Exposure to polycyclic aromatic hydrocarbons promotes the progression of low-grade cervical intraepithelial neoplasia: A population-based cohort study in China.

Low-grade cervical intraepithelial neoplasia (CIN1) is an early stage of cervical cancer development. Previously, we reported that exposure to polycyclic aromatic hydrocarbons (PAHs) increases the risk of cervical precancerous lesions, especially in females with a high-risk human papillomavirus (HR-HPV) infection. However, the effects of PAHs on CIN1 progression remain unclear. A community-based prospective cohort study was conducted to evaluate the role of exposure to PAHs in the progression of CIN1. A total of 564 patients diagnosed with CIN1 were followed-up at 6, 12, and 24 months, post-diagnosis, to determine CIN1 reversion, persistence, and progression. Exposure to PAHs was determined by the urine 1-hydroxipayrene (1-OHP) level. Our results showed that the 1-OHP level was significantly higher in patients with CIN1 persistence/progression than in those with reversion (P < .05). High exposure to PAHs increased the risk of CIN1 persistence/progression, with hazard ratios (HR), 95% confidence intervals (CI) of (1.62, 1.24-2.67), (1.98, 1.42-2.75), and (2.37, 1.61-3.49) at 6, 12, and 24 months, post-diagnosis, respectively. The effect was enhanced with HR-HPV positivity, as determined at 6 (1.82, 1.24-2.67), 12 (3.02, 1.74-5.23), and 24 (2.51, 1.48-4.26) months, post-diagnosis. Moreover, the predictive value of exposure to PAHs for CIN1 persistence/progression was higher in HR-HPV-positive patients than in HR-HPV-negative patients. The results revealed that exposure to PAHs facilitated the malignant progression of CIN1 and hindered its reversal, particularly in patients with HR-HPV infection. Our findings provide novel insights into early prevention and intervention targeting the initiation and progression of cervical neoplasia.

SaraNet: Semantic aggregation reverse attention network for pulmonary nodule segmentation.

Accurate segmentation of pulmonary nodule is essential for subsequent pathological analysis and diagnosis. However, current U-Net architectures often rely on a simple skip connection scheme, leading to the fusion of feature maps with different semantic information, which can have a negative impact on the segmentation model. In response to this challenge, this study introduces a novel U-shaped model specifically designed for pulmonary nodule segmentation. The proposed model incorporates features such as the U-Net backbone, semantic aggregation feature pyramid module, and reverse attention module. The semantic aggregation module combines semantic information with multi-scale features, addressing the semantic gap between the encoder and decoder. The reverse attention module explores missing object parts and captures intricate details by erasing the currently predicted salient regions from side-output features. The proposed model is evaluated using the LIDC-IDRI dataset. Experimental results reveal that the proposed method achieves a dice similarity coefficient of 89.11%and a sensitivity of 90.73 %, outperforming state-of-the-art approaches comprehensively.

Vaginal micro-environment disorder promotes malignant prognosis of low-grade cervical intraepithelial neoplasia: a prospective community cohort study in Shanxi Province, China.

