Search

Existing state-of-the-art methods for salient object detection mainly achieve significant progress by integrating multi-level features. However, most of them simply resize the multi-level features to the same spatial resolution and aggregate them by channel-wise concatenation or element-wise addition. Thus, they are limited to integrating features of adjacent layers due to large discrepancy between these multi-level features. Besides, most existing methods adopt the U-shape architecture where high-level semantic information is gradually transmitted to shallower layers to suppress the background noises. Nonetheless, little attention has been paid to refine high-level features. In this paper, we propose the BINet to solve the above problems. Specifically, we design the feature interaction module (FIM) to exploit complementary information between multiple features, which is then utilized to simultaneously refine these features. Besides, we propose the cascaded bidirectional interaction decoder (CBID) to further refine multi-level features iteratively. Our CBID progressively refines multi-level features with feedback mechanisms and employs a channel attention module (CAM) to assign larger weights to channels showing higher response to salient regions. Equipped with these modules, our BINet is capable of segmenting salient regions accurately and quickly. Experimental results on six widely used benchmark datasets validate that our BINet outperforms 16 other state-of-the-art methods in terms of 7 standard evaluation metrics. Our code will be publicly available at https://github.com/clelouch/BINet .

Recently, convolutional neural networks have improved the results of salient object detection by a significant margin. Most existing methods focus on aggregating multi-level features but pay little attention to the differences between their spatial resolution. Besides, the widely used binary cross entropy loss treats all pixels equally and neglects the fact that pixels near the salient boundaries are prone to being misclassified. To solve these problems, we propose a novel network named BPFINet to aggregate low-level detail features, high-level semantic information, and global information progressively by using the U-shape Feature Integration Modules (UFIMs). Moreover, a U-shape Self-Refinement Module (USRM) is proposed to generate multi-scale representation from the intra-layer features and fuse them progressively to generate features robust to scale variation of salient objects. Besides, a Channel Compression Module (CCM) is designed to reduce the channel number of certain features and enhance the features by leveraging channel-wise attention. Furthermore, an integrated loss is introduced to highlight pixels near the salient boundaries and solve the problem caused by the imbalance of foreground and background regions. Experimental results on six benchmark datasets prove that our BPFINet is competitive compared with 16 other state-of-the-art methods. The source code will be publicly available at https://github.com/clelouch/BPFINet .

Background There have been few literature reports on the use of perioperative parameters to predict the risk of albumin transfusion after spinal tuberculosis surgery based on the application of nomogram and propensity score matching (PSM) analysis. Objective The purpose was to predict the risk of albumin transfusion after spinal tuberculosis surgery based on a combination of PSM and nomogram. Methods The clinical data of the patients were collected in our hospital, including preoperative clinical data, preoperative laboratory tests, and postoperative clinical data. All data were divided into 2 groups, including the albumin transfusion group and the non–albumin transfusion group. The PSM analysis was used to adjust the baseline data of the 2 groups. The nomogram was further constructed. The practicability and predictive ability of the model were evaluated. Results A total of 494 cases were collected in this article; 102 pairs by PSM analysis were used to construct the nomogram. There were statistical differences in surgical approach, aspartate aminotransferase/alanine aminotransferase levels, drainage, and kyphosis by logistic analysis, and these parameters were included in the construction of the nomogram. The C-index of the prediction model was 0.734. The area under the curve was 0.73 and the net benefit was between 0.13 and 0.99. The calculated C-index was 0.71 by the internal verification method. Conclusions The PSM analysis had a good matching effect and the nomogram had a good predictive ability. Surgical approach, aspartate aminotransferase/alanine aminotransferase levels, drainage, and kyphosis might be predictors of albumin transfusion after spinal tuberculosis surgery.

