LRENet: a location-related enhancement network for liver lesions in CT images.

Objective. Liver cancer is a major global health problem expected to increase by more than 55% by 2040. Accurate segmentation of liver tumors from computed tomography (CT) images is essential for diagnosis and treatment planning. However, this task is challenging due to the variations in liver size, the low contrast between tumor and normal tissue, and the noise in the images. APPROACH: In this study, we propose a novel method called location-related enhancement network (LRENet) which can enhance the contrast of liver lesions in CT images and facilitate their segmentation. LRENet consists of two steps: (1) locating the lesions and the surrounding tissues using a morphological approach and (2) enhancing the lesions and smoothing the other regions using a new loss function. MAIN RESULTS: We evaluated LRENet on two public datasets (LiTS and 3Dircadb01) and one dataset collected from a collaborative hospital (Liver cancer dateset), and compared it with state-of-the-art methods regarding several metrics. The results of the experiments showed that our proposed method outperformed the compared methods on three datasets in several metrics. We also trained the Swin-Transformer network on the enhanced datasets and showed that our method could improve the segmentation performance of both liver and lesions. SIGNIFICANCE: Our method has potential applications in clinical diagnosis and treatment planning, as it can provide more reliable and informative CT images of liver tumors.

Site-Specific Anchoring a Luminescent Tag in a Protein with Non-Emissive Iridium(III) Complex.

Site-specific modification of proteins with synthetic fluorescent tag effectively improves the resolution of imaging, and such a labeling method with negligible three-dimensional structural perturbations and minimal impact on the biological functions of proteins is of high interest to dissect the high-resolution activities of biomolecules in complex systems. To this end, several non-emissive iridium(III) complexes [Ir(C-N)2 (H2 O)2 ]+ OTF- (C-N denotes various cyclometalated ligands) were designed and synthesized. These complexes were tested for attaching a protein by coordinating to H/X (HisMet, HisHis, and HisCys) that are separated by i and i+4 in α-helix. Replacement of the two labile water ligands in the iridium(III) complex by a protein HisHis pair increases the luminescent intensity up to over 100 folds. This labeling approach has been demonstrated in a highly specific and efficient manner in a number of proteins, and it is also feasible for labeling target proteins in cell lysates.

Sulfate reduction behavior in response to landfill dynamic pressure changes.

During the long-term stabilization process of landfills, the pressure field undergoes constant changes. This study constructed dynamic pressure changes scenarios of high-pressure differentials (0.6 MPa) and low-pressure differentials (0.2 MPa) in the landfill pressure field at 25 °C and 50 °C, and investigated the sulfate reduction behavior in response to landfill dynamic pressure changes. The results showed that the pressurization or depressurization of high-pressure differentials caused more significant differences in sulfate reduction behavior than that of low-pressure differentials. The lowest hydrogen sulfide (H2S) release peak concentration under pressurization was only 29.67% of that under initial pressure condition; under depressurization, the highest peak concentration of H2S was up to 21,828 mg m-3, posing a serious risk of H2S pollution. Microbial community and correlation analysis showed that pressure had a negative impact on the sulfate-reducing bacteria (SRB) community, and the SRB community adjusted its structure to adapt to pressure changes. Specific SRBs were further enriched with pressure changes. Differential H2S release behavior under pressure changes in the 25 °C pressure environments were mediated by Desulfofarcimen (ASV343) and Desulfosporosinus (ASV1336), while Candidatus Desulforudis (ASV24) and Desulfohalotomaculum (ASV94) played a key role at 50 °C. This study is helpful in the formulation of control strategies for the source of odor pollution in landfills.

Microplastic release and sulfate reduction response in the early stage of a simulated landfill.

