Primary Features Research Articles

Enclaves as mushy magma strain archives: New perspectives on composite magmatic fabrics in plutons

Mineral fabrics within igneous intrusions can archive both tectonic and magmatic processes. However, whether magmatic state fabrics reflect primary magmatic processes or regional tectonic strain is often ambiguous. To investigate when fabrics are formed, one can compare the mineral fabrics to primary magmatic features, such as the interface between solidified magmas in mingling zones. The monzodioritic Fanad pluton shows a NNE-SSW–aligned petrofabric parallel to the strike of a nearby shear zone, with dioritic enclaves aligned parallel and oblique to this petrofabric. We therefore aimed to test if the enclaves’ internal fabrics are passive and align with enclave morphology or result from progressive overprint by regional tectonic strain. Crystallographic preferred orientation and anisotropy of magnetic susceptibility data from all enclaves and the host monzodiorite revealed a NNE-SSW petrofabric parallel to the regional tectonomagmatic fabric. However, anisotropy of anhysteretic remanent magnetization data within petrofabric-oblique enclaves revealed a primary fabric parallel to the enclave long axis. Therefore, we interpret enclave morphologies to reflect earlier magmatic state deformation, with fabrics being realigned to regional tectonic deformation. These two distinct petrofabrics were interpreted in the context of the magmatic processes and the evolving late Caledonian paleostress field, with earlier magma processes distinguished from subsequent tectonic overprinting occurring in the magmatic state. Our new data show that multiple fabrics are preserved within enclaves even though all fabric development occurred within a magmatic state. Our results also show that enclaves can effectively record successive strain events, providing new insight with which to decipher tectonomagmatic processes.

EEG Findings in a Patient with Holmes Tremor after AVM Surgery: A Case Report and Literature Review.

Background: Holmes tremor (HT) is a rare motor disorder characterized by high-amplitude and low-frequency resting, intentional, and postural tremors. HT typically arises from disruptions in neural pathways, including the dopaminergic system. Its causes include cerebrovascular incidents, neoplasms, demyelination, and infections. Diagnosis involves thorough clinical, neurophysiological, and neuroimaging assessments. Our report details the clinical profile, neuroimaging and EEG results and levodopa treatment response of an HT patient after cerebral arteriovenous malformation (AVM) surgery. Case Report: A female patient who underwent AVM surgery developed head tremor and dystonia. Neuroimaging revealed left thalamus involvement. Video electroencephalography (EEG) revealed high-amplitude, low-frequency tremors. The patient responded well to levodopa treatment. Conclusions: Involuntary rhythmic or non-rhythmic movements are a primary clinical feature of HT. A differential diagnosis of epilepsy and HT can be achieved through neurophysiological monitoring, avoiding the overuse of antiepileptic drugs. Symptoms can be alleviated with levodopa intervention.

Atomistic insight into laser shock peening response of α-titanium: an experimentally verified simulation study

Laser shock peening (LSP) can induce severe plastic deformation in the surface zone of metallic materials, which potentially enhances their mechanical properties. Although it is widely recognized that the improvement of mechanical properties can be attributed to microstructure evolution, the microstructural characteristics and response under different LSP parameters are complex, leading to distinct mechanical behaviors of materials at the macroscale. Besides, the exceedingly brief duration of LSP also poses considerable challenges to capture the microstructure evolution within the surface layer of materials. Therefore, to grasp a first in-situ atomistic insight into LSP response of α-titanium, molecular dynamics method is applied to simulate laser incidence at the [101¯0] crystallographic orientation with various energy densities. The results show that the lattice reorientation and dislocation slip dominate the plastic deformation at low laser energy density, while stacking faults and crystal disordering are the primary microstructural features at high laser energy density. The above shock-induced microstructures are verified by transmission electron microscopy (TEM) observations. Further, varied microscale plastic deformation modes under varying shock energies are proposed based on Schmid factors and energy barriers. The findings bridge laser energy to post-processing microstructure of α-titanium, which paves the way for improving mechanical properties of materials by optimizing LSP treatment parameters.

