Search

Stratification of spontaneous intracerebral hemorrhage (sICH) patients without cerebral herniation at admission, to determine the subgroups may be suffered from poor outcomes or benefit from surgery, is important for following treatment decision. The aim of this study was to establish and verify a de novo nomogram predictive model for long-term survival in sICH patients without cerebral herniation at admission. This study recruited sICH patients from our prospectively maintained ICH patient database (RIS-MIS-ICH, ClinicalTrials.gov Identifier: NCT03862729) between January 2015 and October 2019. All eligible patients were randomly classified into a training cohort and a validation cohort according to the ratio of 7:3. The baseline variables and long-term survival outcomes were collected. And the long-term survival information of all the enrolled sICH patients, including the occurrence of death and overall survival. Follow-up time was defined as the time from the onset to death of the patient or the last clinical visit. The nomogram predictive model was established based on the independent risk factors at admission for long-term survival after hemorrhage. The concordance index (C-index) and ROC curve were used to evaluate the accuracy of the predictive model. Discrimination and calibration were used to validate the nomogram in both the training cohort and the validation cohort. A total of 692 eligible sICH patients were enrolled. During the average follow-up time of 41.77 ± 0.85 months, a total of 178 (25.7%) patients died. The Cox Proportional Hazard Models showed that age (HR 1.055, 95% CI 1.038–1.071, P P P

Pedestrian detection in low-light environments has been an extremely challenging task because of the serious degradation of color and texture information. In the latest research, multi-task learning is introduced into image relighting and pedestrian detection tasks, which improves the performance of detecting pedestrians in low-light environments significantly. However, many problems in the multi-task learning period, including the misalignment of scale and channel of features from image relighting and pedestrian detection tasks, remain unresolved, thereby resulting in insufficient feature representation. In this paper, we propose a novel cross-task feature alignment method to tackle the aforementioned problems. Specifically, the proposed method imposes four feature alignment (FA) layers before the feature fusing and sharing step in multi-task learning period to align the scale and channel of features across tasks and fine-tune feature representation iteratively. In addition, we design a novel multi-scale feature-enhanced detection network to further improve the performance of the detector. Experimental results from simulated and real-world scenarios prove that our method prominently boosts the ability to detect pedestrians in the dark.

Previous genome-wide association studies (GWAS) reported that the allele C of rs945270 of the kinectin 1 gene (KTN1) most significantly increased the gray matter volume (GMV) of the putamen and modestly regulated the risk for attention deficit hyperactivity disorder (ADHD). On the other hand, ADHD is known to be associated with a reduction in subcortical and cortical GMVs. Here, we examined the interrelationships of the GMVs, rs945270 alleles, and ADHD symptom scores in the same cohort of children. With data of rs945270 genotypes, GMVs of 118 brain regions, and ADHD symptom scores of 3372 boys and 3129 girls of the Adolescent Brain Cognition Development project, we employed linear regression analyses to examine the pairwise correlations adjusted for the third of the three traits and other relevant covariates, and examine their mediation effects. We found that the major allele C of rs945270 modestly increased risk for ADHD in males only when controlling for the confounding effects of the GMV of any one of the 118 cerebral regions (0.026 ≤ p ≤ 0.059: Top two: left and right putamen). This allele also significantly increased putamen GMV in males alone (left p = 2.8 × 10−5, and right p = 9.4 × 10−5; α = 2.1 × 10−4) and modestly increased other subcortical and cortical GMVs in both sexes (α p −7 ≤ p α; Top two: left pallidum and putamen) and males (3.5 × 10−6 ≤ p α), respectively. Finally, the left and right putamen GMVs reduced 14.0% and 11.7% of the risk effects of allele C on ADHD, and allele C strengthened 4.5% (left) and 12.2% (right) of the protective effects of putamen GMVs on ADHD risk, respectively. We concluded that the rs945270-GMVs-ADHD relationships were sex-different. In males, the major allele C of rs945270 increased risk for ADHD, which was compromised by putamen GMVs; this allele also but only significantly increased putamen GMVs that then significantly protected against ADHD risk. In females, the top two GMVs significantly decreasing ADHD risk were left pallidum and putamen GMVs. Basal ganglia the left putamen in particular play the most critical role in the pathogenesis of ADHD.