Landfills are essential facilities for treating and disposing municipal solid waste. They emit sulfur-containing odors and serve as an important sink for a new type of pollutant called microplastics (MPs). This study focused on the initial stage of anaerobic degradation to establish the relationship between the release of MPs and odor generation. Our findings show the rapid release of MPs into the leachate in the early stage of landfill and their predominant accumulation in the leachate sediment. The circulating leachate contained 1.45 times higher concentrations of MPs than the noncirculating leachate, with a peak concentration of 39 items·L-1. In addition, fragmentation of MPs occurred. The percentage of MPs with particle sizes of 2.5-5 mm decreased from 66.70 % to 22.32 %, while those measuring 0.1-0.5 mm increased by 33.12 %. A positive correlation was observed between MP release and sulfate reduction. Although leachate circulation increased the release of MPs, it also reduced the overall release time and total amount of MPs exported from the landfill. Compared with the initial landfill waste, the leachate operation mode, regardless of circulation, resulted in a 6.15-8.93-fold increase in MP release. These findings provide a valuable foundation for the simultaneous regulation of traditional pollutant odor and new pollutants (MPs) in landfills.

Hot spots and trends in PCI prognostic research: A bibliometric analysis with CiteSpace.

BACKGROUND: The number of patients undergoing percutaneous coronary intervention (PCI) procedures is increasing along with the number of studies involving guidelines, prognostic assessments, and cardiac rehabilitation related to PCI strategies. However, fewer studies have reported the mapping of knowledge structure and hotspot analysis in this field. Our goal was to discuss and analyze the current status, hot spots and developmental trends associated with research into the prognosis of patients undergoing PCI, and to provide reference for PCI-related research. METHODS: The Web of Science Core Collection and China Knowledge Network were searched for relevant literature from January 2003 to October 2022, and CiteSpace 6.1. R3 software was used to analyze the co-occurrence, clustering, and emerging authors, institutions, and keywords. RESULTS: A total of 2666 English and 2010 Chinese publications were included. The number of publications showed a growing trend. The author with the maximum number of articles was Xu Bo. The institutions with high productivity were Peking Union Medical College and Capital Medical University. Although the number of Chinese articles was high, the cooperation between institutions was low and the impact was small. The results of the analysis suggest a shift in the focus of keywords from coronary artery disease and PCI to studies involving the assessment and intervention of risk factors associated with poor prognosis of PCI. Traditional Chinese Medicine and anxiety represent the emerging direction of PCI prognosis. The assessment of major adverse cardiovascular events and cardiac rehabilitation require careful analysis in post-PCI research. CONCLUSION: The findings of this bibliometric study present a comprehensive and systematic overview of the PCI prognosis, based on the analysis of the current status and trends in research, which may facilitate the identification of hot topics and new directions for future research.

Sulfate reduction behavior in response to changing of pressure coupling with temperature inside landfill.

The behavior of sulfate reduction, which was the source of hydrogen sulfide (H2S) odor, was investigated under changing pressure and temperature conditions inside landfills. The results showed that the release of H2S and methyl mercaptan (MM) was significantly inhibited at 25 °C and 50 °C under pressure, and the highest H2S and MM concentrations released were only 0.82 %-1.30 % and 1.87 %-4.32 % of atmospheric pressure, respectively. Analysis of the microbial community structure and identification of sulfate-reducing bacteria (SRB) revealed that temperature significantly altered the microbial community in the landfill environment, while pressure inhibited some bacteria and induced the growth and reproduction of specific bacteria. Key SRB (Desulfosporosinus-ASV212, Desulfitibacter-ASV1744) mediated differentiated sulfate reduction behavior in the pressure-bearing environment at 25 °C, while key SRB (Dethiobacter-ASV177, Desulfitibacter-ASV2355 and ASV316) were involved at 50 °C. This study provides a theoretical basis for the formulation of landfill gas management and control strategies.

Autonomous detection of myocarditis based on the fusion of improved quantum genetic algorithm and adaptive differential evolution optimization back propagation neural network.