PURPOSE: Emerging evidence suggests that vaginal micro-environment disorder is closely related to the development of cervical lesions. Low-grade cervical intraepithelial neoplasia (CIN1), as an early stage of cervical lesions, exhibits a high risk of progressing to high-grade lesions or even cervical cancer. However, the effect of vaginal micro-environment on the malignant prognosis of CIN1 remains uncertain. METHODS: A total of 504 patients diagnosed with CIN1 by pathology, who were from the population-based cohorts established in Shanxi Province, China, were enrolled and followed up for 2 years. Micro-environmental factors such as vaginal pH, cleanliness, hydrogen peroxide (H2O2), ß-glucuronidase (GUSB), leucocyte esterase (LE), and sialidase (SNA) were detected to evaluate their effect on the malignant prognosis of CIN1. RESULTS: Abnormal vaginal pH (HR = 1.472, 95%CI 1.071-2.022), cleanliness (HR = 1.446, 95%CI 1.067-1.960), H2O2 (HR = 1.525, 95%CI 1.155-2.013), GUSB (HR = 1.739, 95%CI 1.235-2.448), LE (HR = 1.434, 95%CI 1.038-1.981), and SNA (HR = 1.411, 95%CI 1.065-1.870) could promote a higher incidence of CIN1 malignant prognosis, and the combined effects of these micro-environmental factors resulted in a nearly twofold increased risk (HR = 2.492, 95%CI 1.773-3.504) compared to any single factor alone, especially under the high-risk human papillomavirus (HR-HPV) infection. Notably, the cumulative incidence of malignant prognosis for CIN1 gradually increased during the early follow-up period, reaching its peak at approximately 8 months, and then stabilizing. CONCLUSION: Vaginal micro-environment disorder could promote CIN1 malignant prognosis, particularly in HR-HPV-infected women. Taking micro-environmental factors as the breakthrough, our study provides a feasible vision for preventing early stage cervical lesions.

Progress in Research on White Organic Light-Emitting Diodes Based on Ultrathin Emitting Layers.

White organic light-emitting diodes (WOLEDs) hold vast prospects in the fields of next-generation displays and solid-state lighting. Ultrathin emitting layers (UEMLs) have become a research hotspot because of their unique advantage. On the basis of simplifying the device structure and preparation process, they can achieve electroluminescent performance comparable to that of doped devices. In this review, we first discuss the working principles and advantages of WOLEDs based on UEML architecture, which can achieve low cost and more flexibility by simplifying the device structure and preparation process. Subsequently, the successful applications of doping and non-doping technologies in fluorescent, phosphorescent, and hybrid WOLEDs combined with UEMLs are discussed, and the operation mechanisms of these WOLEDs are emphasized briefly. We firmly believe that this article will bring new hope for the development of UEML-based WOLEDs in the future.

Highly efficient fluorescent and hybrid white organic light-emitting diodes based on a bimolecular excited system: publisher's note.

This publisher's note contains a correction to Opt. Lett.48, 5771 (2023)10.1364/OL.506371.

Design, synthesis, anti-infective potency and mechanism study of novel Ru-based complexes containing substituted adamantane as antibacterial agents.

Infections caused by Staphylococcus aureus (S. aureus) are increasing difficult to treat because this pathogen is easily resistant to antibiotics. However, the development of novel antibacterial agents with high antimicrobial activity and low frequency of resistance remains a huge challenge. Here, building on the coupling strategy, an adamantane moiety was linked to the membrane-active Ru-based structure and then developed three novel metalloantibiotics: [Ru(bpy)2(L)](PF6)2 (Ru1) (bpy = 2,2-bipyridine, L = amantadine modified ligand), [Ru(dmb)2(L)](PF6)2 (Ru2) (dmb = 4,4'-dimethyl-2,2'-bipyridine) and [Ru(dpa)2(L)](PF6)2 (Ru3), (dpa = 2,2'-dipyridylamine). Notably, complex Ru1 was identified to be the best candidate agent, showing greater efficacy against S. aureus than most of clinical antibiotics and low resistance frequencies. Mechanism studies demonstrated that Ru1 could not only increase the permeability of bacterial cell membrane and then caused the leakage of bacterial contents, but also promoted the production of reactive oxygen species (ROS) in bacteria. Importantly, complex Ru1 inhibited the biofilm formation, exotoxin secretion and increased the potency of some clinical used antibiotics. In addition, Ru1 showed low toxic in vivo and excellent anti-infective efficacy in two animal infection model. Thus, Ru-based metalloantibiotic bearing adamantane moiety are promising antibacterial agents, providing a certain research basis for the future antibiotics research.

A Principal Component Regression-Based Electrophysiological Study of Patients with Severe Infections.