Although face verification algorithms have made great success under controlled conditions in recent years, there’s plenty of room at its performance under uncontrolled real-world due to lack of discriminative feature representation ability. From the perspective of metric learning, we proposed a context-aware based Siamese neural network (CASNN) to learn a simple yet powerful network for face verification task to enhance its discriminative feature representation ability. Firstly, a context-aware module is used to automatically focus on the key area of the input facial images without irrelevant background area. Then we design a Siamese network equipped with center-classification loss to compress intra-class features and enlarge between-class ones for discriminative metric learning. Finally, we propose a quantitative indicator named “D-score” to show the discriminative representation ability of the learnt features from different methods. The extensive experiments are conducted on LFW dataset, YouTube Face dataset (YTF) and real-world dataset. The results confirm that CASNN outperforms some state-of-the-art deep learning-based face verification methods.

Chaotification can be employed to weaken or eliminate the feature of line spectra of waterborne noise. The efficiency of this method lies on the use of small control. The analysis reveals that the critical control gain depends on the stiffness of vibration isolation systems. Thus, an isolation raft system based on quasi-zero-stiffness (QZS) property is proposed for line spectrum chaotification. A nonlinear time-delay controller is derived accordingly. Comparative analysis shows that the new approach allows much smaller control, and the intensity of line spectra is further reduced. Numerical simulations also indicate other advantages with the introduction of QZS system into chaotification.

Objective: Neuroendoscopic treatment is an alternative therapeutic strategy for the treatment of septate chronic subdural hematoma (sCSDH). However, the safety and efficacy of this strategy remain controversial. We compared the clinical outcomes of neuroendoscopic treatment with those of standard (large bone flap) craniotomy for sCSDH reported in our center. Furthermore, the safety and efficacy of the neuroendoscopic treatment procedure for sCSDH were evaluated.Methods: We retrospectively collected the clinical data of 43 patients (37 men and six women) with sCSDH who underwent either neuroendoscopic treatment or standard (large bone flap) craniotomy, such as sex, age, smoking, drinking, medical history, use of antiplatelet drugs, postoperative complications, sCSDH recurrence, length of hospital stay, and postoperative hospital stay. We recorded the surgical procedures and the neurological function recovery prior to surgery and 6 months following the surgical treatment.Results: The enrolled patients were categorized into neuroendoscopic treatment (n = 23) and standard (large bone flap) craniotomy (n = 20) groups. There were no differences in sex, age, smoking, drinking, medical history, antiplatelet drug use, postoperative complications, and sCSDH recurrence between the two groups (p > 0.05). However, the patients in neuroendoscopic treatment group had a shorter length of total hospital stay and postoperative hospital stay as compared with the standard craniotomy group (total hospital stay: 5.26 ± 1.89 vs. 8.15 ± 1.04 days, p < 0.001; postoperative hospital stay: 4.47 ± 1.95 vs. 7.96 ± 0.97 days, p < 0.001). The imaging and Modified Rankin Scale at the 6-month follow-up were satisfactory, and no sCSDH recurrence was reported in the two groups.Conclusions: The findings of this study indicate that neuroendoscopic treatment is safe and effective for sCSDH; it is minimally invasive and could be clinically utilized.

Background and Purpose: Perihematomal edema (PHE) is associated with poor functional outcomes after intracerebral hemorrhage (ICH). Early identification of risk factors associated with PHE growth may allow for targeted therapeutic interventions.Methods: We used data contained in the risk stratification and minimally invasive surgery in acute intracerebral hemorrhage (Risa-MIS-ICH) patients: a prospective multicenter cohort study. Patients' clinical, laboratory, and radiological data within 24 h of admission were obtained from their medical records. The absolute increase in PHE volume from baseline to day 3 was defined as iPHE volume. Poor outcome was defined as modified Rankin Scale (mRS) of 4 to 6 at 90 days. Binary logistic regression was used to assess the relationship between iPHE volume and poor outcome. The receiver operating characteristic curve was used to find the best cutoff. Linear regression was used to identify variables associated with iPHE volume (ClinicalTrials.gov Identifier: NCT03862729).Results: One hundred ninety-seven patients were included in this study. iPHE volume was significantly associated with poor outcome [P = 0.003, odds ratio (OR) 1.049, 95% confidence interval (CI) 1.016–1.082] after adjustment for hematoma volume. The best cutoff point of iPHE volume was 7.98 mL with a specificity of 71.4% and a sensitivity of 47.5%. Diabetes mellitus (P = 0.043, β = 7.66 95% CI 0.26–15.07), black hole sign (P = 0.002, β = 18.93 95% CI 6.84–31.02), and initial ICH volume (P = 0.018, β = 0.20 95% CI 0.03–0.37) were significantly associated with iPHE volume. After adjusting for hematoma expansion, the black hole sign could still independently predict the increase of PHE (P < 0.001, β = 21.62 95% CI 10.10–33.15).Conclusions: An increase of PHE volume >7.98 mL from baseline to day 3 may lead to poor outcome. Patients with diabetes mellitus, black hole sign, and large initial hematoma volume result in more PHE growth, which should garner attention in the treatment.

