Automatic data augmentation for medical image segmentation using Adaptive Sequence-length based Deep Reinforcement Learning.

Although existing deep reinforcement learning-based approaches have achieved some success in image augmentation tasks, their effectiveness and adequacy for data augmentation in intelligent medical image analysis are still unsatisfactory. Therefore, we propose a novel Adaptive Sequence-length based Deep Reinforcement Learning (ASDRL) model for Automatic Data Augmentation (AutoAug) in intelligent medical image analysis. The improvements of ASDRL-AutoAug are two-fold: (i) To remedy the problem of some augmented images being invalid, we construct a more accurate reward function based on different variations of the augmentation trajectories. This reward function assesses the validity of each augmentation transformation more accurately by introducing different information about the validity of the augmented images. (ii) Then, to alleviate the problem of insufficient augmentation, we further propose a more intelligent automatic stopping mechanism (ASM). ASM feeds a stop signal to the agent automatically by judging the adequacy of image augmentation. This ensures that each transformation before stopping the augmentation can smoothly improve the model performance. Extensive experimental results on three medical image segmentation datasets show that (i) ASDRL-AutoAug greatly outperforms the state-of-the-art data augmentation methods in medical image segmentation tasks, (ii) the proposed improvements are both effective and essential for ASDRL-AutoAug to achieve superior performance, and the new reward evaluates the transformations more accurately than existing reward functions, and (iii) we also demonstrate that ASDRL-AutoAug is adaptive for different images in terms of sequence length, as well as generalizable across different segmentation models.

An Integrated Multi-Channel Deep Neural Network for Mesial Temporal Lobe Epilepsy Identification Using Multi-Modal Medical Data.

Epilepsy is a chronic brain disease with recurrent seizures. Mesial temporal lobe epilepsy (MTLE) is the most common pathological cause of epilepsy. With the development of computer-aided diagnosis technology, there are many auxiliary diagnostic approaches based on deep learning algorithms. However, the causes of epilepsy are complex, and distinguishing different types of epilepsy accurately is challenging with a single mode of examination. In this study, our aim is to assess the combination of multi-modal epilepsy medical information from structural MRI, PET image, typical clinical symptoms and personal demographic and cognitive data (PDC) by adopting a multi-channel 3D deep convolutional neural network and pre-training PET images. The results show better diagnosis accuracy than using one single type of medical data alone. These findings reveal the potential of a deep neural network in multi-modal medical data fusion.

A retrospective cohort study evaluating the improvement of medical records management based on whole-process control.

BACKGROUND: Whole-process management is a novel approach widely applied in industry and commerce; however, it is not widely used in the management of medical records in hospitals. OBJECTIVE: The purpose of this study is to investigate the application of whole-process control in the administration of a hospital's medical records department to achieve refined management of medical records. METHODS: Whole-process control is a management measure that begins with process conception and implementation and includes control over all processes. The control group included medical records that were created prior to the implementation of whole-process control, i.e., those created between June 1 and December 31, 2020. The observation group included medical records that were created after the implementation of whole-process control. The behavior of the medical records staff (in terms of medical record collection, sorting, entry, inquiry, and supply) and the final quality of the medical records (the number of grade-A medical records and their front-page quality) were compared between the two groups, and subjective judgments related to staff satisfaction were reviewed. RESULTS: The implementation of whole-process control improved the behavior of the medical records staff. The final quality of the medical records was also improved, as was the job satisfaction of the medical records staff. CONCLUSION: Implementing whole-process control improved the management of medical records and quality of medical records.

Recommendation model based on generative adversarial network and social reconstruction.