Myocarditis is cardiac damage caused by a viral infection. Its result often leads to a variety of arrhythmias. However, rapid and reliable identification of myocarditis has a great impact on early diagnosis, expedited treatment, and improved patient survival rates. Therefore, a novel strategy for the autonomous detection of myocarditis is suggested in this work. First, the improved quantum genetic algorithm (IQGA) is proposed to extract the optimal features of ECG beat and heart rate variability (HRV) from raw ECG signals. Second, the backpropagation neural network (BPNN) is optimized using the adaptive differential evolution (ADE) algorithm to classify various ECG signal types with high accuracy. This study examines analogies among five different ECG signal types: normal, abnormal, myocarditis, myocardial infarction (MI), and prior myocardial infarction (PMI). Additionally, the study uses binary and multiclass classification to group myocarditis with other cardiovascular disorders in order to assess how well the algorithm performs in categorization. The experimental results demonstrate that the combination of IQGA and ADE-BPNN can effectively increase the precision and accuracy of myocarditis autonomous diagnosis. In addition, HRV assesses the method's robustness, and the classification tool can detect viruses in myocarditis patients one week before symptoms worsen. The model can be utilized in intensive care units or wearable monitoring devices and has strong performance in the detection of myocarditis.

[Research Progress in Precision Nursing for Enhanced Recovery After Surgery].

With the evolution and development of the concepts of medicine, research concerning precision medicine and precision nursing is constantly expanding and deepening, creating new challenges and opportunities for the nursing practice of enhanced recovery after surgery (ERAS). In this paper, we reviewed the current status of research on precision nursing for ERAS, giving an overview of the application status of precision nursing in ERAS from the perspectives of precision nursing assessment, precision symptom management, precision nutrition support, and precision health education and nursing follow-up. In addition, we analyzed the challenges and their solutions for further promotion and application of precision nursing in ERAS, including strengthening the basic professional knowledge and skills, building a nursing information platform, and actively applying new tools and technologies. In the future, clinical nursing staffs should further utilize the relevant concepts and methods of precision nursing to optimize and improve perioperative patient care strategies, ensure patient safety, enhance the quality of nursing care, improve patient outcomes, and promote a more important role played by precision nursing in ERAS.

Interaction of HSP70-2 gene polymorphism with body mass index and alcohol consumption on the prognosis of Uyghur patients with ischemic heart failure. / HSP70-2åŸºå› å¤šæ€æ€§ä¸Žä½“è´¨æŒ‡æ•°ã€é¥®é ’çš„äº¤äº’ä½œç”¨å¯¹ç»´å¾å°”æ—ç¼ºè¡€æ€§å¿ƒåŠ›è¡°ç«­æ‚£è€ é¢„åŽçš„å½±å“.

OBJECTIVES: To investigate the interaction of HSP70-2 gene polymorphism with body mass index (BMI) and alcohol consumption on the prognosis of Uyghur patients with ischemic heart failure (IHF). METHODS: A total of 205 Uyghur patients with IHF admitted in Urumqi Friendship Hospital from June 2014 to June 2017 were enrolled; 200 age and sex-matched healthy Uyghur physical examiners in the hospital were enrolled as healthy controls. The HSP70-2 gene +1267 polymorphism was detected by PCR. Multivariate unconditional logistic regression was used to analyze the risk factors associated with prognosis in patients with IHF, and the relative excess risk of interaction (RERI) was calculated by crossover analysis to determine the interaction of HSP70-2 gene polymorphism with BMI and alcohol consumption. RESULTS: Patients were followed up for 3 years, there were 56 cases with poor prognosis (27.32%) and 149 cases with good prognosis (72.68%). Compared with the healthy control group and the good prognosis group, the poor prognosis group had a significantly higher proportion of subjects with alcohol consumption, abnormal alanine aminotransferase (ALT) and aspartate aminotransferase (AST) levels as well as lower BMI and left ventricular ejection fraction (all P<0.05). There were significant differences in distributions of HSP70-2 genotype AA/AG/GG and A/G allele between the good prognosis group and the poor prognosis group (both P<0.05). There were significant differences in the distribution of HSP70-2 genotype (χ2=45.42, P<0.01) and A/G allele among IHF patients with different NYHA cardiac function class; the frequency of A allele of HSP70-2 gene increased, and G allele decreased with the increase of cardiac function class (χ2=19.14, P<0.01). Multivariate logistic regression analysis showed that alcohol consumption as well as abnormal ALT and AST were risk factors for poor prognosis in patients with IHF, while BMI and GG type of HSP70-2 gene (compared with AA type) were protective factors (all P<0.05). Crossover analysis showed a significant additive interaction between BMI and HSP70-2 gene polymorphism (RERI=1.15, 95%CI: 0.54-1.76, P<0.01), and for patients carrying HSP70-2 gene type AA/AG, BMI<26.5 kg/m2 increased the risk of poor prognosis (OR=7.47, 95%CI: 2.51-22.22, P<0.01); there was no significant additive interaction between alcohol consumption and HSP70-2 gene polymorphism (RERI=0.56, 95%CI: －6.07-7.20, P>0.05). CONCLUSIONS: The HSP70-2 gene polymorphism interacts with BMI in Uyghur IHF patients, and BMI<26.5 kg/m2 increases the risk of poor prognosis in IHF patients carrying the HSP70-2 AA/AG genotype.

