SubGE-DDI: A new prediction model for drug-drug interaction established through biomedical texts and drug-pairs knowledge subgraph enhancement.

Biomedical texts provide important data for investigating drug-drug interactions (DDIs) in the field of pharmacovigilance. Although researchers have attempted to investigate DDIs from biomedical texts and predict unknown DDIs, the lack of accurate manual annotations significantly hinders the performance of machine learning algorithms. In this study, a new DDI prediction framework, Subgraph Enhance model, was developed for DDI (SubGE-DDI) to improve the performance of machine learning algorithms. This model uses drug pairs knowledge subgraph information to achieve large-scale plain text prediction without many annotations. This model treats DDI prediction as a multi-class classification problem and predicts the specific DDI type for each drug pair (e.g. Mechanism, Effect, Advise, Interact and Negative). The drug pairs knowledge subgraph was derived from a huge drug knowledge graph containing various public datasets, such as DrugBank, TwoSIDES, OffSIDES, DrugCentral, EntrezeGene, SMPDB (The Small Molecule Pathway Database), CTD (The Comparative Toxicogenomics Database) and SIDER. The SubGE-DDI was evaluated from the public dataset (SemEval-2013 Task 9 dataset) and then compared with other state-of-the-art baselines. SubGE-DDI achieves 83.91% micro F1 score and 84.75% macro F1 score in the test dataset, outperforming the other state-of-the-art baselines. These findings show that the proposed drug pairs knowledge subgraph-assisted model can effectively improve the prediction performance of DDIs from biomedical texts.

The benefits and risks of menopause hormone therapy for the cardiovascular system in postmenopausal women: a systematic review and meta-analysis.

BACKGROUND: Menopause hormone therapy (MHT), as an effective method to alleviate the menopause-related symptoms of women, its benefits, risks, and potential influencing factors for the cardiovascular system of postmenopausal women are not very clear. OBJECTIVES: To evaluate cardiovascular benefits and risks of MHT in postmenopausal women, and analyze the underlying factors that affect both. SEARCH STRATEGY: The EMBASE, MEDLINE, and CENTRAL databases were searched from 1975 to July 2022. SELECTION CRITERIA: Randomized Clinical Trials (RCTs) that met pre-specified inclusion criteria were included. DATA COLLECTION AND ANALYSIS: Two reviewers extracted data independently. A meta-analysis of random effects was used to analyze data. MAIN RESULTS: This systematic review identified 33 RCTs using MHT involving 44,639 postmenopausal women with a mean age of 60.3 (range 48 to 72 years). There was no significant difference between MHT and placebo (or no treatment) in all-cause death (RR = 0.96, 95%CI 0.85 to 1.09, I2 = 14%) and cardiovascular events (RR = 0.97, 95%CI 0.82 to 1.14, I2 = 38%) in the overall population of postmenopausal women. However, MHT would increase the risk of stroke (RR = 1.23, 95%CI 1.08 to 1.41,I2 = 0%) and venous thromboembolism (RR = 1.86, 95%CI 1.39 to 2.50, I2 = 24%). Compared with placebo, MHT could improve flow-mediated arterial dilation (FMD) (SMD = 1.46, 95%CI 0.86 to 2.07, I2 = 90%), but it did not improve nitroglycerin-mediated arterial dilation (NMD) (SMD = 0.27, 95%CI - 0.08 to 0.62, I2 = 76%). Compared with women started MHT more than 10 years after menopause, women started MHT within 10 years after menopause had lower frequency of all-cause death (P = 0.02) and cardiovascular events (P = 0.002), and more significant improvement in FMD (P = 0.0003). Compared to mono-estrogen therapy, the combination therapy of estrogen and progesterone would not alter the outcomes of endpoint event. (all-cause death P = 0.52, cardiovascular events P = 0.90, stroke P = 0.85, venous thromboembolism P = 0.33, FMD P = 0.46, NMD P = 0.27). CONCLUSIONS: MHT improves flow-mediated arterial dilation (FMD) but fails to lower the risk of all-cause death and cardiovascular events, and increases the risk of stroke and venous thrombosis in postmenopausal women. Early acceptance of MHT not only reduces the risk of all-cause death and cardiovascular events but also further improves FMD, although the risk of stroke and venous thrombosis is not reduced. There is no difference in the outcome of cardiovascular system endpoints between mono-estrogen therapy and combination therapy of estrogen and progesterone.