Social relations can effectively alleviate the data sparsity problem in recommendation, but how to make effective use of social relations is a difficulty. However, the existing social recommendation models have two deficiencies. First, these models assume that social relations are applicable to various interaction scenarios, which does not match the reality. Second, it is believed that close friends in social space also have similar interests in interactive space and then indiscriminately adopt friends' opinions. To solve the above problems, this paper proposes a recommendation model based on generative adversarial network and social reconstruction (SRGAN). We propose a new adversarial framework to learn interactive data distribution. On the one hand, the generator selects friends who are similar to the user's personal preferences and considers the influence of friends on users from multiple angles to get their opinions. On the other hand, friends' opinions and users' personal preferences are distinguished by the discriminator. Then, the social reconstruction module is introduced to reconstruct the social network and constantly optimize the social relations of users, so that the social neighborhood can assist the recommendation effectively. Finally, the validity of our model is verified by experimental comparison with multiple social recommendation models on four datasets.

[A research on epilepsy source localization from scalp electroencephalograph based on patient-specific head model and multi-dipole model].

Accurate source localization of the epileptogenic zone (EZ) is the primary condition of surgical removal of EZ. The traditional localization results based on three-dimensional ball model or standard head model may cause errors. This study intended to localize the EZ by using the patient-specific head model and multi-dipole algorithms using spikes during sleep. Then the current density distribution on the cortex was computed and used to construct the phase transfer entropy functional connectivity network between different brain areas to obtain the localization of EZ. The experiment result showed that our improved methods could reach the accuracy of 89.27% and the number of implanted electrodes could be reduced by (19.34 ± 7.15)%. This work can not only improve the accuracy of EZ localization, but also reduce the additional injury and potential risk caused by preoperative examination and surgical operation, and provide a more intuitive and effective reference for neurosurgeons to make surgical plans.

Dynamic Correlation Adjacency-Matrix-Based Graph Neural Networks for Traffic Flow Prediction.

Modeling complex spatial and temporal dependencies in multivariate time series data is crucial for traffic forecasting. Graph convolutional networks have proved to be effective in predicting multivariate time series. Although a predefined graph structure can help the model converge to good results quickly, it also limits the further improvement of the model due to its stationary state. In addition, current methods may not converge on some datasets due to the graph structure of these datasets being difficult to learn. Motivated by this, we propose a novel model named Dynamic Correlation Graph Convolutional Network (DCGCN) in this paper. The model can construct adjacency matrices from input data using a correlation coefficient; thus, dynamic correlation graph convolution is used for capturing spatial dependencies. Meanwhile, gated temporal convolution is used for modeling temporal dependencies. Finally, we performed extensive experiments to evaluate the performance of our proposed method against ten existing well-recognized baseline methods using two original and four public datasets.

A Systematic Evaluation of Supervised Machine Learning Algorithms for Cell Phenotype Classification Using Single-Cell RNA Sequencing Data.

The new technology of single-cell RNA sequencing (scRNA-seq) can yield valuable insights into gene expression and give critical information about the cellular compositions of complex tissues. In recent years, vast numbers of scRNA-seq datasets have been generated and made publicly available, and this has enabled researchers to train supervised machine learning models for predicting or classifying various cell-level phenotypes. This has led to the development of many new methods for analyzing scRNA-seq data. Despite the popularity of such applications, there has as yet been no systematic investigation of the performance of these supervised algorithms using predictors from various sizes of scRNA-seq datasets. In this study, 13 popular supervised machine learning algorithms for cell phenotype classification were evaluated using published real and simulated datasets with diverse cell sizes. This benchmark comprises two parts. In the first, real datasets were used to assess the computing speed and cell phenotype classification performance of popular supervised algorithms. The classification performances were evaluated using the area under the receiver operating characteristic curve, F1-score, Precision, Recall, and false-positive rate. In the second part, we evaluated gene-selection performance using published simulated datasets with a known list of real genes. The results showed that ElasticNet with interactions performed the best for small and medium-sized datasets. The NaiveBayes classifier was found to be another appropriate method for medium-sized datasets. With large datasets, the performance of the XGBoost algorithm was found to be excellent. Ensemble algorithms were not found to be significantly superior to individual machine learning methods. Including interactions in the ElasticNet algorithm caused a significant performance improvement for small datasets. The linear discriminant analysis algorithm was found to be the best choice when speed is critical; it is the fastest method, it can scale to handle large sample sizes, and its performance is not much worse than the top performers.