Synthesis and biomedical potential of silk fiber/methylcellulose composite containing copper and zinc co-substituted hydroxyapatite for bone tissue engineering applications

The primary feature of biomaterials is to aid in the regeneration of damaged tissues and organs. To attain a biomaterial, we fabricated a double mineral (copper and zinc) substituted hydroxyapatite/silk fiber/methylcellulose (CZ-HAP/SF/MC) nanocomposite by the E-Spin method. The as-developed CZ-HAP/SF/MC nanocomposite was characterized by Fourier transform infrared spectroscopy (FT-IR), X-ray diffraction (XRD) and moreover, the fabricated nanocomposites were used to investigate morphological changes, porosity, swelling test, mechanical strength, antibacterial activity and apatite growth. In addition, antimicrobial studies demonstrated that CZ-HAP/SF/MC nanocomposite exhibited excellent antimicrobial activity against S. aureus, E. coli and C. albicans and, the resultant nanocomposite revealed that the CZ-HAP/SF/MC nanocomposite will be an effective implant material for better cell growth in BTE applications.

Establish an Effective Framework for Accurate Prediction of Employee Mental Health for Public Health

Employee mental health is a primary feature of workplace efficiency and overall public health. With rising mental health problems impaired by variables contains stress, burnout, and isolation, there is an urgent need for effective prediction models that can identify at-risk employees. This study proposes a robust predictive model utilizing dynamic lion optimized VGG16 (DLO-VGG16), for employee mental health prediction represents a significant advancement in public healthcare. The use of these sophisticated prediction models can improve medical results for groups at risk and is essential in the battle against heart disease. Employee’s mental health data collected from Kaggle website. The data preprocessing phase employed Z-score normalization to standardize input values, thereby addressing data inconsistencies and errors. The Sequential Forward Floating Search Algorithm (SFFS) was utilized for extracting the employee’s mental health. This enhanced heuristic search method begins with an empty feature set, incrementally adding features until the optimal set is identified. The proposed DLO-VGG16 framework to balance accuracy, ROC curve, and f1-score ensuring reliable detection and forecasting of employee mental health issues, thereby contributing to the broader public health landscape.

Trends in total shoulder arthroplasty utilization and implant pricing

BackgroundTotal shoulder arthroplasty (TSA) is the third most common total joint replacement procedure in the United States, with high rates of success and cost-effectiveness. As indications continue to expand, anatomic TSA (aTSA), reverse shoulder arthroplasty (RSA), and hemiarthroplasty are available procedures for treating patients with varying end-stage shoulder pathologies. While previous studies have documented trends in overall costs and reimbursements in TSA, there is limited information regarding recent trends in implant utilization, pricing, and procedure type. Therefore, this study aimed to analyze trends in implant and technology utilization for TSA in the United States between 2013 and 2022 to inform decision-making and improve clinical best practices. MethodsUtilization trends and average implant prices between 2013 and 2022 were extracted from Orthopedic Network News, the largest publicly available implant registry. All costs and prices were adjusted for inflation. Trends were analyzed using linear regressions. ResultsAverages and nationwide estimates for 2022 were based off 7339 shoulder cases from 117 US hospitals. RSA significantly increased from 40% in 2013 to 72% of all shoulder arthroplasties in 2022 (β = 4.18; P < .001), whereas aTSA significantly decreased from 43% to 20% (β = −0.34; P < .001), and hemiarthroplasty significantly decreased from 10% to 1% (β = −1.07; P < .001). Other types of procedures, such as revisions and shoulder resurfacings, constituted 7%. Anatomic constructs showed a rise in stemless humeral component usage from 2% in 2017 to 10% in 2022 (β = 1.4; P < .01). Financially, Medicare physician payment for shoulder surgeries witnessed significant decline from $1882 USD in 2017 to $1428 in 2023 (β = −73; P < .001). The inflation-adjusted cost of aTSA also decreased from $8055 in 2013 to $6223 in 2022 (β = −173.56; P < .01), and RSA from $12,207 to $8882 in 2022 (β = −318.31; P < .001). ConclusionTrends in primary TSA procedures feature a growing prevalence of RSA as compared to aTSA, in addition to a rise in stemless humeral implants within aTSA. As both Medicare physician reimbursements and implant prices continue to decrease, it is important for surgeons to consider the tradeoffs of different implant materials and patient-specific technology when performing such procedures.

Astragaloside IV suppresses the proliferation and inflammatory response of human epidermal keratinocytes and ameliorates imiquimod-induced psoriasis-like skin damage in mice.