Objective: Severe infections can lead to neuromyopathy in critically ill patients, resulting in limb weakness and difficulty in weaning from a ventilator. This study aims to assess the electrophysiological test results in patients with severe infection and their correlation with severity scores (APACHE II and SOFA). Methods: Thirty-one patients with severe infection in the EICU were prospectively studied. Factor analysis and principal component regression were applied to develop linear models of electrophysiological diagnostic outcomes with APACHE II and SOFA scores for the entire patient cohort, the younger group (age<55) cohort, and the older group (age>55) cohort of patients with severe infections, respectively. Results: Among patients with a severe infection in the EICU, the proportion of patients without critical neuromyopathy with more than 50% F-wave presence in the median, ulnar, and tibial nerves (64.9%, 56.8%, 48.6%, respectively) was significantly higher than in the group with critical neuromyopathy (52.1%, 35.4%, 29.2%, respectively.), and the proportion of patients with critical neuromyopathy who did not elicit the three types of F wave was significantly higher in the cohort of patients with critical neuromyopathy (40.5%, 32.4%, 35.1%, respectively.) were significantly higher than in the cohort of patients without critical illness (18.8%, 12.5%, 20.8%, respectively). In addition, on average, patients with critical neuromyopathy had a much lower CMAP for the median nerve (wrist, elbow) (2.4, 1.88, respectively) (4.3, 3.9, respectively in undiagnosed cohort), ulnar nerve (wrist, elbow) (2.4, 1.88, respectively) (5.65, 5.4, respectively in undiagnosed cohort), and tibial nerve(ankle, popliteal fossa) (2.7, 1.57, respectively)(6.55, 5.3, respectively in undiagnosed cohort) nerves than patients without critical neuromyopathy, and showed more non-elicitation, which was not seen in the cohort of patients without critical neuromyopathy. The CMAP returned to normal in the cohort of patients without critical neuromyopathy. Therefore, with respect to our selected electrophysiological parameters, the two patient groups showed significant differences in terms of the specific values and statistical analysis (Table 1). Through factor analysis and principal component regression, we found that CMAP and F-wave were highly correlated with APACHE II and SOFA scores, and the correlation between the electrophysiological wave spectrum and the two scores was further quantified by principal component regression. Conclusion: Electrophysiological spectroscopy can serve as an early warning for the development of neuromuscular disease in EICU patients. Abnormal electrophysiological diagnosis prior to actual neuromuscular abnormalities and its subsequent return to normal can help identify high-risk patients and implement early interventions.

Recent Achievements for Flexible Encapsulation Films Based on Atomic/Molecular Layer Deposition.

The purpose of this paper is to review the research progress in the realization of the organic-inorganic hybrid thin-film packaging of flexible organic electroluminescent devices using the PEALD (plasma-enhanced atomic layer deposition) and MLD (molecular layer deposition) techniques. Firstly, the importance and application prospect of organic electroluminescent devices in the field of flexible electronics are introduced. Subsequently, the principles, characteristics and applications of PEALD and MLD technologies in device packaging are described in detail. Then, the methods and process optimization strategies for the preparation of organic-inorganic hybrid thin-film encapsulation layers using PEALD and MLD technologies are reviewed. Further, the research results on the encapsulation effect, stability and reliability of organic-inorganic hybrid thin-film encapsulation layers in flexible organic electroluminescent devices are discussed. Finally, the current research progress is summarized, and the future research directions and development trends are prospected.

A prospective cohort study of exposure to household pesticide with cardiovascular diseases mortality in older adults.