Ciprofol suppresses proliferation, invasion and migration of human pancreatic cancer cells.

Pancreatic cancer (PC) is heterogeneous cancer having a high death rate and poor prognosis. The perioperative variables, such as anesthetics, may affect the cancer progression. Ciprofol is an intravenous anesthetic widely used recently. We aimed to explore the influence of ciprofol on PC and investigate its possible pathway. The proliferation, migration and invasion roles and apoptosis of ciprofol in human PC cells were examined using methylthiazolyldiphenyl-tetrazolium bromide, trans well and flow cytometery analysis. Then the putative targeted genes were examined using RNA-sequencing (RNA-seq) analysis. When differentially expressed genes (DEGs) were found, a protein-protein interaction network and pathway analyses were made. Moreover, MMP1 gene expression was confirmed in PC cells using quantitative real-time PCR. PANC-1 cells of PC were significantly suppressed with ciprofol in a dose-dependent and time-dependent way, and 20µg/mL ciprofol significantly suppressed tumor cell aggressiveness. Additionally, the RNA-seq analysis demonstrated that ciprofol controls the expression of 929 DEGs. 5 of 20 hub genes with increased connection were selected. Survival analysis demonstrated that MMP1 may be involved in the carcinogenesis and establishment of PC, reflecting the possible roles associated with ciprofol. Moreover, one target miRNA (hsa-miR-330-5p) of MMP1 was identified.

Biological Roles and Pathogenic Mechanisms of LncRNA MIR4435-2HG in Cancer: A Comprehensive Review.

The long non-coding RNA MIR4435-2HG has been confirmed to play a crucial regulatory role in various types of tumors. As a novel type of non-coding RNA, MIR4435-2HG plays a key role in regulating the expression of tumor-related genes, interfering with cellular signaling pathways, and affecting tumor immune evasion. Its unique structure allows it to regulate the expression of various tumor-related genes through different pathways, participating in the regulation of tumor signaling pathways, such as regulating the expression of oncogenes and tumor suppressor genes, influencing the biological behaviors of proliferation, metastasis, and apoptosis in tumors. Numerous studies have found a high expression of MIR4435-2HG in various tumor tissues, closely related to the clinical pathological characteristics of tumors, such as staging, lymph node metastasis and prognosis. Some studies have discovered that MIR4435-2HG can regulate the sensitivity of tumor cells to chemotherapy drugs, affecting tumor cell drug resistance. This provides new insights into overcoming tumor drug resistance by regulating MIR4435-2HG. Therefore, studying its molecular mechanisms, expression regulation, and its relationship with the clinical features of tumors is of great significance for revealing the mechanisms of tumor occurrence and developing new therapeutic targets.

MicroRNA-376b-3p Promotes Porcine Reproductive and Respiratory Syndrome Virus Replication by Targeting Viral Restriction Factor TRIM22.

