world data. Our findings indicate that as the number of parameters increases, LLM models outperform the reference GAN model. Even the smallest 14M parameter models perform comparably to GANs. Moreover, we observe a positive correlation between the size of the training dataset and model performance. We discuss implications, challenges, and considerations for the real-world usage of LLM models for synthetic tabular data generation.
Subject(s)
Benchmarking , Computer SimulationABSTRACT
Background: Low-dose computed tomography (LDCT) is a diagnostic imaging technique designed to minimize radiation exposure to the patient. However, this reduction in radiation may compromise computed tomography (CT) image quality, adversely impacting clinical diagnoses. Various advanced LDCT methods have emerged to mitigate this challenge, relying on well-matched LDCT and normal-dose CT (NDCT) image pairs for training. Nevertheless, these methods often face difficulties in distinguishing image details from nonuniformly distributed noise, limiting their denoising efficacy. Additionally, acquiring suitably paired datasets in the medical domain poses challenges, further constraining their applicability. Hence, the objective of this study was to develop an innovative denoising framework for LDCT images employing unpaired data. Methods: In this paper, we propose a LDCT denoising network (DNCNN) that alleviates the need for aligning LDCT and NDCT images. Our approach employs generative adversarial networks (GANs) to learn and model the noise present in LDCT images, establishing a mapping from the pseudo-LDCT to the actual NDCT domain without the need for paired CT images. Results: Within the domain of weakly supervised methods, our proposed model exhibited superior objective metrics on the simulated dataset when compared to CycleGAN and selective kernel-based cycle-consistent GAN (SKFCycleGAN): the peak signal-to-noise ratio (PSNR) was 43.9441, the structural similarity index measure (SSIM) was 0.9660, and the visual information fidelity (VIF) was 0.7707. In the clinical dataset, we conducted a visual effect analysis by observing various tissues through different observation windows. Our proposed method achieved a no-reference structural sharpness (NRSS) value of 0.6171, which was closest to that of the NDCT images (NRSS =0.6049), demonstrating its superiority over other denoising techniques in preserving details, maintaining structural integrity, and enhancing edge contrast. Conclusions: Through extensive experiments on both simulated and clinical datasets, we demonstrated the superior efficacy of our proposed method in terms of denoising quality and quantity. Our method exhibits superiority over both supervised techniques, including block-matching and 3D filtering (BM3D), residual encoder-decoder convolutional neural network (RED-CNN), and Wasserstein generative adversarial network-VGG (WGAN-VGG), and over weakly supervised approaches, including CycleGAN and SKFCycleGAN.
ABSTRACT
Micro light-emitting diodes (micro-LEDs) are pivotal in next-generation display technologies, driven by the need for high pixel density. This study introduces a novel methodology utilizing wide sapphire nanomembranes (W-SNM) as a dual-purpose template for high-quality epitaxial growth and the mechanical lift-off of individual micro-LEDs. Micro-LEDs grow individually on W-SNM, obviating the chip singulation process. By employing mechanical fracturing of the thin W-SNM, our method facilitates the transfer of micro-LEDs without the conventional laser lift-off (LLO) process. Previously introduced sapphire nanomembranes (SNM) have shown promise in enhancing epitaxial layer quality; however, they encountered challenges in managing micro-LED size variation and achieving efficient mechanical transfer. Here, we apply simple yet effective adjustments to the SNM structure, specifically, its elevation and widening. This strategic modification allows micro-LEDs to endure applied forces without incurring cracks or defects, ensuring that only the targeted W-SNM are selectively fractured. The mechanically transferred vertical 15 × 15 µm2 micro-LED device operates at an optimal turn-on voltage of 3.3 V. Finite element simulations validate the mechanical strain distribution between the W-SNM and GaN when pressure is applied, confirming the efficacy of our design approach. This pioneering methodology offers a streamlined, efficient pathway for the production and mechanical transfer of micro-LEDs, presenting new avenues for their integration into next-generation, high-performance displays.