Stability and Stabilization for Fuzzy Systems With Time Delay by Applying Polynomial Membership Function and Iteration Algorithm.

Recently, a switching method is applied to deal with the membership function-dependent Lyapunov-Krasovskii functional (LKF) for fuzzy systems with time delay; however, the Lyapunov matrices are only linear dependent on the grades of membership which leads to linear switching (Wang and Lam, 2019). In this article, the linear dependence on the grades of membership is extended to homogenous polynomially membership function dependent (HPMFD) and the linear switching is extended to polynomial matrix switching, based on which the obtained result contains the previous one as a special case. Furthermore, in order to fully use the introduced variables without speial structure, an iteration algorithm is designed to construct the switching controller and the initial condition of the algorithm is also discussed. The final simulation demonstrates the effectiveness of the developed new results.

Probabilistic Graph Convolutional Network via Topology-Constrained Latent Space Model.

Although many graph convolutional neural networks (GCNNs) have achieved superior performances in semisupervised node classification, they are designed from either the spatial or spectral perspective, yet without a general theoretical basis. Besides, most of the existing GCNNs methods tend to ignore the ubiquitous noises in the network topology and node content and are thus unable to model these uncertainties. These drawbacks certainly reduce their effectiveness in integrating network topology and node content. To provide a probabilistic perspective to the GCNNs, we model the semisupervised node classification problem as a topology-constrained probabilistic latent space model, probabilistic graph convolutional network (PGCN). By representing the nodes in a more efficient distribution form, the proposed framework can seamlessly integrate the node content and network topology. When specifying the distribution in PGCN to be a Gaussian distribution, the transductive node classification problems can be solved by the general framework and a specific method, called PGCN with the Gaussian distribution representation (PGCN-G), is proposed. To overcome the overfitting problem in covariance estimation and reduce the computational complexity, PGCN-G is further improved to PGCN-G+ by imposing the covariance matrices of all vertices to possess the identical singular vectors. The optimization algorithm based on expectation-maximization indicates that the proposed method can iteratively denoise the network topology and node content with respect to each other. Besides the effectiveness of this top-down framework demonstrated via extensive experiments, it can also be deduced to cover the existing methods, graph convolutional network, graph attention network, and Gaussian mixture model and elaborate their characteristics and relationships by specific derivations.

Comparison of the effect of fluticasone combined with salmeterol and fluticasone alone in the treatment of pediatric asthma.

INTRODUCTION: A systematic review and meta-analysis was performed to investigate the effect of fluticasone + salmeterol and fluticasone alone in the treatment of pediatric asthma. EVIDENCE ACQUISITION: Studies meeting specific selection criteria were selected from online databases, including Pubmed, Embase, and the Cochrane Library. The quality of randomized controlled trials was assessed using the Cochrane Library. Weighted mean difference (WMD) and 95% CI were used to evaluate the effect size of continuous variables, while rate ratio (RR) and 95% CI were used for dichotomous variables. EVIDENCE SYNTHESIS: A total of 11 studies, including 8272 pediatric asthma patients, were included in this meta-analysis. Among these, 4133 patients were in the salmeterol + fluticasone group. The changes in forced expiratory volume in 1 second in children with asthma in the salmeterol + fluticasone and fluticasone alone groups were significantly different (fixed effects model, WMD=3.26, 95% CI: 1.52-5.00, P=0.0002). Asthma exacerbation between two groups were significantly different (fixed effects model, RR=0.85, 95% CI: 0.73-0.98, Z=2.18, P=0.03). There was no difference in the incidence of adverse events between salmeterol + fluticasone and fluticasone alone in the treatment of pediatric asthma (P>0.05). When the control group was treated with double dose fluticasone, the difference of changes in FEV1 and asthma exacerbation in children with asthma between the two groups was not significant. CONCLUSIONS: The efficacy of salmeterol + fluticasone is better than fluticasone alone, and the efficacy of salmeterol + fluticasone is equal to doubling the dose of fluticasone in the treatment of pediatric asthma.