OBJECTIVES: We examined the associations of self-reported exposures, and urinary metabolites related to household pesticide with cardiovascular disease (CVD) mortality in older adults based on the 2007 to 2014 waves of National Health and Nutrition Examination Survey (NHANES). METHODS: Information on application and urinary metabolites related to household pesticide exposure were collected. We estimated the risks of household pesticide exposure, urinary metabolites with subsequent incident CVD death using Cox proportional hazards regression models. The indirect effects of urinary metabolites and effect modifications were examined. RESULTS: The participants who reported exposure to household pesticide had a higher risk of incident CVD death (adjusted HR 1.40, 95% CI 1.08 to 1.81). Per 1-log10 increase in urinary N, N-diethyl-3-methylbenzamide (DEET) related to household insect repellents was associated with a higher risk of incident CVD death (adjusted HR 1.97, 95% CI 1.14 to 3.40). Urinary DEET explained 4.21% of the total association between household pesticide exposure and CVD death risk. The participants who persisted a low level of health diet exhibited pronounced CVD death risks with household pesticide exposures. CONCLUSIONS: Exposure to household pesticide, especially household insect repellents, was consistently associated with an elevated CVD death risk in older adults. A heatlhy diet could partly attenuate the associations.

Contribution of the transcription factor SfGATAe to Bt Cry toxin resistance in Spodoptera frugiperda through reduction of ABCC2 expression.

Insect resistance evolution poses a significant threat to the advantages of biopesticides and transgenic crops utilizing insecticidal Cry-toxins from Bacillus thuringiensis (Bt). However, there is limited research on the relationship between transcriptional regulation of specific toxin receptors in lepidopteran insects and their resistance to Bt toxins. Here, we report the positive regulatory role of the SfGATAe transcription factor on the expression of the ABCC2 gene in Spodoptera frugiperda. DNA regions in the SfABCC2 promoter that are vital for regulation by SfGATAe, utilizing DAP-seq technology and promoter deletion mapping. Through yeast one-hybrid assays, DNA pull-down experiments, and site-directed mutagenesis, we confirmed that the transcription factor SfGATAe regulates the core control site PBS2 in the ABCC2 target gene. Tissue-specific expression analysis has revealed that SfGATAe is involved in the regulation and expression of midgut cells in the fall armyworm. Silencing SfGATAe in fall armyworm larvae resulted in reduced expression of SfABCC2 and decreased sensitivity to Cry1Ac toxin. Overall, this study elucidated the regulatory mechanism of the transcription factor SfGATAe on the expression of the toxin receptor gene SfABCC2 and this transcriptional control mechanism impacts the resistance of the fall armyworm to Bt toxins.

Toxic effect and mRNA mechanism of moon dust simulant induced pulmonary inflammation in rats.

Moon dust presents a significant hazard to manned moon exploration missions, yet our understanding of its toxicity remains limited. The objective of this study is to investigate the pattern and mechanism of lung inflammation induced by subacute exposure to moon dust simulants (MDS) in rats. SD rats were exposed to MDS and silica dioxide through oral and nasal inhalation for 6 hours per day continuously for 15 days. Pathological analysis indicated that the toxicity of MDS was lower than that of silica dioxide. MDS led to a notable recruitment and infiltration of macrophages in the rat lungs. Material characterization and biochemical analysis revealed that SiO2, Fe2O3, and TiO2 could be crucial sources of MDS toxicity. The study revealed that MDS-induced oxidative stress response can lead to pulmonary inflammation, which potentially may progress to lung fibrosis. Transcriptome sequencing revealed that MDS suppresses the PI3K-AKT signaling pathway, triggers the Tnfr2 non-classical NF-kB pathway and IL-17 signaling pathway, ultimately causing lung inflammation and activating predominantly antioxidant immune responses. Moreover, the study identified the involvement of upregulated genes IL1b, csf2, and Sod2 in regulating immune responses in rat lungs, making them potential key targets for preventing pulmonary toxicity related to moon dust exposure. These findings are expected to aid in safeguarding astronauts against the hazardous effects of moon dust and offer fresh insights into the implications and mechanisms of moon dust toxicity.

A Study of Electroplated Nanoporous Copper Using Aberration-Corrected Transmission Electron Microscopy.