Reduced-dose post-transplant cyclophosphamide plus low-dose post-transplant anti-thymocyte globulin as graft-versus-host disease prophylaxis with fludarabine-busulfan-cytarabine conditioning in haploidentical peripheral blood stem cell transplantation: A multicentre, randomized controlled clinical trial.

Anti-thymocyte globulin (ATG) or post-transplant cyclophosphamide (PTCy)-based regimens are widely used for graft-versus-host disease (GVHD) prophylaxis in haploidentical haematopoietic stem cell transplantation (haplo-HSCT). To improve the effectiveness of GVHD prophylaxis in haploidentical peripheral blood stem cell transplantation (haplo-PBSCT), we conducted a multicentre, randomized clinical trial to determine the efficacy of reduced-dose PTCy (40 mg/kg/d on days 3 and 4) combined with low-dose post-transplant ATG (2.5 mg/kg on day 8)-based GVHD prophylaxis (reduced-dose PTCy/ATG) with fludarabine-busulfan-cytarabine (FBA) conditioning for patients with haematological malignancies. From 2018 to 2022, 122 patients from four institutions were randomly assigned 1:1 to either a reduced-dose PTCy/ATG or a standard-dose ATG group ('Beijing Protocol', ATG: 10 mg/kg). All patients achieved myeloid engraftment. Cumulative incidences of grade II-IV (11.5% vs 39.3%, p = 0.001) and grade III-IV (6.6% vs 24.6%, p = 0.014) acute GVHD at day 100 were significantly reduced in the reduced-dose PTCy/ATG group. Furthermore, two-year overall survival, disease-free survival and GVHD-free/relapse-free survival were significantly improved in the reduced-dose PTCy/ATG group (75.4% vs 54.1%, p = 0.021; 72.7% vs 55.0%, p = 0.044; 61.3% vs 42.3%, p = 0.022 respectively). Our results demonstrate that the addition of low-dose ATG to reduced-dose PTCy with FBA conditioning is a promising strategy in haplo-PBSCT.

COVID-19 ground-glass opacity segmentation based on fuzzy c-means clustering and improved random walk algorithm.

Accurate segmentation of ground-glass opacity (GGO) is an important premise for doctors to judge COVID-19. Aiming at the problem of mis-segmentation for GGO segmentation methods, especially the problem of adhesive GGO connected with chest wall or blood vessel, this paper proposes an accurate segmentation of GGO based on fuzzy c-means (FCM) clustering and improved random walk algorithm. The innovation of this paper is to construct a Markov random field (MRF) with adaptive spatial information by using the spatial gravity Model and the spatial structural characteristics, which is introduced into the FCM model to automatically balance the insensitivity to noise and preserve the effectiveness of image edge details to improve the clustering accuracy of image. Then, the coordinate values of nodes and seed points in the image are combined with the spatial distance, and the geodesic distance is added to redefine the weight. According to the edge density of the image, the weight of the grayscale and the spatial feature in the weight function is adaptively calculated. In order to reduce the influence of edge noise on GGO segmentation, an adaptive snowfall model is proposed to preprocess the image, which can suppress the noise without losing the edge information. In this paper, CT images of different types of COVID-19 are selected for segmentation experiments, and the experimental results are compared with the traditional segmentation methods and several SOTA methods. The results suggest that the paper method can be used for the auxiliary diagnosis of COVID-19, so as to improve the work efficiency of doctors.