Studies have found that both FibroScan (FS) and Gd-EOB-DTPA-enhanced T1 mapping magnetic resonance imaging (Gd-MRI) could assess liver fibrosis (LF) with high effectiveness. The aim of this study is to compare their accuracy in the quantitative evaluation of LF in patients with chronic hepatitis B (CHB), and to explore the diagnostic accuracy of their combination. 160 patients with CHB were included in this study. FS and Gd-MRI were performed within 3 months before the pathological LF staging, which was classified according to the Scheuer-Ludwig scale. The liver stiffness measurement (LSM) was obtained by FS. T1 mapping images of the liver before and 20 min after enhancement were obtained by Look-Locker Gd-MRI. There were 45, 35, 31 and 49 patients with stage S1, S2, S3 and S4 LF, respectively. LSM increased and the reduction rate of T1 relaxation time of 20 min (rrT120min%) decreased with the severity of LF. The area under curve (AUC) of LSM, rrT120min% and LSM + rrT120min% for the diagnosis of ≥ S2 LF were 0.892, 0.811 and 0.900, respectively. The AUC for ≥ S3 LF was 0.883, 0.838 and 0.899, respectively. The AUC for S4 LF was 0.882, 0.894 and 0.928, respectively. The diagnostic accuracy of FS is better than that of Gd-MRI in the evaluation of ≥ S2 stage LF. The combination of these two methods significantly improved the diagnostic efficiency in the evaluation of S4 stage LF.

Research on designing local feature descriptors has gradually shifted to deep learning. Different from other computer vision tasks, the biggest challenge for local descriptor learning lies with the formulation of loss functions. Existing methods solve the problem by leveraging Siamese loss or triplet loss and improve the performance of the learned descriptors by a significant margin. However, the widely used Siamese loss and triplet loss cannot fully utilize the context information. In this paper, we propose a novel loss function to introduce more context information to facilitate training. After incorporating the proposed loss function into training, our learned descriptor demonstrates state-of-the-art performance in patch verification, image matching and patch retrieval benchmarks. The pretrained model will be publicly available at https://github.com/clelouch/CANet.

IntroductionOsteosarcoma is among the most common orthopedic neoplasms, and currently, there are no adequate biomarkers to predict its prognosis. Therefore, the present study was aimed to identify the prognostic biomarkers for autophagy-and immune-related osteosarcoma using bioinformatics tools for guiding the clinical diagnosis and treatment of this disease.Materials and MethodsThe gene expression and clinical information data were downloaded from the Public database. The genes associated with autophagy were extracted, followed by the development of a logistic regression model for predicting the prognosis of osteosarcoma using univariate and multivariate COX regression analysis and LASSO regression analysis. The accuracy of the constructed model was verified through the ROC curves, calibration plots, and Nomogram plots. Next, immune cell typing was performed using CIBERSORT to analyze the expression of the immune cells in each sample. For the results obtained from the analysis, we used qRT-PCR validation in two strains of human osteosarcoma cells.ResultsThe screening process identified a total of three genes that fulfilled all the screening criteria. The survival curves of the constructed prognostic model revealed that patients with the high risk presented significantly lower survival than the patients with low risk. Finally, the immune cell component analysis revealed that all three genes were significantly associated with the immune cells. The expressions of TRIM68, PIKFYVE, and DYNLL2 were higher in the osteosarcoma cells compared to the control cells. Finally, we used human pathological tissue sections to validate the expression of the genes modeled in osteosarcoma and paracancerous tissue.ConclusionThe TRIM68, PIKFYVE, and DYNLL2 genes can be used as biomarkers for predicting the prognosis of osteosarcoma.

The current study is aimed at developing and validating a nomogram of the risk of failure of internal fixation devices in Chinese patients undergoing spinal internal fixation. We collected data from a total of 1139 patients admitted for spinal internal fixation surgery at the First Affiliated Hospital of Guangxi Medical University from May 2012 to February 2019. Of these, 1050 patients were included in the spinal internal fixation group and 89 patients in the spinal internal fixation device failure group. Patients were divided into training and validation tests. The risk assessment of the failure of the spinal internal fixation device used 14 characteristics. In the training test, the feature selection of the failure model of the spinal internal fixation device was optimized using the least absolute shrinkage and selection operator (LASSO) regression model. Based on the characteristics selected in the LASSO regression model, multivariate logistic regression analysis was used for constructing the model. Identification, calibration, and clinical usefulness of predictive models were assessed using C-index, calibration curve, and decision curve analysis. A validation test was used to validate the constructed model. In the training test, the risk prediction nomogram included gender, age, presence or absence of scoliosis, and unilateral or bilateral fixation. The model demonstrated moderate predictive power with a C-index of 0.722 (95% confidence interval: 0.644–0.800) and the area under the curve (AUC) of 0.722. Decision curve analysis depicted that the failure risk nomogram was clinically useful when the probability threshold for internal fixation device failure was 3%. The C-index of the validation test was 0.761. This novel nomogram of failure risk for spinal instrumentation includes gender, age, presence or absence of scoliosis, and unilateral or bilateral fixation. It can be used for evaluating the risk of instrumentation failure in patients undergoing spinal instrumentation surgery.