ABSTRACT
Background: Influenza virus is one of the most common pathogens that cause viral pneumonia. During pneumonia, host immune inflammation regulation involves microbiota in the intestine and glycolysis in the lung tissues. In the clinical guidelines for pneumonia treatment in China, Ma Xing Shi Gan Decoction (MXSG) is a commonly prescribed traditional Chinese medicine formulation with significant efficacy, however, it remains unclear whether its specific mechanism of action is related to the regulation of intestinal microbiota structure and lung tissue glycolysis. Objective: This study aimed to investigate the mechanism of action of MXSG in an animal model of influenza virus-induced pneumonia. Specifically, we aimed to elucidate how MXSG modulates intestinal microbiota structure and lung tissue glycolysis to exert its therapeutic effects on pneumonia. Methods: We established a mouse model of influenza virus-induced pneumoni, and treated with MXSG. We observed changes in inflammatory cytokine levels and conducted 16S rRNA gene sequencing to assess the intestinal microbiota structure and function. Additionally, targeted metabolomics was performed to analyze lung tissue glycolytic metabolites, and Western blot and enzyme-linked immunosorbent assays were performed to assess glycolysis-related enzymes, lipopolysaccharides (LPSs), HIF-1a, and macrophage surface markers. Correlation analysis was conducted between the LPS and omics results to elucidate the relationship between intestinal microbiota and lung tissue glycolysis in pneumonia animals under the intervention of Ma Xing Shi Gan Decoction. Results: MXSG reduced the abundance of Gram-negative bacteria in the intestines, such as Proteobacteria and Helicobacter, leading to reduced LPS content in the serum and lungs. This intervention also suppressed HIF-1a activity and lung tissue glycolysis metabolism, decreased the number of M1-type macrophages, and increased the number of M2-type macrophages, effectively alleviating lung damage caused by influenza virus-induced pneumonia. Conclusion: MXSG can alleviate glycolysis in lung tissue, suppress M1-type macrophage activation, promote M2-type macrophage activation, and mitigate inflammation in lung tissue. This therapeutic effect appears to be mediated by modulating gut microbiota and reducing endogenous LPS production in the intestines. This study demonstrates the therapeutic effects of MXSG on pneumonia and explores its potential mechanism, thus providing data support for the use of traditional Chinese medicine in the treatment of respiratory infectious diseases.
ABSTRACT
Effectively compressing transmitted images and reducing the distortion of reconstructed images are challenges in image semantic communication. This paper proposes a novel image semantic communication model that integrates a dynamic decision generation network and a generative adversarial network to address these challenges as efficiently as possible. At the transmitter, features are extracted and selected based on the channel's signal-to-noise ratio (SNR) using semantic encoding and a dynamic decision generation network. This semantic approach can effectively compress transmitted images, thereby reducing communication traffic. At the receiver, the generator/decoder collaborates with the discriminator network, enhancing image reconstruction quality through adversarial and perceptual losses. The experimental results on the CIFAR-10 dataset demonstrate that our scheme achieves a peak SNR of 26 dB, a structural similarity of 0.9, and a compression ratio (CR) of 81.5% in an AWGN channel with an SNR of 3 dB. Similarly, in the Rayleigh fading channel, the peak SNR is 23 dB, structural similarity is 0.8, and the CR is 80.5%. The learned perceptual image patch similarity in both channels is below 0.008. These experiments thoroughly demonstrate that the proposed semantic communication is a superior deep learning-based joint source-channel coding method, offering a high CR and low distortion of reconstructed images.
ABSTRACT
Circular Synthetic Aperture Radar(CSAR) imaging is vulnerable to perturbations in the atmosphere and various other elements that can lead to position offset errors in the antenna's phase center as well as induce motion errors. Traditional phase compensation methods that operate in the time domain, such as Auto-regressive Back-projection (ARBP), typically require computation on a direction-by-direction basis, which can result in the considerable expenditure of time and memory resources. To address these challenges, thispaperintroduces a novel approach for focusing on CSAR images. This method leverages the training of a Generative Adversarial Network (GAN) to directly achieve focus on CSAR sub-aperture images. Additionally, to counteract the network's tendency towards low-frequency preferences, the Auto-focus Frequency Loss (AFFL) is introduced. Moreover, to enhance the accuracy of focus position extraction, the Focus Position Feature Attention (FPFA) is proposed. These innovations, along with a new fusion strategy for the sub-aperture images post-focusing, have been experimentally validated, demonstrating significant improvements in the efficiency and accuracy of CSAR image focusing.