Research on multi-modal autonomous diagnosis algorithm of COVID-19 based on whale optimized support vector machine and improved D-S evidence fusion.

Aiming at the problem that the single CT image signal feature recognition method in the self-diagnosis of diseases cannot accurately and reliably classify COVID-19, and it is easily confused with suspected cases. The collected CT signals and experimental indexes are extracted to construct different feature vectors. The support vector machine is optimized by the improved whale algorithm for the preliminary diagnosis of COVID-19, and the basic probability distribution function of each evidence is calculated by the posterior probability modeling method. Then the similarity measure is introduced to optimize the basic probability distribution function. Finally, the multi-domain feature fusion prediction model is established by using the weighted D-S evidence theory. The experimental results show that the fusion of multi-domain feature information by whale optimized support vector machine and improved D-S evidence theory can effectively improve the accuracy and the precision of COVID-19 autonomous diagnosis. The method of replacing a single feature parameter with multi-modal indicators (CT, routine laboratory indexes, serum cytokines and chemokines) provides a more reliable signal source for the diagnosis model, which can effectively distinguish COVID-19 from the suspected cases.

Frailty and hearing loss: From association to causation.

Background: Observational studies suggest that frailty is associated with hearing loss (HL) but with inconsistent results. This study aims to examine such association and to assess its causality. Materials and methods: The cross-sectional data from the National Health and Nutrition Examination Survey (NHANES). Multivariate logistic regression models were used to assess the association between HL and frailty index (FI). Genetic variants associated with the FI and HL were obtained from a large genome-wide association study (GWAS) meta-analysis and UK Biobank GWAS. The inverse variance weighting (IVW) method was used to estimate causal effects. Sensitivity analyses were performed to further validate the robustness of results. Results: In this cross-sectional analysis, results support the possibility that frailty may be associated with a higher risk of developing HL, with self-reported [odds ratio (OR) = 2.813; 95% CI, 2.386, 3.317; p < 0.001], speech frequency HL (OR = 1.975; 95% CI, 1.679-2.323; p < 0.001), and high frequency HL (OR = 1.748; 95% CI, 1.459-2.094; p < 0.001). In the adjusted model, frail participants remained at high risk of HL. Mendelian randomization (MR) studies showed a bidirectional causal association between genetically predicted FI and risk of HL (FI for exposure: OR = 1.051; 95% CI, 1.020-1.083; p = 0.001; HL for exposure: OR = 1.527; 95% CI, 1.227-1.901; p < 0.001). Conclusion: Our observational study found that inter-individual differences in frailty were associated with the risk of developing HL. Genetic evidence suggests a potential bidirectional causal association between FI and HL. Furthermore, the potential mechanisms of this association require investigation.

Risk factors for inpatient malnutrition and length of stay assessed by 'NutritionDay' in China.

BACKGROUND AND OBJECTIVES: NutritionDay is a yearly global point-prevalence study of malnutrition or nutritional risk in hospitals. We aimed to provide a comprehensive nutritional survey of hospitalized patients and analyze the risk factors of malnutrition and prolonged hospitalization in Chinese inpatients. METHODS AND STUDY DESIGN: The international daylong cross-sectional survey was performed on November 07th, 2019. Ten hospitals were invited to participate in this NutritionDay survey. Nutritional risk was identified by nutritional risk screening 2002, and malnutrition was identified by the ESPEN criteria. We measured the incidence of malnutrition and nutritional risk. And we analysed risk factors for malnutrition and length of stay in Chinese hospitalized patients. RESULTS: 875 hospitalized patients from 6 departments were included in the analysis. The malnutrition rate was 11.6% and the incidence of nutritional risk was 17.8%. It was analyzed that tumor load, end-stage disease, motility, self-rated health, types of oral medicine, and food intake during the past week were independent risk factors for malnutrition or nutritional risk. 56.2% (118/210) of patients at nutritional risk or malnutrition received extra nutritional support, whereas 22.5% (88/391) well-nourished patients did. Moreover, nutrition status, ever stayed in ICU and self-rated health were associated with prolonged length of stay. CONCLUSIONS: In a word, the prevalence of malnutrition or nutritional risk was about 29.4%. Patients with malnutrition or nutritional risk had a higher transfer rate, lower rehabilitation rate and longer hospital stays. The attention to malnutrition patients needs to be further strengthened.