Nanoporous Cu foam is widely applied in many fields such as the packaging of electronic power devices. In this study, a sandwich-structured Cu-Zn eutectic alloy precursor composed of Cu0.53Zn0.47/Cu5Zn8/Cu0.53Zn0.47 is prepared through electroplating. The surface layer of the precursor, Cu0.53Zn0.47, has a flat surface with numerous grain boundaries, which effectively promotes its dealloying behavior. By contrast, Cu5Zn8 has a porous structure, which promotes the dealloying behavior at the center of the precursor. The dealloying of Cu0.53Zn0.47 is dominated by the coherent surface diffusion of Cu atoms, and the crystal lattice and orientation show no changes before and after dealloying. By contrast, the dealloying behavior of Cu5Zn8 requires the renucleation of Cu crystals; in this process, Cu atoms are transported to the surface of the layer by capillary forces to form clusters, which nucleate and grow.

Multifunctional chitosan-based lanthanide luminescent hydrogel with stretchability, adhesion, self-healing, color tunability and antibacterial ability.

Lanthanide luminescent hydrogels have broad application prospects in various fields. However, most of lanthanide hydrogels possess relatively simple functions, which is not conducive to practical applications. Therefore, it is becoming increasingly urgent to develop multifunctional hydrogels. Herein, a multifunctional chitosan-based lanthanide luminescent hydrogel with ultra-stretchability, multi-adhesion, excellent self-healing, emission color tunability, and good antibacterial ability was prepared by a simple one-step free radical polymerization. In this work, our designed lanthanide complexes [Ln(4-VDPA)3] contain three reaction sites, which can be copolymerized with N-[tris(hydroxymethyl) methyl] acrylamide (THMA), acrylamide (AM), and diacryloyl poly(ethylene glycol) (DPEG) to form the first chemical crosslinking network, while hydroxypropyltrimethyl ammonium chloride chitosan (HACC) interacts with the hydroxyl and amino groups derived from the chemical crosslinking network through hydrogen bonds to form the second physical crosslinking network. The structure of the double network as well as the dynamic hydrogen bond and lanthanide coordination endow the hydrogel with excellent stretchability, adhesion and self-healing properties. Moreover, the introduction of lanthanide complexes and chitosan makes the hydrogel exhibit outstanding luminescence and antibacterial performances. This research not only realizes the simple synthesis of multifunctional luminescent hydrogels, but also provides a new idea for the fabrication of biomass-based hydrogels as intelligent and sustainable materials.

Enhancing multi-UAV air combat decision making via hierarchical reinforcement learning.

In the realm of air combat, autonomous decision-making in regard to Unmanned Aerial Vehicle (UAV) has emerged as a critical force. However, prevailing autonomous decision-making algorithms in this domain predominantly rely on rule-based methods, proving challenging to design and implement optimal solutions in complex multi-UAV combat environments. This paper proposes a novel approach to multi-UAV air combat decision-making utilizing hierarchical reinforcement learning. First, a hierarchical decision-making network is designed based on tactical action types to streamline the complexity of the maneuver decision-making space. Second, the high-quality combat experience gained from training is decomposed, with the aim of augmenting the quantity of valuable experiences and alleviating the intricacies of strategy learning. Finally, the performance of the algorithm is validated using the advanced UAV simulation platform JSBSim. Through comparisons with various baseline algorithms, our experiments demonstrate the superior performance of the proposed method in both even and disadvantaged air combat environments.

Profiles of subgingival microbiomes and gingival crevicular metabolic signatures in patients with amnestic mild cognitive impairment and Alzheimer's disease.