The primary pathological features of psoriasis include excessive epidermal keratinocytes and infiltration of inflammatory cells, which are pivotal targets for psoriasis therapy. Astragaloside IV (AS-IV), the principal active compound of astragalus, exhibits anti-inflammatory, antioxidant, and immune-modulatory properties. This study aims to investigate AS-IV's anti--psoriatic effects and underlying mechanisms. Normal human epidermal keratinocytes (NHEKs) were stimulated with a combination of TNF-α, IL-17A, IL-1α, IL-22, and oncostatin M (M5) to replicate psoriatic keratinocyte pathology in vitro. Cell proliferation was assessed using CCK8 and EDU staining. Pro-inflammatory cytokine levels were measured via qRT-PCR. In addition, an imiquimod (IMQ)-induced psoriasis mouse model was utilized. Skin histology changes were evaluated with HE staining, while IL-6 and TNF-α levels in mouse serum were quantified using ELISA. NF-κB pathway protein expression was analyzed by western blotting. The results demonstrated that AS-IV inhibited M5-induced proliferation of NHEKs. AS-IV reduced M5-stimulated IL-1β, IL-6, IL-8, TNF-α, IL-23, and MCP-1 expression in NHEKs. Moreover, M5-induced phosphorylation of IκBα and p65 was significantly attenuated by AS-IV. Furthermore, AS-IV application ameliorated erythema, scale formation, and epidermal thickening in IMQ-induced psoriasis-like mouse models. AS-IV also decreased IL-6 and TNF-α levels in mouse serum and inhibited IκBα and p65 phosphorylation in skin tissues. However, prostratin treatment reversed these effects. These findings underscore AS-IV's capacity to mitigate M5-induced NHEK proliferation and inflammation. AS-IV shows promise in alleviating IMQ-induced psoriasis-like skin lesions and inflammation by suppressing the NF-κB pathway.

Novel homozygous missense variants in MED27 associated with neurodevelopmental disorder: Clinical and pathogenetic research

BackgroundNeurodevelopmental disorder with spasticity, cataracts, and cerebellar hypoplasia (NEDSCAC), induced by MED27 gene, is an autosomal recessive rare disorder characterized by widespread developmental delay with varying degrees of intellectual impairment. Other symptoms include limb spasticity, cataracts, and cerebellar hypoplasia. So far there have been limited reports on NEDSCAC. MethodsIn this study, we conducted genetic testing on a child presenting with developmental delay as the primary clinical feature. The genetic test results indicated the presence of novel homozygous missense variants c.74G > A, p.(Arg25His) in the MED27 gene. In vitro functional validation experiments, including plasmid construction and cell transfection, Western blotting, and molecular dynamics structural modeling, were performed on the MED27 Arg25His variant. ResultsThe results demonstrated a significant reduction in protein expression of MED27 Arg25His and indicated may weaken the interaction force between the MED27 subunit and MED14 subunit. ConclusionsThis study expands our understanding of MED27 gene variants and their associated clinical phenotypes. Additionally, it contributes to the investigation of the potential pathogenesis of NEDSCAC caused by MED27 gene variants.

HIRI-ViT: Scaling Vision Transformer With High Resolution Inputs.

The hybrid deep models of Vision Transformer (ViT) and Convolution Neural Network (CNN) have emerged as a powerful class of backbones for vision tasks. Scaling up the input resolution of such hybrid backbones naturally strengthes model capacity, but inevitably suffers from heavy computational cost that scales quadratically. Instead, we present a new hybrid backbone with HIgh-Resolution Inputs (namely HIRI-ViT), that upgrades prevalent four-stage ViT to five-stage ViT tailored for high-resolution inputs. HIRI-ViT is built upon the seminal idea of decomposing the typical CNN operations into two parallel CNN branches in a cost-efficient manner. One high-resolution branch directly takes primary high-resolution features as inputs, but uses less convolution operations. The other low-resolution branch first performs down-sampling and then utilizes more convolution operations over such low-resolution features. Experiments on both recognition task (ImageNet-1K dataset) and dense prediction tasks (COCO and ADE20 K datasets) demonstrate the superiority of HIRI-ViT. More remarkably, under comparable computational cost ( ∼5.0 GFLOPs), HIRI-ViT achieves to-date the best published Top-1 accuracy of 84.3% on ImageNet with 448×448 inputs, which absolutely improves 83.4% of iFormer-S by 0.9% with 224×224 inputs.