Telomere Length and Hearing Loss: A Two-Sample Mendelian Randomization.

BACKGROUND: Observational studies have suggested that there may be an association between telomere length (TL) and hearing loss (HL). However, inferring causality from observational studies is subject to residual confounding effects, reverse causation, and bias. This study adopted a two-sample Mendelian randomization (MR) approach to evaluate the causal relationship between TL and increased risk of HL. METHODS: A total of 16 single nucleotide polymorphisms (SNPs) associated with TL were identified from a genome-wide association study (GWAS) meta-analysis of 78,592 European participants and applied to our modeling as instrumental variables. Summary-level data for hearing loss (HL), age-related hearing loss (ARHL), and noise-induced hearing loss (NIHL) were obtained from the recent largest available GWAS and five MR analyses were used to investigate the potential causal association of genetically predicted TL with increased risk for HL, including the inverse-variance-weighted (IVW), weighted median, MR-Egger regression, simple mode, and weighted mode. In addition, sensitivity analysis, pleiotropy, and heterogeneity tests were also used to evaluate the robustness of our findings. RESULTS: There was no causal association between genetically predicted TL and HL or its subtypes (by the IVW method, HL: odds ratio (OR) = 1.216, p = 0.382; ARHL: OR = 0.934, p = 0.928; NIHL: OR = 1.003, p = 0.776). Although heterogenous sites rs2736176, rs3219104, rs8105767, and rs2302588 were excluded for NIHL, the second MR analysis was consistent with the first analysis (OR = 1.003, p = 0.572). CONCLUSION: There was no clear causal relationship between shorter TLs and increased risk of HL or its subtypes in this dataset.

Two-dimensional reciprocal cross entropy multi-threshold combined with improved firefly algorithm for lung parenchyma segmentation of COVID-19 CT image.

The lesions of COVID-19 CT image show various kinds of ground-glass opacity and consolidation, which are distributed in left lung, right lung or both lungs. The lung lobes are uneven and it have similar gray value to the surrounding arteries, veins, and bronchi. The lesions of COVID-19 have different sizes and shapes in different periods. Accurate segmentation of lung parenchyma in CT image is a key step in COVID-19 detection and diagnosis. Aiming at the unideal effect of traditional image segmentation methods on lung parenchyma segmentation in CT images, a lung parenchyma segmentation method based on two-dimensional reciprocal cross entropy multi-threshold combined with improved firefly algorithm is proposed. Firstly, the optimal threshold method is used to realize the initial segmentation of the lung, so that the segmentation threshold can change adaptively according to the detailed information of lung lobes, trachea, bronchi and ground-glass opacity. Then the lung parenchyma is further processed to obtain the lung parenchyma template, and then the defective template is repaired combined with the improved Freeman chain code and Bezier curve. Finally, the lung parenchyma is extracted by multiplying the template with the lung CT image. The accuracy of lung parenchyma segmentation has been improved in the contrast clarity of CT image and the consistency of lung parenchyma regional features, with an average segmentation accuracy rate of 97.4%. The experimental results show that for COVID-19 and suspected cases, the method has an ideal segmentation effect, and it has good accuracy and robustness.

A multi-layer soft lattice based model for Chinese clinical named entity recognition.