Porcine reproductive and respiratory syndrome virus (PRRSV) is a major economically significant pathogen and has evolved several strategies to evade host antiviral response and provide favorable conditions for survival. In the present study, we demonstrated that a host microRNA, miR-376b-3p, was upregulated by PRRSV infection through the viral components, nsp4 and nsp11, and that miR-376b-3p can directly target tripartite motif-containing 22 (TRIM22) to impair its anti-PRRSV activity, thus facilitating the replication of PRRSV. Meanwhile, we found that TRIM22 induced degradation of the nucleocapsid protein (N) of PRRSV by interacting with N protein to inhibit PRRSV replication, and further study indicated that TRIM22 could enhance the activation of the lysosomal pathway by interacting with LC3 to induce lysosomal degradation of N protein. In conclusion, PRRSV increased miR-376b-3p expression and hijacked the host miR-376b-3p to promote PRRSV replication by impairing the antiviral effect of TRIM22. Therefore, our finding outlines a novel strategy of immune evasion exerted by PRRSV, which is helpful for better understanding the pathogenesis of PRRSV. IMPORTANCE Porcine reproductive and respiratory syndrome virus (PRRSV) causes enormous economic losses each year in the swine industry worldwide. MicroRNAs (miRNAs) play important roles during viral infections via modulating the expression of viral or host genes at the posttranscriptional level. TRIM22 has recently been identified as a key restriction factor that inhibited the replication of a number of human viruses, such as HIV, encephalomyocarditis virus (ECMV), hepatitis C virus (HCV), HBV, influenza A virus (IAV), and respiratory syncytial virus (RSV). In this study, we showed that host miR-376b-3p could be upregulated by PRRSV and functioned to impair the anti-PRRSV role of TRIM22 to facilitate PRRSV replication. Meanwhile, we found that TRIM22 inhibited the replication of PRRSV by interacting with viral N protein and accelerating its degradation through the lysosomal pathway. Collectively, the findings reveal a novel mechanism that PRRSV used to exploit the host miR-376b-3p to evade antiviral responses and provide new insight into the study of virus-host interactions.

Research on calibration of a binocular stereo-vision imaging system based on the artificial neural network.

Camera calibration is a key problem for 3D reconstruction in computer vision. Existing calibration methods, such as traditional, active, and self-calibration, all need to solve the internal and external parameters of the imaging system to clarify the image-object mapping relationship. The artificial neural network, which is based on connectionist architecture, provides a novel idea for the calibration of nonlinear mapping vision systems. It can learn the image-object mapping relationship from some sample points without considering too many uncertain factors in the middle. This paper discusses the learning ability. A binocular stereo-vision mapping model is used as the learning model to explore the ability of image-object mapping for artificial neural networks. This paper constructs sample libraries by pixel and world coordinates of checkerboard corners, builds the artificial neural network, and, through the training samples and test samples prediction, verifies the learning performance of the network. Furthermore, by the laser scanning binocular vision device constructed in the authors' laboratory and trained-well network, the 3D point cloud reconstruction of a physical target is performed. The experimental results show that the artificial neural network can learn the image-object mapping relationship well and more effectively avoid the impact of lens distortion and achieve more accurate nonlinear mapping at the edge of the image. When the X and Y coordinates are in the range of 100 mm and the Z coordinates are in the range of a 1000 mm, the absolute error rarely exceeds 2.5 mm, and the relative error is in the level of 10-3; for 1000 mm distance measurement, the standard deviation does not exceed 1.5 mm. Network parameter selection experiments show that, for image-object mapping, a three-layer network and increasing the number of hidden layer's nodes can improve the training time more significantly.

High-precision rotation angle measurement method based on polarization self-mixing interference.

In this study, a high-precision rotation angle measurement method based on polarization self-mixing interference (SMI) is proposed. The higher signal-to-noise ratio SMI signal can be obtained by the differential processing of two polarized SMI signals with opposite phases. In order to reduce the influence of the speckle effect, the envelope signal is used to normalize the SMI signal. The fringe subdivision method is used to improve the accuracy of the rotation angle measurement. The experimental results show that the error of the rotation angle measurement is within ±0.5%, and the measurement range can reach up to 20°.

Susceptibility to mice and potential evolutionary characteristics of porcine deltacoronavirus.