BACKGROUND: The relationship between periodontitis and Alzheimer's disease (AD) has attracted more attention recently, whereas profiles of subgingival microbiomes and gingival crevicular fluid (GCF) metabolic signatures in AD patients have rarely been characterized; thus, little evidence exists to support the oral-brain axis hypothesis. Therefore, our study aimed to characterize both the microbial community of subgingival plaque and the metabolomic profiles of GCF in patients with AD and amnestic mild cognitive impairment (aMCI) for the first time. METHODS: This was a cross-sectional study. Clinical examinations were performed on all participants. The microbial community of subgingival plaque and the metabolomic profiles of GCF were characterized using the 16S ribosomal RNA (rRNA) gene high-throughput sequencing and liquid chromatography linked to tandem mass spectrometry (LC-MS/MS) analysis, respectively. RESULTS: Thirty-two patients with AD, 32 patients with aMCI, and 32 cognitively normal people were enrolled. The severity of periodontitis was significantly increased in AD patients compared with aMCI patients and cognitively normal people. The 16S rRNA gene sequencing results showed that the relative abundances of 16 species in subgingival plaque were significantly correlated with cognitive function, and LC-MS/MS analysis identified a total of 165 differentially abundant metabolites in GCF. Moreover, multiomics Data Integration Analysis for Biomarker discovery using Latent cOmponents (DIABLO) analysis revealed that 19 differentially abundant metabolites were significantly correlated with Veillonella parvula, Dialister pneumosintes, Leptotrichia buccalis, Pseudoleptotrichia goodfellowii, and Actinomyces massiliensis, in which galactinol, sn-glycerol 3-phosphoethanolamine, D-mannitol, 1 h-indole-1-pentanoic acid, 3-(1-naphthalenylcarbonyl)- and L-iditol yielded satisfactory accuracy for the predictive diagnosis of AD progression. CONCLUSIONS: This is the first combined subgingival microbiome and GCF metabolome study in patients with AD and aMCI, which revealed that periodontal microbial dysbiosis and metabolic disorders may be involved in the etiology and progression of AD, and the differential abundance of the microbiota and metabolites may be useful as potential markers for AD in the future.

Channel Adaptive and Sparsity Personalized Federated Learning for Privacy Protection in Smart Healthcare Systems.

With the booming development of Smart Healthcare Systems (SHSs), employing federated learning (FL) in SHS devices has become a research hotspot. FL, as a distributed learning framework, can train models without sharing the original data among users, and then protect the user privacy. Existing research has proposed many methods to improve the security and efficiency of FL, which may not fully consider the characteristics of SHSs. Specifically, the requirements of privacy protection and efficiency pose significant challenges to FL. Current studies have struggled to balance privacy security and efficiency, and the degradation of model training efficiency in SHSs can be critical to patient health. Therefore, to improve the privacy protection of healthcare data and ensure communication efficiency, this work proposes a novel personalized FL framework based on Communication quality and Adaptive Sparsification (pFedCAS). In order to achieve privacy protection, a control unit is proposed and introduced to adjust the sparsity of the local model adaptively. To further improve the training efficiency, a selection unit is added during global model aggregation to select suitable clients for parameter updates. Finally, we validate the proposed method operated on the HAM10000 dataset. Simulation results validate that pFedCAS can not only improve privacy protection, but also gain an improvement of 15% in training accuracy and a reduction of 30% in training costs based on communication quality. The simulation results also validate the excellent robustness of pFedCAS to non-iid data.

APPA-3D: an autonomous 3D path planning algorithm for UAVs in unknown complex environments.

Due to their high flexibility, low cost, and ease of handling, Unmanned Aerial Vehicles (UAVs) are often used to perform difficult tasks in complex environments. Stable and reliable path planning capability is the fundamental demand for UAVs to accomplish their flight tasks. Most researches on UAV path planning are carried out under the premise of known environmental information, and it is difficult to safely reach the target position in the face of unknown environment. Thus, an autonomous collision-free path planning algorithm for UAVs in unknown complex environments (APPA-3D) is proposed. An anti-collision control strategy is designed using the UAV collision safety envelope, which relies on the UAV's environmental awareness capability to continuously interact with external environmental information. A dynamic reward function of reinforcement learning combined with the actual flight environment is designed and an optimized reinforcement learning action exploration strategy based on the action selection probability is proposed. Then, an improved RL algorithm is used to simulate the UAV flight process in unknown environment, and the algorithm is trained by interacting with the environment, which finally realizes autonomous collision-free path planning for UAVs. The comparative experimental results in the same environment show that APPA-3D can effectively guide the UAV to plan a safe and collision-free path from the starting point to the target point in an unknown complex 3D environment.