OBJECTIVE: Named entity recognition (NER) is a key and fundamental part of many medical and clinical tasks, including the establishment of a medical knowledge graph, decision-making support, and question answering systems. When extracting entities from electronic health records (EHRs), NER models mostly apply long short-term memory (LSTM) and have surprising performance in clinical NER. However, increasing the depth of the network is often required by these LSTM-based models to capture long-distance dependencies. Therefore, these LSTM-based models that have achieved high accuracy generally require long training times and extensive training data, which has obstructed the adoption of LSTM-based models in clinical scenarios with limited training time. METHOD: Inspired by Transformer, we combine Transformer with Soft Term Position Lattice to form soft lattice structure Transformer, which models long-distance dependencies similarly to LSTM. Our model consists of four components: the WordPiece module, the BERT module, the soft lattice structure Transformer module, and the CRF module. RESULT: Our experiments demonstrated that this approach increased the F1 by 1-5% in the CCKS NER task compared to other models based on LSTM with CRF and consumed less training time. Additional evaluations showed that lattice structure transformer shows good performance for recognizing long medical terms, abbreviations, and numbers. The proposed model achieve 91.6% f-measure in recognizing long medical terms and 90.36% f-measure in abbreviations, and numbers. CONCLUSIONS: By using soft lattice structure Transformer, the method proposed in this paper captured Chinese words to lattice information, making our model suitable for Chinese clinical medical records. Transformers with Mutilayer soft lattice Chinese word construction can capture potential interactions between Chinese characters and words.

Asymptomatic COVID-19 CT image denoising method based on wavelet transform combined with improved PSO.

The quality of asymptomatic corona virus disease 2019 (COVID-19) computed tomography (CT) image is reduced due to interference from Gaussian noise, which affects the subsequent image processing. Aiming at the problem that asymptomatic COVID-19 CT image often have small flake ground-glass shadow in the early lesions, and the density is low, which is easily confused with noise. A denoising method of wavelet transform with shrinkage factor is proposed. The threshold decreases with the increase of decomposition scale, and it reduces the misjudgment of signal points. In the advanced stage, the range of lesions increases, with consolidation and fibrosis in different sizes, which have similar gray value to the CT images of suspected cases. Aiming at the problems of low contrast and fuzzy boundary in the traditional wavelet transform, the threshold function based on the optimization of parameters combined with the improved particle swam optimization (PSO) is proposed, so that the parameters of wavelet threshold function can change adaptively according to the lung lobe and ground-glass lesions with fewer iterations. The simulation results show that the paper method is significantly better than other algorithms in peak signal-to-noise ratio (PSNR), signal-to-noise ratio (SNR) and mean absolute error (MSE). For example, aiming at the early asymptomatic COVID-19, compared with the comparison methods, the PSNR under the proposed method has increased by about 5 dB, the MSE has been greatly reduced, and the SNR has increased by about 6.1 dB. It can be seen that the denoising effect under the proposed method is the best.

Deep learning for predicting respiratory rate from biosignals.

In the past decade, deep learning models have been applied to bio-sensors used in a body sensor network for prediction. Given recent innovations in this field, the prediction accuracy of novel models needs to be evaluated for bio-signals. In this paper, we evaluate the performance of deep learning models for respiratory rate prediction. We consider three datasets from bio-sensors which include electrocardiogram (ECG), photoplethysmogram (PPG) data, and surface electromyogram (sEMG) data. The deep learning models include Long short-term memory (LSTM) networks, Bidirectional LSTM (Bi-LSTM), attention-based variants of LSTM, CNN-LSTM and Convolutional-LSTM networks. The deep learning models are evaluated for two separate windows which are 32 s and 64 s window. The models' performance is evaluated using mean absolute error (MAE). The 64 s window has more accurate prediction compared to the 32 s window. Our results indicate Bi-LSTM with Bahdanu Attention has the best performance for the bio-signals. LSTM performs best with one of the datasets, yielding an MAE of 0.70 ± 0.02. Bi-LSTM with Bahdanau attention showed best results with two of the three datasets with MAE of 0.51 ± 0.03 for sEMG based data and MAE of 0.24 ± 0.03 with PPG and ECG based data.