The gut microbiota system plays a vital role in liver diseases. This study aimed to address the diversity of gut microbiota and its correlations with clinical parameters in healthy individuals, chronic liver disease (CLD), and hepatocellular carcinoma (HCC) patients. Fecal specimens of nine healthy individuals, 11 CLD, and 21 HCC were collected. The diversity of gut microbiota was examined by PCR and Illumina MiSeq sequencing and analyzed using 16S rRNA gene sequencing database. The correlations between gut microbiota and the clinical parameters of participants were also addressed. Compared to healthy individuals, Firmicutes at a phylum level decreased in CLD and HCC patients and Proteobacteria increased (p < 0.05). The composition of Blautia on a genus level in CLD and HCC patients significantly decreased compared to healthy controls (p < 0.05). Firmicutes composition was negatively associated with age and number of males (p < 0.05) and was positively associated with monocytes, high-density lipoprotein cholesterol (HDL-C), and estimated glomerular filtration rate (eGFR) levels (p < 0.05). At a genus level, Blautia composition was negatively associated with cirrhosis, age, and number of males (p < 0.01), while it was positively associated with red blood cells (RBCs), triglycerides, HDL-C, and lymphocyte levels (p < 0.05). Conclusively, there was a significant compositional difference in gut microbiota in CLD and HCC patients compared with healthy subjects. Firmicutes and Blautia in gut microbiota system lessened in CLD and HCC patients. Clinical biochemical parameters have an impact on the diversity of gut microbiota in liver diseases.

Background The aim of this study is to explore the use of preoperative imaging stability studies of adult lumbar spondylolisthesis and it's effects on intraoperative correction, postoperative observation, and clinical efficacy. Methods We retrospectively analyzed a total of 104 patients diagnosed with lumbar spondylolisthesis who underwent Posterior lumbar interbody fusion surgery between 2011 and 2014. The qualified patients were divided into two groups; group A (study/unstable group: 52 cases) and group B (control/stable group: 52 cases). Group A was further divided into group A1 (slip instability: 27 cases) and group A2 (angular instability: 25 cases). The preoperative lumbar sagittal plane translation distances and segmental angle of the preoperative lateral X-rays, hyperflexion X-rays, and hyperextension X-rays were measured and compared with their third-day postoperative lateral X-ray, and slip rate. The occurrences of intraoperative or postoperative complications, one-month postoperative follow-up data, including JOA, and VAS scores were access to evaluate the clinical efficacy of the treatment. Results Satisfactory postoperative radiographic correction was recorded in all groups. Better correction and correction was observed in group A1 patients and group B patients who used puller screws compared to those who used normal screws (P

This study was aimed to reveal the role of ferroptosis in tuberculosis infection. To elucidate the ferroptosis-related DEGs, GEO datasets associated with tuberculosis infection were downloaded. The two external validation GEO datasets were exploited for subsequent verification of the ferroptosis-related DEGs. We further evaluated the correlation among the ferroptosis-related DEGs, therapeutic effects, and drug resistance. Finally, we tried to reveal the engagement of the ferroptosis-related DEGs in bone destruction during TB infection. The present study identified SOCS1 as the only ferroptosis-related DEGs. Compared to the non-TB patients, up-regulation of SOCS1 was evident in the TB patients. After receiving standard anti-TB treatment, significant down-regulation of SOCS1 confirmed its acceptance as the marker for therapeutic efficacy. The involvement of SOCS1 has also been suggested in the regulation of the micro immune environment in TB. Furthermore, SOCS1 might play an important role in causing bone destruction during TB infection. FRGs-SOCS1 may be the key gene involved in the pathogenesis and progression of TB infection.