Modified Zhibai Dihuang pill, a traditional Chinese medicine formula, on steroid withdrawal in systemic lupus erythematosus: A systematic review and meta-analysis.

BACKGROUND: Zhibai Dihuang pill (ZBDH), a Chinese herbal formula, has been widely used as an adjunctive therapy to help reduce the patient's steroid dose and maintain low disease activity in systemic lupus erythematosus (SLE). OBJECTIVE: This systematic review evaluates the therapeutic effect of modified ZBDH in reducing steroid use in patients with SLE. SEARCH STRATEGY: A systematic literature search was carried out using seven databases, including PubMed, Embase, Cochrane Central Register of Controlled Trials, Chinese Biomedical Literature Database, Chinese National Knowledge Infrastructure, Chinese VIP Information and Wanfang Database, from their inception to June 1st, 2019. The search terms included "systemic lupus erythematosus," "Chinese medicine" and "clinical trial," and their synonyms. Subject headings matching the above terms were also used. INCLUSION CRITERIA: This meta-analysis included randomized controlled trials that evaluated the reduction of steroid dose in patients with SLE. Traditional Chinese medicine (TCM) formulas in experimental group should be prescribed based on ZBDH and used as adjunctive therapy and the comparator should contain steroids. DATA EXTRACTION AND ANALYSIS: Two authors independently conducted database search, study selection, data extraction and quality assessment. The extracted information contained study design, sample size, recruitment mode, diagnostic criteria, inclusion and exclusion criteria, participant characteristics, TCM patterns, TCM formulas and treatment outcomes. The primary outcome was the change of steroid dose. Secondary outcomes included SLE Disease Activity Index (SLEDAI), biomarkers of disease activity and clinical response rate. STATA 15.0 was used to analyze the pooled effects reported as weighted mean difference (WMD) or odds ratio, with a 95% confidence interval (CI). RESULTS: In total, 20 trials involving 1470 SLE patients were included. The pooled result showed that modified ZBDH taken in combination with standard care led to a larger reduction in steroid dose, compared to standard care alone (WMD: 3.79; 95% CI: 2.58-5.01; P < 0.001). Favorable outcomes were also seen in secondary outcome criteria, such as SLEDAI and complement 3. The modified ZBDH treatments were well tolerated without increasing adverse effects. CONCLUSION: The systematic review provided preliminary evidence supporting the use of ZBDH as a co-therapy to aid steroid dose reduction in patients with SLE. However, more rigorous studies should be conducted to validate these findings, and explore the mechanisms of ZBDH's relevant bioactive constituents.

PPAI: a web server for predicting protein-aptamer interactions.

BACKGROUND: The interactions between proteins and aptamers are prevalent in organisms and play an important role in various life activities. Thanks to the rapid accumulation of protein-aptamer interaction data, it is necessary and feasible to construct an accurate and effective computational model to predict aptamers binding to certain interested proteins and protein-aptamer interactions, which is beneficial for understanding mechanisms of protein-aptamer interactions and improving aptamer-based therapies. RESULTS: In this study, a novel web server named PPAI is developed to predict aptamers and protein-aptamer interactions with key sequence features of proteins/aptamers and a machine learning framework integrated adaboost and random forest. A new method for extracting several key sequence features of both proteins and aptamers is presented, where the features for proteins are extracted from amino acid composition, pseudo-amino acid composition, grouped amino acid composition, C/T/D composition and sequence-order-coupling number, while the features for aptamers are extracted from nucleotide composition, pseudo-nucleotide composition (PseKNC) and normalized Moreau-Broto autocorrelation coefficient. On the basis of these feature sets and balanced the samples with SMOTE algorithm, we validate the performance of PPAI by the independent test set. The results demonstrate that the Area Under Curve (AUC) is 0.907 for prediction of aptamer, while the AUC reaches 0.871 for prediction of protein-aptamer interactions. CONCLUSION: These results indicate that PPAI can query aptamers and proteins, predict aptamers and predict protein-aptamer interactions in batch mode precisely and efficiently, which would be a novel bioinformatics tool for the research of protein-aptamer interactions. PPAI web-server is freely available at http://39.96.85.9/PPAI.