Porcine deltacoronavirus (PDCoV) is a novel coronavirus that causes diarrhea in suckling piglets and has the potential for cross-species transmission, posing a threat to animal and human health. However, the susceptibility profile of different species of mice to PDCoV infection and its evolutionary characteristics are still unclear. In the current study, we found that BALB/c and Kunming mice are susceptible to PDCoV. Our results showed that there were obvious lesions in intestinal and lung tissues from the infected mice. PDCoV RNAs were detected in the lung, kidney, and intestinal tissues from the infected mice of both strains, and there existed wider tissue tropism in the PDCoV-infected BALB/c mice. The RNA and protein levels of aminopeptidase N from mice were relatively high in the kidney and intestinal tissues and obviously increased after PDCoV infection. The viral-specific IgG and neutralizing antibodies against PDCoV were detected in the serum of infected mice. An interesting finding was that two key amino acid mutations, D138H and Q641K, in the S protein were identified in the PDCoV-infected mice. The essential roles of these two mutations for PDCoV-adaptive evolution were confirmed by cryo-electron microscope structure model analysis. The evolutionary characteristics of PDCoV among Deltacoronaviruses (δ-CoVs) were further analyzed. δ-CoVs from multiple mammals are closely related based on the phylogenetic analysis. The codon usage analysis demonstrated that similar codon usage patterns were used by most of the mammalian δ-CoVs at the global codon, synonymous codon, and amino acid usage levels. These results may provide more insights into the evolution, host ranges, and cross-species potential of PDCoV.

Automated prediction of early spontaneous miscarriage based on the analyzing ultrasonographic gestational sac imaging by the convolutional neural network: a case-control and cohort study.

BACKGROUND: It is challenging to predict the outcome of the pregnancy when fetal heart activity is detected in early pregnancy. However, an accurate prediction is of importance for obstetricians as it helps to provide appropriate consultancy and determine the frequency of ultrasound examinations. The purpose of this study was to investigate the role of the convolutional neural network (CNN) in the prediction of spontaneous miscarriage risk through the analysis of early ultrasound gestational sac images. METHODS: A total of 2196 ultrasound images from 1098 women with early singleton pregnancies of gestational age between 6 and 8 weeks were used for training a CNN for the prediction of the miscarriage in the retrospective study. The patients who had positive fetal cardiac activity on their first ultrasound but then experienced a miscarriage were enrolled. The control group was randomly selected in the same database from the fetuses confirmed to be normal during follow-up. Diagnostic performance of the algorithm was validated and tested in two separate test sets of 136 patients with 272 images, respectively. Performance in prediction of the miscarriage was compared between the CNN and the manual measurement of ultrasound characteristics in the prospective study. RESULTS: The accuracy of the predictive model was 80.32% and 78.1% in the retrospective and prospective study, respectively. The area under the receiver operating characteristic curve (AUC) for classification was 0.857 (95% confidence interval [CI], 0.793-0.922) in the retrospective study and 0.885 (95%CI, 0.846-0.925) in the prospective study, respectively. Correspondingly, the predictive power of the CNN was higher compared with manual ultrasound characteristics, for which the AUCs of the crown-rump length combined with fetal heart rate was 0.687 (95%CI, 0.587-0.775). CONCLUSIONS: The CNN model showed high accuracy for predicting miscarriage through the analysis of early pregnancy ultrasound images and achieved better performance than that of manual measurement.

Study on the Construction of a Time-Space Four-Dimensional Combined Imaging Model and Moving Target Location Prediction Model.

Time-space four-dimensional motion target localization is a fundamental and challenging task in the field of intelligent driving, and an important part of achieving the upgrade in existing target localization technologies. In order to solve the problem of the lack of localization of moving targets in a spatio-temporal four-dimensional environment in the existing spatio-temporal data model, this paper proposes an optical imaging model in the four-dimensional time-space system and a mathematical model of the object-image point mapping relationship in the four-dimensional time-space system based on the central perspective projection model, combined with the one-dimensional "time" and three-dimensional "space". After adding the temporal dimension, the imaging system parameters are extended. In order to solve the nonlinear mapping problem of complex systems, this paper proposes to construct a time-space four-dimensional object-image mapping relationship model based on a BP artificial neural network and demonstrates the feasibility of the joint time-space four-dimensional imaging model theory. In addition, indoor time-space four-dimensional localization prediction experiments verify the performance of the model in this paper. The maximum relative error rates of the predicted motion depth values, time values, and velocity values of this localization method compared with the real values do not exceed 0.23%, 2.03%, and 1.51%, respectively.