Improving the stability of perovskite nanocrystals via SiO2 coating and their applications.

Lead halide perovskite nanocrystals (LHP NCs) with outstanding optical properties have been regarded as promising alternatives to traditional phosphors for lighting and next-generation display technology. However, the practical applications of LHP NCs are seriously hindered by their poor stability upon exposure to moisture, oxygen, light, and heat. Hence, various strategies have been proposed to solve this issue. In this review, we have focused our attention on improving the stability of LHP NCs via SiO2 coating because it has the advantages of simple operation, less toxicity, and easy repetition. SiO2 coating is classified into four types: (a) in situ hydrolytic coating, (b) mesoporous silica loading, (c) mediated anchoring, and (d) double coating. The potential applications of SiO2-coated LHP NCs in the field of optoelectronics, biology, and catalysis are presented to elucidate the reliability and availability of SiO2 coating. Finally, the future development and challenges in the preparation of SiO2-coated LHP NCs are analyzed in order to promote the commercialization process of LHP NC-related commodities.

Prognostic nomogram for patients with tongue squamous cell carcinoma: A SEER-based study.

OBJECTIVES: In order to predict the patients' prognosis with tongue squamous cell carcinoma (SCC), this study set out to develop a clinically useful and trustworthy prognostic nomogram. SUBJECTS AND METHODS: The Surveillance, Epidemiology, and End Results (SEER) Program was used to compile clinical information on patients with tongue SCC between 2010 and 2015. The likelihood of Cancer-Specific Survival (CSS) and Overall Survival (OS) for specific patients was predicted using a prognostic nomogram created with the help of the RStudio software. The nomogram's predictive ability was evaluated using the consistency index (C-index) and decision curve analysis, and the nomogram was calibrated for 1-, 2-, 3-, 5-, and 10-year CSS and OS. RESULTS: Patients numbering 6453were enrolled in this study. The primary cohort (3895) and validation cohort (2558) were each randomly assigned. Sex, age, tumor-node-metastasis (TNM) stage, surgery, chemotherapy, and radiation were significant risk factors for OS, whereas age, TNM stage, surgery, chemotherapy, and radiotherapy were significant risk factors for CSS. Additionally, C-index and calibration curves indicated that the prognostic nomogram prediction and the actual observation in both cohorts would be very coherent. CONCLUSIONS: The predictive nomogram created in this study can offer patients with tongue SCC customized treatment and survival risk assessment.

Dmbg-Net: Dilated multiresidual boundary guidance network for COVID-19 infection segmentation.

Accurate segmentation of infected regions in lung computed tomography (CT) images is essential for the detection and diagnosis of coronavirus disease 2019 (COVID-19). However, lung lesion segmentation has some challenges, such as obscure boundaries, low contrast and scattered infection areas. In this paper, the dilated multiresidual boundary guidance network (Dmbg-Net) is proposed for COVID-19 infection segmentation in CT images of the lungs. This method focuses on semantic relationship modelling and boundary detail guidance. First, to effectively minimize the loss of significant features, a dilated residual block is substituted for a convolutional operation, and dilated convolutions are employed to expand the receptive field of the convolution kernel. Second, an edge-attention guidance preservation block is designed to incorporate boundary guidance of low-level features into feature integration, which is conducive to extracting the boundaries of the region of interest. Third, the various depths of features are used to generate the final prediction, and the utilization of a progressive multi-scale supervision strategy facilitates enhanced representations and highly accurate saliency maps. The proposed method is used to analyze COVID-19 datasets, and the experimental results reveal that the proposed method has a Dice similarity coefficient of 85.6% and a sensitivity of 84.2%. Extensive experimental results and ablation studies have shown the effectiveness of Dmbg-Net. Therefore, the proposed method has a potential application in the detection, labeling and segmentation of other lesion areas.