Background Tuberculosis (TB) is a global health problem that brings us numerous difficulties. Diverse genetic factors play a significant role in the progress of TB disease. However, still no key genes for TB susceptibility have been reported. This study aimed to identify the key genes of TB through comprehensive bioinformatics analysis. Methods The series microarray datasets from the gene expression omnibus (GEO) database were analyzed. We used the online tool GEO2R to filtrate differentially expressed genes (DEGs) between TB and health control. Database for annotation can complete gene ontology function analysis as well as Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis. Protein-protein interaction (PPI) networks of DEGs were established by STRING online tool and visualized by Cytoscape software. Molecular Complex Detection can complete the analysis of modules in the PPI networks. Finally, the significant hub genes were confirmed by plug-in Genemania of Cytoscape, and verified by the verification cohort and protein test. Results There are a total of 143 genes were confirmed as DEGs, containing 48 up-regulated genes and 50 down-regulated genes. The gene ontology and Kyoto Encyclopedia of Genes and Genomes analysis show that upregulated DEGs were associated with cancer and phylogenetic, whereas downregulated DEGs mainly concentrate on inflammatory immunity. PPI networks show that signal transducer and activator of transcription 1 (STAT1), guanylate binding protein 5 (GBP5), 2'-5'-oligoadenylate synthetase 1 (OAS1), catenin beta 1 (CTNNB1), and guanylate binding protein 1 (GBP1) were identified as significantly different hub genes. Conclusion We conclude that these genes, including TAT1, GBP5, OAS1, CTNNB1, GBP1 are a candidate as potential core genes in TB and treatment of TB in the future.

Objective This study is aimed to develop a new nomogram for the clinical diagnosis of osteoarticular tuberculosis (TB). Methods xCell score estimation to obtained the immune cell type abundance scores. We downloaded the expression profile of GSE83456 from GEO and proceed xCell score estimation. The routine blood examinations of 326 patients were collected for further validation. We analyzed univariate and multivariate logistic regression to identified independent predicted factor for developing the nomogram. The performance of the nomogram was assessed using the receiver operating characteristic (ROC) curves. The correlation of ESR with lymphocytes, monocytes, and ML ratio was performed and visualized in osteoarticular TB patients. Results Compared with the healthy control group in the dataset GSE83456, the xCell score of basophils, monocytes, neutrophils, and platelets was higher, while lymphoid was lower in the EPTB group. The clinical data showed that the cell count of monocytes were much higher, while the cell counts of lymphocytes were lower in the osteoarticular TB group. AUCs of the nomogram was 0.798 for the dataset GSE83456, and 0.737 for the clinical data. We identified the ML ratio, BMI, and ESR as the independent predictive factors for osteoarticular TB diagnosis and constructed a nomogram for the clinical diagnosis of osteoarticular TB. AUCs of this nomogram was 0.843. Conclusions We demonstrated a significant change between the ML ratio of the EPTB and non-TB patients. Moreover, we constructed a nomogram for the clinical diagnosis of the osteoarticular TB diagnosis, which works satisfactorily.

Background: Ewing sarcoma (ES), the second most prevalent bone malignant tumor has no widely known prognostic biomarker. Earlier studies have suggested that chaperonin containing TCP1 complex 6A (CCT6A), which encodes a molecular protein chaperone, is involved in the pathogenesis of many cancers. However, there are no known reports providing clear evidence of its role in ES pathogenesis. Methods: We performed a bioinformatic analysis of 32 ES specimens from the GSE17618 dataset concentrating on the differences in gene expression, OS, event-free survival (EFS) in the different subgroups. Immunohistochemical studies were also performed to identify the expression levels of selected genes in ES and immediate paracancerous tissues. Results: After 3 screenings, CCT6A was identified to be highly correlated with ES prognosis. Our survival analysis revealed a low overall survival (OS) for high CCT6A expression (P-value = .024). Our Cox regression analysis identified CCT6A expression, lEFS, and age were strongly associated with prognosis of ES. Our multivariate Cox regression analysis shows that CCT6A (P-value = .015), age (P-value = .026), and EFS (P-value = .002) were independent poor prognostic biomarkers. Our immunohistochemical analysis showed that the expression levels of CCT6A were significantly higher in ES tissues compared to the paracancerous tissues. Conclusion: From the results of our study, we identified the expression levels of CCT6A to be strongly associated with prognosis of ES. Thus, the expression levels of the CCT6A gene could serve as a biomarker for the prediction of ES prognosis.