APB-13 improves the adverse outcomes caused by TGEV infection by correcting the intestinal microbial disorders in piglets.

Porcine transmissible gastroenteritis virus (TGEV) is an enteric coronavirus that has caused high morbidity and mortality of piglets worldwide. Previous studies have shown that the TGEV can lead to severe diarrhoea, vomiting and dehydration in 2-week-old piglets and weaned piglets, resulting in a large number of piglet deaths. Antimicrobial peptides have broad-spectrum antimicrobial activity and a strong killing effect on bacteria, especially on the drug-resistant pathogenic bacteria, and it has attracted broad concern. However, there are very few reports on the effect of APB-13 (an antimicrobial peptide) on the intestinal microbes of piglets infected with TGEV. In this study, 16S rRNA gene sequencing was used to compare the microbial phylum and the genus of piglet's enteric microorganism in different experimental groups, and to predict the metabolic function of the microbial flora. At the same time, the apparent digestibility of nutrients, digestive enzyme activity, daily weight gain and survival rate were also measured. TGEV infection could cause the imbalance of intestinal microbes in piglets, and increase of the relative abundance of Proteobacteria, and decrease of the relative abundance of Firmicutes, Bacteroidetes and Actinobacteri. With the addition of APB-13, this problem can be alleviated, which can reduce the relative abundance of Proteobacteria and improve the balance of intestinal microorganisms. At the microbial genus level, after adding APB-13, the relative abundance of Catenibacterium, Enterobacter and Streptococcus in the intestinal tract of piglets infected with TGEV showed significant decrease, while the relative abundance of Lactobacillus and Ruminococcus increased. Finally, we found that APB-13 can significantly increase the activity of digestive enzyme in the intestinal tract of piglet, thereby improving the apparent digestibility of nutrients and the growth performance of piglets. This study demonstrates that APB-13 can alleviate the adverse outcomes caused by TGEV infection by correcting the intestinal microbial disorders.

Protective role of exosomes derived from regulatory T cells against inflammation and apoptosis of BV-2 microglia under oxygen-glucose deprivation/reperfusion challenge.

Regulatory T cells (Tregs) are found to participate in the pathogenesis of cerebral ischemic stroke. Exosomes derived from Tregs (Treg-Exos) were found to mediate the mechanism of Tregs' roles under various physiological and pathological conditions. But the roles of Treg-Exos in cerebral ischemic stroke are still unclear. Here, we explored the protective effects of Treg-Exos against microglial injury in response to oxygen-glucose deprivation/reperfusion (OGD/R) exposure. The results showed that Tregs-Exos relieved OGD/R-caused increases in LDH release and caspase-3 activity in BV-2 cells. The decreased cell viability and increased percentage of TUNEL-positive cells in OGD/R-exposed BV-2 cells were attenuated by Tregs-Exos treatment. Tregs-Exos also suppressed OGD/R-induced increase in production of tumor necrosis factor (TNF)-α, interleukin (IL)-1ß, and IL-6 in BV-2 microglia. Furthermore, Tregs-Exos induced the expression levels of phosphorylated phosphatidylinositol-3-kinase (p-PI3K) and phosphorylated protein kinase B (p-Akt) in BV-2 microglia under the challenge of OGD/R. Inhibition of the PI3K/Akt signaling by LY294002 partly reversed the effects of Tregs-Exos on cell apoptosis and inflammation in OGD/R-exposed BV-2 microglia. These results indicated that Tregs-Exos exerted protective effects against the OGD/R-caused injury of BV-2 microglia by activating the PI3K/Akt signaling.

Expression of porcine interferon-α and its bioactivity analysis in vitro and in vivo.