Potential biomarkers of acute myocardial infarction based on weighted gene co-expression network analysis.

BACKGROUND: Acute myocardial infarction (AMI) is the common cause of mortality in developed countries. The feasibility of whole-genome gene expression analysis to identify outcome-related genes and dysregulated pathways remains unknown. Molecular marker such as BNP, CRP and other serum inflammatory markers have got the notice at this point. However, these biomarkers exhibit elevated levels in patients with thyroid disease, renal failure and congestive heart failure. In this study, three groups of microarray data sets (GES66360, GSE48060, GSE29532) were collected from GEO, a total of 99, 52 and 55 samples, respectively. Weighted gene co-expression network analysis (WGCNA) was performed to obtain a classifier which composed of related genes that best characterize the AMI. RESULTS: Here, this study obtained three groups of microarray data sets (GES66360, GSE48060, GSE29532) on AMI blood samples, a total of 99, 52 and 24 samples, respectively. In all, 4672 genes, 3185 genes, 3660 genes were identified in GSE66360, GSE48060, GSE60993 modules, respectively. We preformed WGCNA, GO and KEGG pathway enrichment analysis on these three data sets, finding function enrichment of the differential expression gene on inflammation and immune response. Transcriptome analysis were performed in AMI patients at four time points compared to CAD patients with no history of MI, to determine gene expression profiles and their possible changes during the recovery from myocardial infarction. CONCLUSIONS: The results suggested that three overlapping genes (FGFBP2, GFOD1 and MLC1) between two modules could be a potential use of gene biomarkers for the diagnose of AMI.

Improved L0 Gradient Minimization with L1 Fidelity for Image Smoothing.

Edge-preserving image smoothing is one of the fundamental tasks in the field of computer graphics and computer vision. Recently, L0 gradient minimization (LGM) has been proposed for this purpose. In contrast to the total variation (TV) model which employs the L1 norm of the image gradient, the LGM model adopts the L0 norm and yields much better results for the piecewise constant image. However, as an improvement of the total variation (TV) model, the LGM model also suffers, even more seriously, from the staircasing effect and is not robust to noise. In order to overcome these drawbacks, in this paper, we propose an improvement of the LGM model by prefiltering the image gradient and employing the L1 fidelity. The proposed improved LGM (ILGM) behaves robustly to noise and overcomes the staircasing artifact effectively. Experimental results show that the ILGM is promising as compared with the existing methods.

[Effect of intravenous drip infusion of cyclophosphamide with high-dose Astragalus injection in treating lupus nephritis].

OBJECTIVE: To observe the effect of high-dose Astragalus injection and cyclophosphamide (CTX) on infection, urine protein and immune function of the patients with lupus nephritis. METHODS: Forty-three patients diagnosed as systemic lupus erythematosus (SLE) complicated by kidney damage and qi-deficiency syndrome were randomly divided into trial group (n=23) and control group (n=20). Patients in both groups were treated for 3 months. Intravenous drip infusion of 0.8 g CTX was administered to all patients once a month, while intravenous drip infusion of 20 ml Astragalus injection was only administered to patients in the trial group every day for 12 days in each month. RESULTS: The decrease of active clinical symptom score after the treatment in the trial group was greater than that in the control group (P<0.05). The infection rates of the trial group and the control group were 4.35% and 25% respectively. The decrease of 24-hour urine protein and CD8, and the increase of red blood cell count and serum albumin in the trial group were greater than those in the control group, and there were significant differences between the two groups (P<0.05). White blood cell count in the trial group was decreased less than that in the control group after the treatment (P<0.05). CONCLUSION: High-dose Astragalus injection used together with CTX is more effective than CTX alone in decreasing infection rate and urine protein and improving immune function for patients with lupus nephritis.