Drone-Based Visible–Thermal Object Detection with Transformers and Prompt Tuning

The use of unmanned aerial vehicles (UAVs) for visible–thermal object detection has emerged as a powerful technique to improve accuracy and resilience in challenging contexts, including dim lighting and severe weather conditions. However, most existing research relies on Convolutional Neural Network (CNN) frameworks, limiting the application of the Transformer’s attention mechanism to mere fusion modules and neglecting its potential for comprehensive global feature modeling. In response to this limitation, this study introduces an innovative dual-modal object detection framework called Visual Prompt multi-modal Detection (VIP-Det) that harnesses the Transformer architecture as the primary feature extractor and integrates vision prompts for refined feature fusion. Our approach begins with the training of a single-modal baseline model to solidify robust model representations, which is then refined through fine-tuning that incorporates additional modal data and prompts. Tests on the DroneVehicle dataset show that our algorithm achieves remarkable accuracy, outperforming comparable Transformer-based methods. These findings indicate that our proposed methodology marks a significant advancement in the realm of UAV-based object detection, holding significant promise for enhancing autonomous surveillance and monitoring capabilities in varied and challenging environments.

Human efferent ductules and epididymis display unique cell lineages with motile and primary cilia.

Previous research has illustrated the role of cilia as mechanical and sensory antennae in various organs within the mammalian male reproductive system across different developmental stages. Despite their significance in both organ development and homeostasis, primary cilia in the human male reproductive excurrent duct have been overlooked due to limited access to human specimens. This study aimed to characterize the unique cellular composition of human efferent and epididymal ducts, with a focus on their association with primary cilia. Human efferent ductules/epididymides from five donors aged 32-47 years, were obtained through our local organ transplant program. Cell lineage specificity and primary cilia features were examined by immunofluorescent staining and confocal microscopy in the efferent ductules and the distinct segments of the epididymis. The epithelium of the human efferent duct exhibited estrogen receptor-positive cells with primary cilia, FoxJ1-positive multiciliated cells with numerous motile cilia, and non-ciliated intraepithelial immune cells. Notably, intraluminal macrophages, identified by CD163/CD68 positivity, were observed to engage in sperm phagocytosis. In all three segments of the human epididymis, primary cilia were found on the surface of principal and basal cells. Our research indicates that the human efferent ductules create a distinct environment, characterized by the presence of two types of ciliated cells that are in contact with immune cells. The discovery of sensory primary cilia exposed on the surface of reabsorptive cells in the efferent ductules, as well as on basal and principal cells in the epididymis, lays the foundation for complementary functional studies. This research uncovers novel characteristics exclusive to human efferent ductules and epididymides, providing a basis for exploring innovative approaches to male contraception and infertility treatment.

Telomere biology disorders: from dyskeratosis congenita and beyond.

Defective telomerase function or telomere maintenance causes genomic instability. Alterations in telomere length and/or attrition are the primary features of rare diseases known as telomere biology disorders or telomeropathies. Recent advances in the molecular basis of these disorders and cutting-edge methods assessing telomere length have increased our understanding of this topic. Multiorgan manifestations and different phenotypes have been reported even in carriers within the same family. In this context, apart from dyskeratosis congenita, disorders formerly considered idiopathic (i.e. pulmonary fibrosis, liver cirrhosis) frequently correlate with underlying defective telomere maintenance mechanisms. Moreover, these patients are prone to developing specific cancer types and exhibit exceptional sensitivity and toxicity in standard chemotherapy regimens. The current review describes the diverse spectrum of clinical manifestations of telomere biology disorders in pediatric and adult patients, their correlation with pathogenic variants, and considerations during their management to increase awareness and improve a multidisciplinary approach.

Inflammatory aspects of Alzheimer's disease.

Alzheimer´s disease (AD) stands out as the most common chronic neurodegenerative disorder. AD is characterized by progressive cognitive decline and memory loss, with neurodegeneration as its primary pathological feature. The role of neuroinflammation in the disease course has become a focus of intense research. While microglia, the brain's resident macrophages, have been pivotal to study central immune inflammation, recent evidence underscores the contributions of other cellular entities to the neuroinflammatory process. In this article, we review the inflammatory role of microglia and astrocytes, focusing on their interactions with AD's core pathologies, amyloid beta deposition, and tau tangle formation. Additionally, we also discuss how different modes of regulated cell death in AD may impact the chronic neuroinflammatory environment. This review aims to highlight the evolving landscape of neuroinflammatory research in AD and underscores the importance of considering multiple cellular contributors when developing new therapeutic strategies.