Interferon α (IFN-α) plays a crucial role in the host's immune response. In this study, the amino acid sequence of porcine interferon α (PoIFN-α) was analyzed. Seven substitutions, S38F, H40Q, F43L, N78D, Y86C, S151A, and R156T, were mutated and obtained by aligning the sequences of PoIFN-α subtypes. The PoIFN-α mutants were designed, expressed, and purified in E. coli. The antiviral activities of these PoIFN-αs were measured in Vero and swine testis cells against vesicular stomatitis virus (VSV). Their inhibitory abilities on pseudorabies virus (PRV) were also examined. Commercial PoIFN-α was used as a control. We found the ideal inducer concentration of isopropyl ß-D-thiogalactoside was 1 mM, and the best time-point for induction was 8 h. The PoIFN-α mutant named PoIFN-α-156s had the highest antiviral activity, which was about 200-fold more than that of PoIFN-α. PoIFN-α-156s could inhibit VSV and PRV replication in a dose-dependent manner in vitro. The half-life of PoIFN-α-156s was longer than that of PoIFN-α in mice, and the effective antiviral action was higher than PoIFN-α. Animal experiments showed that PoIFN-α-156s could decrease the viral load after infection with VSV. Overall, these results suggest that recombinant PoIFN-α-156s has the ability of antivirus, and is feasible for veterinary clinical applications and fundamental research.

FOXF1 ameliorates angiotensin II-induced cardiac fibrosis in cardiac fibroblasts through inhibiting the TGF-ß1/Smad3 signaling pathway.

Cardiac fibrosis is a pathological feature common to a variety of heart diseases such as myocardial infarction, arrhythmias, cardiomyopathies and heart failure. The molecular mechanism underlying the cardiac fibrosis is still unclear. Forkhead box F1 (FOXF1), a member of the forkhead transcription factor superfamily, plays critical roles in the development of hepatic fibrosis. However, whether FOXF1 is involved in the pathogenesis of cardiac fibrosis remains to be elucidated. The present study aimed to investigate the role of FOXF1 and its mechanisms in regulating cardiac fibrosis. The results demonstrated that FOXF1 was downregulated in Ang II-induced CFs. Overexpression of FOXF1 inhibited angiotensin II (Ang II)-induced proliferation, migration and oxidative stress in cardiac fibroblasts (CFs). Overexpression of FOXF1 also reduced the expression of alpha-smooth muscle actin (a-SMA) in Ang II-induced CFs, suggesting that overexpression of FOXF1 prevented the differentiation of CFs to myofibroblasts. Furthermore, the production of extracellular matrix (ECM) components including type I collagen and fibronectin were reduced by overexpression of FOXF1 in Ang II-induced CFs. Furthermore, overexpression of FOXF1 prevented Ang II-induced activation of transforming growth factor beta 1 (TGF-ß1)/Smad3 pathway in CFs. In conclusion, the results of the present study indicated that FOXF1 acted as a key regulator of pathological cardiac fibrosis, and overexpression of FOXF1 ameliorated cardiac fibrosis by inhabiting the TGF-ß1/Smad3 signaling pathway. These results indicated that FOXF1 may be a novel target for attenuating cardiac fibrosis.

Predicting Unnecessary Nodule Biopsies from a Small, Unbalanced, and Pathologically Proven Dataset by Transfer Learning.

This study explores an automatic diagnosis method to predict unnecessary nodule biopsy from a small, unbalanced, and pathologically proven database. The automatic diagnosis method is based on a convolutional neural network (CNN) model. Because of the small and unbalanced samples, the presented method aims to improve the transfer learning capability via the VGG16 architecture and optimize the related transfer learning parameters. For comparison purpose, a traditional machine learning method is implemented, which extracts the texture features and classifies the features by support vector machine (SVM). The database includes 68 biopsied nodules, 16 are pathologically proven benign and the remaining 52 are malignant. To consider the volumetric data by the CNN model, each image slice from each nodule volume is selected randomly until all image slices of each nodule are utilized. The leave-one-out and 10-folder cross validations are applied to train and test the randomly selected 68 image slices (one image slice from one nodule) in each experiment, respectively. The averages over all the experimental outcomes are the final results. The experiments revealed that the features from both the medical and the natural images share the similarity of focusing on simpler and less-abstract objects, leading to the conclusion that not the more the transfer convolutional layers, the better the classification results. Transfer learning from other larger datasets can supply additional information to small and unbalanced datasets to improve the classification performance. The presented method has shown the potential to adapt CNN architecture to improve the prediction of unnecessary nodule biopsy from small, unbalanced, and pathologically proven volumetric dataset.