ABSTRACT
Objective. Auto-segmentation in mouse micro-CT enhances the efficiency and consistency of preclinical experiments but often struggles with low-native-contrast and morphologically complex organs, such as the spleen, resulting in poor segmentation performance. While CT contrast agents can improve organ conspicuity, their use complicates experimental protocols and reduces feasibility. We developed a 3D Cycle Generative Adversarial Network (CycleGAN) incorporating anatomy-constrained U-Net models to leverage contrast-enhanced CT (CECT) insights to improve unenhanced native CT (NACT) segmentation.Approach.We employed a standard CycleGAN with an anatomical loss function to synthesize virtual CECT images from unpaired NACT scans at two different resolutions. Prior to training, two U-Nets were trained to automatically segment six major organs in NACT and CECT datasets, respectively. These pretrained 3D U-Nets were integrated during the CycleGAN training, segmenting synthetic images, and comparing them against ground truth annotations. The compound loss within the CycleGAN maintained anatomical fidelity. Full image processing was achieved for low-resolution datasets, while high-resolution datasets employed a patch-based method due to GPU memory constraints. Automated segmentation was applied to original NACT and synthetic CECT scans to evaluate CycleGAN performance using the Dice Similarity Coefficient (DSC) and the 95th percentile Hausdorff Distance (HD95p).Main results.High-resolution scans showed improved auto-segmentation, with an average DSC increase from 0.728 to 0.773 and a reduced HD95p from 1.19 mm to 0.94 mm. Low-resolution scans benefited more from synthetic contrast, showing a DSC increase from 0.586 to 0.682 and an HD95preduction from 3.46 mm to 1.24 mm.Significance.Implementing CycleGAN to synthesize CECT scans substantially improved the visibility of the mouse spleen, leading to more precise auto-segmentation. This approach shows the potential in preclinical imaging studies where contrast agent use is impractical.
Subject(s)
Contrast Media , Imaging, Three-Dimensional , Spleen , X-Ray Microtomography , Animals , Mice , Spleen/diagnostic imaging , X-Ray Microtomography/methods , Imaging, Three-Dimensional/methods , Algorithms , Image Processing, Computer-Assisted/methods , Neural Networks, ComputerABSTRACT
BACKGROUND: Mental disorders have ranked among the top 10 prevalent causes of burden on a global scale. Generative artificial intelligence (GAI) has emerged as a promising and innovative technological advancement that has significant potential in the field of mental health care. Nevertheless, there is a scarcity of research dedicated to examining and understanding the application landscape of GAI within this domain. OBJECTIVE: This review aims to inform the current state of GAI knowledge and identify its key uses in the mental health domain by consolidating relevant literature. METHODS: Records were searched within 8 reputable sources including Web of Science, PubMed, IEEE Xplore, medRxiv, bioRxiv, Google Scholar, CNKI and Wanfang databases between 2013 and 2023. Our focus was on original, empirical research with either English or Chinese publications that use GAI technologies to benefit mental health. For an exhaustive search, we also checked the studies cited by relevant literature. Two reviewers were responsible for the data selection process, and all the extracted data were synthesized and summarized for brief and in-depth analyses depending on the GAI approaches used (traditional retrieval and rule-based techniques vs advanced GAI techniques). RESULTS: In this review of 144 articles, 44 (30.6%) met the inclusion criteria for detailed analysis. Six key uses of advanced GAI emerged: mental disorder detection, counseling support, therapeutic application, clinical training, clinical decision-making support, and goal-driven optimization. Advanced GAI systems have been mainly focused on therapeutic applications (n=19, 43%) and counseling support (n=13, 30%), with clinical training being the least common. Most studies (n=28, 64%) focused broadly on mental health, while specific conditions such as anxiety (n=1, 2%), bipolar disorder (n=2, 5%), eating disorders (n=1, 2%), posttraumatic stress disorder (n=2, 5%), and schizophrenia (n=1, 2%) received limited attention. Despite prevalent use, the efficacy of ChatGPT in the detection of mental disorders remains insufficient. In addition, 100 articles on traditional GAI approaches were found, indicating diverse areas where advanced GAI could enhance mental health care. CONCLUSIONS: This study provides a comprehensive overview of the use of GAI in mental health care, which serves as a valuable guide for future research, practical applications, and policy development in this domain. While GAI demonstrates promise in augmenting mental health care services, its inherent limitations emphasize its role as a supplementary tool rather than a replacement for trained mental health providers. A conscientious and ethical integration of GAI techniques is necessary, ensuring a balanced approach that maximizes benefits while mitigating potential challenges in mental health care practices.
ABSTRACT
Background In the face of the escalating COVID-19 pandemic amid shortages of medications and vaccines, a Vietnamese herbal formula known as Shen Cao Gan Jiang Tang (SCGJT) has been put into use for non-severe COVID-19 patients. This study aims to assess its efficacy and safety. Methods A multicenter, open-label, randomized controlled trial was conducted on 300 patients with non-severe COVID-19, randomly assigned into two groups: 150 receiving standard care (control group) and 150 receiving additional SCGJT for 10 days (SCGJT group). Time to resolution of symptoms, symptom severity, disease progression, time to discharge, the National Early Warning Score 2 (NEWS2) score, usage of Western drugs, time to viral clearance, and safety outcomes were continuously monitored. Results The SCGJT group exhibited faster symptom resolution (median: 9 vs. 13 days) and improved symptom severity, including cough, fatigue, hypogeusia, muscle aches, nasal congestion, runny nose, and sore throat, compared to the control group. Although there was a lower rate of severe progression in the SCGJT group (0.7% vs. 4.7%), the difference was not statistically significant. The time to discharge was significantly shorter in the SCGJT group (median: 7 vs. 8 days). Changes in the NEWS2 score did not show significant differences between groups. SCGJT has been demonstrated to reduce the need for symptomatic relief medications and hasten SARS-CoV-2 viral clearance. No adverse events were reported, and routine tests showed no significant differences. Conclusions SCGJT is safe and has potential clinical efficacy in non-severe COVID-19 patients. However, data regarding preventing severe progression remains inconclusive. Further studies should be conducted in light of the current state of the COVID-19 pandemic.