Age-Associated Contraction of Tumor-Specific T Cells Impairs Antitumor Immunity.

Progressive decline of the adaptive immune system with increasing age coincides with a sharp increase in cancer incidence. In this study, we set out to understand whether deficits in antitumor immunity with advanced age promote tumor progression and/or drive resistance to immunotherapy. We found that multiple syngeneic cancers grew more rapidly in aged versus young adult mice, driven by dysfunctional CD8+ T-cell responses. By systematically mapping immune cell profiles within tumors, we identified loss of tumor antigen-specific CD8+ T cells as a primary feature accelerating the growth of tumors in aged mice and driving resistance to immunotherapy. When antigen-specific T cells from young adult mice were administered to aged mice, tumor outgrowth was delayed and the aged animals became sensitive to PD-1 blockade. These studies reveal how age-associated CD8+ T-cell dysfunction may license tumorigenesis in elderly patients and have important implications for the use of aged mice as preclinical models of aging and cancer.

Renal Fibrosis: SIRT1 Still of Value.

Chronic kidney disease (CKD) is a major global health concern. Renal fibrosis, a prevalent outcome regardless of the initial cause, ultimately leads to end-stage renal disease. Glomerulosclerosis and renal interstitial fibrosis are the primary pathological features. Preventing and slowing renal fibrosis are considered effective strategies for delaying CKD progression. However, effective treatments are lacking. Sirtuin 1 (SIRT1), a nicotinamide adenine dinucleotide (NAD+)-dependent deacetylase belonging to class III histone deacetylases, is implicated in the physiological regulation and protection of the kidney and is susceptible to a diverse array of pathological influences, as demonstrated in previous studies. Interestingly, controversial conclusions have emerged as research has progressed. This review provides a comprehensive summary of the current understanding and advancements in the field; specifically, the biological roles and mechanisms of SIRT1 in regulating renal fibrosis progression. These include aspects such as lipid metabolism, epithelial-mesenchymal transition, oxidative stress, aging, inflammation, and autophagy. This manuscript explores the potential of SIRT1 as a therapeutic target for renal fibrosis and offers new perspectives on treatment approaches and prognostic assessments.

Desert oasis vegetation information extraction by PLANET and unmanned aerial vehicle image fusion

Sparse vegetation is a key factor in maintaining the health and sustainability of oasis ecosystems under extreme drought conditions. Combining the advantages of both satellites and drones, using image processing and machine learning technology, it can efficiently and accurately extract information on the vegetation of desert oases, providing a scientific basis for ecological monitoring and management. Therefore, in this study, the Dariyabui natural oasis in the hinterland of the Taklamakan Desert, China, was used as the study area to fuse PLANET and UAV images to screen 19 feature factors from different data sources. The machine learning binary classification model was evaluated based on the overall accuracy (OA, %), kappa, balanced accuracy (BA, %), F1_score (F1, %), and Area Under Curve (AUC) values. The results were validated using aerial imaging data from different months. The results show that (1) the primary feature factors for extracting sparse ground vegetation information in a desert oasis include the soil-adjusted vegetation index (SAVI); modified soil-adjusted vegetation index (MSAVI); optimized soil-adjusted vegetation index (OSAVI); and the mean, entropy, contrast, homogeneity, and digital surface models (DSM). (2) The evaluation indices of the fused images in the vegetation information extraction were better than those of the original satellite images; the difference in the extraction effect with the original UAV images was not significant. (3) The random forest (RF) algorithm achieved the best classification accuracy in extracting sparse vegetation information (Kappa = 0.87, OA = 94.12 %, BA = 93.53 %, F1 = 92.13 %, and AUC = 0.967).

Facial Expression Recognition Using a Semantic-Based Bottleneck Attention Module

Facial expression recognition (FER) is of great value in affective computing. Currently, many FER models have difficulty distinguishing between primary and secondary features. To this end, we propose a FER model based on the semantic bottleneck attention module (BAM). The improvement is that the input image is processed through two branches. BAM uses spatial attention to construct feature maps that can highlight important feature areas and suppress secondary features. The moving flipped bottleneck convolution (MBConv) module introduces random depth, reducing training time and improving model performance. Random depth enables the model to reduce the risk of overfitting during training by randomly skipping some layers. Global average pooling replaces the fully connected layer and compresses the entire feature map (FM) into numerical values to obtain high-purity image features. Through experiments on Extended Cohn-Kanade, Static Facial Expressions in the Wild, and Real-world Affective Faces Database CK+, SFEW, and RAFDB databases, the accuracy of our model reaches 98.33%, 61.14%, and 89.43% respectively, which is better than the other three advanced comparison methods.