Computed tomography-based predictive nomogram for differentiating primary progressive pulmonary tuberculosis from community-acquired pneumonia in children.

BACKGROUND: To investigate the value of predictive nomogram in optimizing computed tomography (CT)-based differential diagnosis of primary progressive pulmonary tuberculosis (TB) from community-acquired pneumonia (CAP) in children. METHODS: This retrospective study included 53 patients with clinically confirmed pulmonary TB and 62 patients with CAP. Patients were grouped at random according to a 3:1 ratio (primary cohort n = 86, validation cohort n = 29). A total of 970 radiomic features were extracted from CT images and key features were screened out to build radiomic signatures using the least absolute shrinkage and selection operator algorithm. A predictive nomogram was developed based on the signatures and clinical factors, and its performance was assessed by the receiver operating characteristic curve, calibration curve, and decision curve analysis. RESULTS: Initially, 5 and 6 key features were selected to establish a radiomic signature from the pulmonary consolidation region (RS1) and a signature from lymph node region (RS2), respectively. A predictive nomogram was built combining RS1, RS2, and a clinical factor (duration of fever). Its classification performance (AUC = 0.971, 95% confidence interval [CI]: 0.912-1) was better than the senior radiologist's clinical judgment (AUC = 0.791, 95% CI: 0.636-0.946), the clinical factor (AUC = 0.832, 95% CI: 0.677-0.987), and the combination of RS1 and RS2 (AUC = 0.957, 95% CI: 0.889-1). The calibration curves indicated a good consistency of the nomogram. Decision curve analysis demonstrated that the nomogram was useful in clinical settings. CONCLUSIONS: A CT-based predictive nomogram was proposed and could be conveniently used to differentiate pulmonary TB from CAP in children.

Algorithm Design for Edge Detection of High-Speed Moving Target Image under Noisy Environment.

For some measurement and detection applications based on video (sequence images), if the exposure time of camera is not suitable with the motion speed of the photographed target, fuzzy edges will be produced in the image, and some poor lighting condition will aggravate this edge blur phenomena. Especially, the existence of noise in industrial field environment makes the extraction of fuzzy edges become a more difficult problem when analyzing the posture of a high-speed moving target. Because noise and edge are always both the kind of high-frequency information, it is difficult to make trade-offs only by frequency bands. In this paper, a noise-tolerant edge detection method based on the correlation relationship between layers of wavelet transform coefficients is proposed. The goal of the paper is not to recover a clean image from a noisy observation, but to make a trade-off judgment for noise and edge signal directly according to the characteristics of wavelet transform coefficients, to realize the extraction of edge information from a noisy image directly. According to the wavelet coefficients tree and the Lipschitz exponent property of noise, the idea of neural network activation function is adopted to design the activation judgment method of wavelet coefficients. Then the significant wavelet coefficients can be retained. At the same time, the non-significant coefficients were removed according to the method of judgment of isolated coefficients. On the other hand, based on the design of Daubechies orthogonal compactly-supported wavelet filter, rational coefficients wavelet filters can be designed by increasing free variables. By reducing the vanishing moments of wavelet filters, more high-frequency information can be retained in the wavelet transform fields, which is benefit to the application of edge detection. For a noisy image of high-speed moving targets with fuzzy edges, by using the length 8-4 rational coefficients biorthogonal wavelet filters and the algorithm proposed in this paper, edge information could be detected clearly. Results of multiple groups of comparative experiments have shown that the edge detection effect of the proposed algorithm in this paper has the obvious superiority.

CNN models discriminating between pulmonary micro-nodules and non-nodules from CT images.