ABSTRACT
Introduction: Deep learning (DL) models predicting biomarker expression in images of hematoxylin and eosin (H&E)-stained tissues can improve access to multi-marker immunophenotyping, crucial for therapeutic monitoring, biomarker discovery, and personalized treatment development. Conventionally, these models are trained on ground truth cell labels derived from IHC-stained tissue sections adjacent to H&E-stained ones, which might be less accurate than labels from the same section. Although many such DL models have been developed, the impact of ground truth cell label derivation methods on their performance has not been studied. Methodology: In this study, we assess the impact of cell label derivation on H&E model performance, with CD3+ T-cells in lung cancer tissues as a proof-of-concept. We compare two Pix2Pix generative adversarial network (P2P-GAN)-based virtual staining models: one trained with cell labels obtained from the same tissue section as the H&E-stained section (the 'same-section' model) and one trained on cell labels from an adjacent tissue section (the 'serial-section' model). Results: We show that the same-section model exhibited significantly improved prediction performance compared to the 'serial-section' model. Furthermore, the same-section model outperformed the serial-section model in stratifying lung cancer patients within a public lung cancer cohort based on survival outcomes, demonstrating its potential clinical utility. Discussion: Collectively, our findings suggest that employing ground truth cell labels obtained through the same-section approach boosts immunophenotyping DL solutions.
Subject(s)
Deep Learning , Immunophenotyping , Lung Neoplasms , Staining and Labeling , Humans , Lung Neoplasms/immunology , Lung Neoplasms/pathology , Staining and Labeling/methods , Biomarkers, Tumor/metabolism , Male , T-Lymphocytes/immunology , FemaleABSTRACT
Introduction: Studying the spatiotemporal patterns of amyloid accumulation in the brain over time is crucial in understanding Alzheimer's disease (AD). Positron Emission Tomography (PET) imaging plays a pivotal role because it allows for the visualization and quantification of abnormal amyloid beta (Aß) load in the living brain, providing a powerful tool for tracking disease progression and evaluating the efficacy of anti-amyloid therapies. Generative artificial intelligence (AI) can learn complex data distributions and generate realistic synthetic images. In this study, we demonstrate for the first time the potential of Generative Adversarial Networks (GANs) to build a low-dimensional representation space that effectively describes brain amyloid load and its dynamics. Methods: Using a cohort of 1,259 subjects with AV45 PET images from the Alzheimer's Disease Neuroimaging Initiative (ADNI), we develop a 3D GAN model to project images into a latent representation space and generate back synthetic images. Then, we build a progression model on the representation space based on non-parametric ordinary differential equations to study brain amyloid evolution. Results: We found that global SUVR can be accurately predicted with a linear regression model only from the latent representation space (RMSE = 0.08 ± 0.01). We generated synthetic PET trajectories and illustrated predicted Aß change in four years compared with actual progression. Discussion: Generative AI can generate rich representations for statistical prediction and progression modeling and simulate evolution in synthetic patients, providing an invaluable tool for understanding AD, assisting in diagnosis, and designing clinical trials. The aim of this study was to illustrate the huge potential that generative AI has in brain amyloid imaging and to encourage its advancement by providing use cases and ideas for future research tracks.
ABSTRACT
BACKGROUND: Modeling heterogeneous disease states by data-driven methods has great potential to advance biomedical research. However, a comprehensive analysis of phenotypic heterogeneity is often challenged by the complex nature of biomedical datasets and emerging imaging methodologies. METHODS: Here, we propose a novel GAN Inversion-enabled Latent Eigenvalue Analysis (GILEA) framework and apply it to in silico phenome profiling and editing. RESULTS: We show the performance of GILEA using cellular imaging datasets stained with the multiplexed fluorescence Cell Painting protocol. The quantitative results of GILEA can be biologically supported by editing of the latent representations and simulation of dynamic phenotype transitions between physiological and pathological states. CONCLUSION: In conclusion, GILEA represents a new and broadly applicable approach to the quantitative and interpretable analysis of biomedical image data. The GILEA code and video demos are available at https://github.com/CTPLab/GILEA.