In recent years, deep learning techniques are explored unceasingly for machinery fault diagnosis. The vibration signal of faulty rotating machines contains distinct periodic impacts, and hence is the ideal candidate for the model input. However, there are still three challenges in deep learning on raw vibration signals: (1) The shifts of the fault impacts among the input samples prone to cause misdiagnosis; (2) The working load is always changing; (3) The background noise such as the vibration from non-goal machines is inevitable. Therefore, a novel method called deep capsule network with stochastic delta rule (DCN-SDR) is proposed for rolling bearing fault diagnosis. DCN-SDR takes raw temporal signal as input and achieves very high accuracy under different working loads. Moreover, the model performs outstandingly under noisy environment via a regularization method based on SDR. The network visualization is demonstrated and analyzed. Comparing with the state-of-the-art methods, superiority of the proposed method is verified.

On the basis of studying and analyzing the basic principles of A star algorithm, this paper compares its advantages and disadvantages with those of genetic algorithm and ant colony algorithm. In the meantime, the paper builds the model of unmanned aerial vehicle(UAV) battlefield environment for route planning and applies the A star algorithm to UAV route planning under the constraints of bearing the least danger and consuming the least fuel. Finally, the paper uses python programming language to simulate the UAV route planning, whose result shows the validity of the model and the feasibility of the algorithm.

The 4D microgravity method is becoming a mature technology. A project to develop practical measurement and interpretation techniques was conducted at Prudhoe Bay, Alaska, from 1994 through 2002. Beginning in 2003 these techniques have been systematically applied to monitor a waterflood in the gas cap of the Prudhoe Bay reservoir. Approximately 300 stations in a [Formula: see text] area are reoccupied in each survey year with sub-[Formula: see text] precision absolute gravity and centimeter precision Global Positioning System (GPS) geodetic measurements. The 4D gravity measured over epochs 2005–2003, 2006–2003, and 2007–2003 has been successfully modeled to track the mass of water injected since late in 2002. A new and improved version of the A-10 field-portable absolute gravity meter was developed in conjunction with this project and has proven to be a key element in the success of the 4D methodology. The use of an absolute gravity meter in a field survey of this magnitude is unprecedented. There are substantial differences between a 4D absolute microgravity survey and a conventional gravity survey in terms of station occupation procedures, GPS techniques, and the 4D elevation correction. We estimate that the overall precision of the 4D gravity signal in each epoch is less than [Formula: see text].

Between 1994 and 2002, a series of experiments was conducted at Prudhoe Bay, Alaska, aimed at the development of an effective 4D (or time-lapse) gravity technique. Theoretical investigations had pointed out the potential for monitoring water injection in the [Formula: see text]-deep reservoir, but it was not clear that gravity measurements of sufficient accuracy could be made in the arctic environment. During the course of these experiments, new techniques and instrumentation were introduced and perfected for both gravity and position measurements. Gravity stations are located using high-precision global positioning system (GPS) techniques without permanent monuments. Robust methods for meter drift control have improved noise resistance in relative gravimeter surveys. Absolute gravity measurements with a field-portable instrument maintain absolute gravity levels among surveys. A 4D gravity-difference noise of [Formula: see text] standard deviation has been established at Prudhoe Bay for GPS-controlled relative gravimeter surveys. The lessons learned are now being applied to full-scale waterflood monitoring at Prudhoe Bay. The basic technique is applicable to microgravity surveys and 4D microgravity surveys for any purpose.

Summary The electromagnetic smoke ring concept is a useful device for understanding how the fields induced in a 1-D earth propagate and diffuse in a medium. Aside from facilitating a physical understanding of field propagation, the smoke ring concept has been used to interpret behavior of vertical and radial magnetic fields at the surface (Pridmore, 1978) and used to estimate depth of penetration for conductivitydepth transforms (Sengpiel, 1988). Previous authors analyzing time-domain systems have focused their analysis on the current induced by a transmitter step-off excitation, neglecting practical airborne EM waveforms. In this paper, we study the current system induced during the on-time of a half-sine transmitter waveform and compare with the offtime current pattern. Since current is continually generated at surface, the on-time current pattern is more densely distributed near-surface than the off-time current system, suggesting that on-time field measurements should be relatively more sensitive to shallow targets.