BACKGROUND: Early and automatic detection of pulmonary nodules from CT lung screening is the prerequisite for precise management of lung cancer. However, a large number of false positives appear in order to increase the sensitivity, especially for detecting micro-nodules (diameter < 3 mm), which increases the radiologists' workload and causes unnecessary anxiety for the patients. To decrease the false positive rate, we propose to use CNN models to discriminate between pulmonary micro-nodules and non-nodules from CT image patches. METHODS: A total of 13,179 micro-nodules and 21,315 non-nodules marked by radiologists are extracted with three different patch sizes (16 × 16, 32 × 32 and 64 × 64) from LIDC/IDRI database and used in the experiments. Three CNN models with different depths (1, 2 or 4 convolutional layers) are designed; their performances are evaluated by the fivefold cross-validation in term of the accuracy, area under the curve (AUC), F-score and sensitivity. The network parameters are also optimized. RESULTS: It is found that the performance of the CNN models is greatly dependent on the patches size and the number of convolutional layers. The CNN model with two convolutional layers presented the best performance in case of 32 × 32 patches size, achieving an accuracy of 88.28%, an AUC of 0.87, a F-score of 83.45% and a sensitivity of 83.82%. CONCLUSIONS: The CNN models with appropriate depth and size of image patches can effectively discriminate between pulmonary micro-nodules and non-nodules, and reduce the false positives and help manage lung cancer precisely.

A hybrid CNN feature model for pulmonary nodule malignancy risk differentiation.

The malignancy risk differentiation of pulmonary nodule is one of the most challenge tasks of computer-aided diagnosis (CADx). Most recently reported CADx methods or schemes based on texture and shape estimation have shown relatively satisfactory on differentiating the risk level of malignancy among the nodules detected in lung cancer screening. However, the existing CADx schemes tend to detect and analyze characteristics of pulmonary nodules from a statistical perspective according to local features only. Enlightened by the currently prevailing learning ability of convolutional neural network (CNN), which simulates human neural network for target recognition and our previously research on texture features, we present a hybrid model that takes into consideration of both global and local features for pulmonary nodule differentiation using the largest public database founded by the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). By comparing three types of CNN models in which two of them were newly proposed by us, we observed that the multi-channel CNN model yielded the best discrimination in capacity of differentiating malignancy risk of the nodules based on the projection of distributions of extracted features. Moreover, CADx scheme using the new multi-channel CNN model outperformed our previously developed CADx scheme using the 3D texture feature analysis method, which increased the computed area under a receiver operating characteristic curve (AUC) from 0.9441 to 0.9702.

Texture feature analysis for computer-aided diagnosis on pulmonary nodules.

Differentiation of malignant and benign pulmonary nodules is of paramount clinical importance. Texture features of pulmonary nodules in CT images reflect a powerful character of the malignancy in addition to the geometry-related measures. This study first compared three well-known types of two-dimensional (2D) texture features (Haralick, Gabor, and local binary patterns or local binary pattern features) on CADx of lung nodules using the largest public database founded by Lung Image Database Consortium and Image Database Resource Initiative and then investigated extension from 2D to three-dimensional (3D) space. Quantitative comparison measures were made by the well-established support vector machine (SVM) classifier, the area under the receiver operating characteristic curves (AUC) and the p values from hypothesis t tests. While the three feature types showed about 90% differentiation rate, the Haralick features achieved the highest AUC value of 92.70% at an adequate image slice thickness, where a thinner or thicker thickness will deteriorate the performance due to excessive image noise or loss of axial details. Gain was observed when calculating 2D features on all image slices as compared to the single largest slice. The 3D extension revealed potential gain when an optimal number of directions can be found. All the observations from this systematic investigation study on the three feature types can lead to the conclusions that the Haralick feature type is a better choice, the use of the full 3D data is beneficial, and an adequate tradeoff between image thickness and noise is desired for an optimal CADx performance. These conclusions provide a guideline for further research on lung nodule differentiation using CT imaging.