RDA-Net: A multi-cascade network for DAS background noise attenuation

The increasing attention to seismic data collection under complex geological conditions is attributed to the utilization of distributed acoustic sensing (DAS), which has gained significant prominence due to the rapid development of exploration techniques. However, the presence of background noise in DAS has adverse effects on the quality of DAS data and significantly affects the accuracy of the subsequent migration and imaging processing. In addition, these interferences have a different generation mechanism from random noise in geophone-acquired seismic data, resulting in the degradation of traditional denoising techniques. Recent advancements have introduced convolutional neural networks (CNNs) for DAS background noise attenuation, showcasing their superiority over conventional techniques in terms of denoising capability and processing accuracy. Unfortunately, most CNN-based methods only have a single-scale architecture and cannot precisely accomplish denoising tasks when confronted with weak reflection signals in DAS records. In this research, we introduce a residual dense-connection attention network called RDA-Net to further augment the denoising ability. More precisely, the multi-scale structure in the backbone of RDA-Net is employed to capture informative features from the DAS data. Simultaneously, we employ a self-enhanced spatial attention module to refine and strengthen the primary features, thereby positively impacting feature representation and denoising performance. Furthermore, dense connections are also leveraged to reinforce the feature-interaction capability and effective features. Compared with typical conventional methods and CNN-based frameworks, RDA-Net can improve the signal-to-noise ratio over 24 dB and show superiority in weak signal recovery and intense DAS noise attenuation, both for synthetic and field records.

Childhood maltreatment and its associations with trauma-related psychopathology: disentangling two classification approaches

Childhood maltreatment (CM) is associated with various mental health disorders, including PTSD, depression, and anxiety. This study explores how specific classifications – dichotomous (abuse versus neglect) and dimensional (physical, emotional, sexual) – relate to distinct psychopathologies. We recruited 642 individuals, screening them for CM history and symptoms. ANOVA, regression, and SEM analyses compared CM approaches and symptom associations. The dichotomous approach showed significant effects of abuse and neglect on all symptoms. In the dimensional approach, sexual and physical CM were primary features for PTSD, while sexual and emotional CM were primary for depression and anxiety. Overall, the dimensional approach outperformed the dichotomous approach in capturing symptoms, suggesting its importance in understanding psychopathologies and guiding therapeutic interventions. Our findings highlight the differential associations of CM experiences with PTSD, depression, and anxiety symptoms. The findings suggest the importance of a dimensional CM approach for understanding psychopathologies and possibly informing targeted therapeutic interventions.

Automated quantification of SARS-CoV-2 pneumonia with large vision model knowledge adaptation

BackgroundLarge vision models (LVM) pretrained by large datasets have demonstrated their enormous capacity to understand visual patterns and capture semantic information from images. We proposed a novel method of knowledge domain adaptation with pretrained LVM for a low-cost artificial intelligence (AI) model to quantify the severity of SARS-CoV-2 pneumonia based on frontal chest X-ray (CXR) images. MethodsOur method used the pretrained LVMs as the primary feature extractor and self-supervised contrastive learning for domain adaptation. An encoder with a 2048-dimensional feature vector output was first trained by self-supervised learning for knowledge domain adaptation. Then a multi-layer perceptron (MLP) was trained for the final severity prediction. A dataset with 2599 CXR images was used for model training and evaluation. ResultsThe model based on the pretrained vision transformer (ViT) and self-supervised learning achieved the best performance in cross validation, with mean squared error (MSE) of 23.83 (95 % CI 22.67–25.00) and mean absolute error (MAE) of 3.64 (95 % CI 3.54–3.73). Its prediction correlation has the R2 of 0.81 (95 % CI 0.79–0.82) and Spearman ρ of 0.80 (95 % CI 0.77–0.81), which are comparable to the current state-of-the-art (SOTA) methods trained by much larger CXR datasets. ConclusionThe proposed new method has achieved the SOTA performance to quantify the severity of SARS-CoV-2 pneumonia at a significantly lower cost. The method can be extended to other infectious disease detection or quantification to expedite the application of AI in medical research.