Human–object interaction (HOI) is a human-centered object detection task that aims to identify the interactions between persons and objects in an image. Previous end-to-end methods have used the attention mechanism of a transformer to spontaneously identify the associations between persons and objects in an image, which effectively improved detection accuracy; however, a transformer can increase computational demands and slow down detection processes. In addition, the end-to-end method can result in asymmetry between foreground and background information. The foreground data may be significantly less than the background data, while the latter consumes more computational resources without significantly improving detection accuracy. Therefore, we proposed an input-controlled transformer, “ratio-transformer” to solve an HOI task, which could not only limit the amount of information in the input transformer by setting a sampling ratio, but also significantly reduced the computational demands while ensuring detection accuracy. The ratio-transformer consisted of a sampling module and a transformer network. The sampling module divided the input feature map into foreground versus background features. The irrelevant background features were a pooling sampler, which were then fused with the foreground features as input data for the transformer. As a result, the valid data input into the Transformer network remained constant, while irrelevant information was significantly reduced, which maintained the foreground and background information symmetry. The proposed network was able to learn the feature information of the target itself and the association features between persons and objects so it could query to obtain the complete HOI interaction triplet. The experiments on the VCOCO dataset showed that the proposed method reduced the computational demand of the transformer by 57% without any loss of accuracy, as compared to other current HOI methods.

ARChitecture Analysis and Design Integrated Approach (ARCADIA) is a kind of Model-Based System Engineering (MBSE) methodology developed by Thales, and Capella is a kind of modeling tool dedicated to ARCADIA. In this paper, we will introduce our practice of ARCADIA/Capella in civil radar design, including the reason we choose this solution and how we use it in civil radar design. We will also briefly introduce our extension of Capella in parametric modeling, dynamic execution and simulation, system and subsystem collaboration, interface detailed design, and document generation.

Classic sparse representation, as one of prevalent feature learning methods, is successfully applied for different computer vision tasks. However it has some intrinsic defects in object detection. Firstly, how to learn a discriminative dictionary for object detection is a hard problem. Secondly, it is usually very time-consuming to learn dictionary based features in a traditional exhaustive search manner like sliding window. In this paper, we propose a novel feature learning framework for object detection with the structure sparsity constraint and classification error minimization constraint to learn a discriminative dictionary. For improving the efficiency, we just learn sparse representation coefficients from object candidate regions and feed them to a kernelized SVM classifier. Experiments on INRIA Person Dataset and Pascal VOC 2007 challenge dataset clearly demonstrate the effectiveness of the proposed approach compared with two state-of-the-art baselines.

Real-time pedestrian detection is very essential for auto assisted driving system. For improving the accuracy, more and more complicate features are proposed. However, most of them are impracticable for the real-world application because of high computation complexity and memory consumption, especially for onboard embedding system in the unmanned vehicle. In this paper, a novel framework that utilizes reconstruction sparsity to synthesize the feature map online is proposed for real-time pedestrian detection for the early warning system of the unmanned vehicle in real world. In this framework, the feature map is computed by sparse line combination of the representative coefficient and the feature response of trained basis which is learned offline. The efficiency of our method only depends on the dictionary decomposition no matter how complicated the feature is. Moreover, our method is suitable for most of the known complicate features. Experiments on four challenging datasets: Caltech, INRIA, ETH and TUD-Brussels, demonstrate that our proposed method is much efficient (more than 10 times acceleration) than the state-of-the-art approaches with comparable accuracy.

Pedestrian attributes recognition is a very important problem in video surveillance and video forensics. Traditional methods assume the pedestrian attributes are independent and design handcraft features for each one. In this paper, we propose a joint hierarchical multi-task learning algorithm to learn the relationships among attributes for better recognizing the pedestrian attributes in still images using convolutional neural networks (CNN). We divide the attributes into local and global ones according to spatial and semantic relations, and then consider learning semantic attributes through a hierarchical multi-task CNN model where each CNN in the first layer will predict each group of such local attributes and CNN in the second layer will predict the global attributes. Our multi-task learning framework allows each CNN model to simultaneously share visual knowledge among different groups of attribute categories. Extensive experiments are conducted on two popular and challenging benchmarks in surveillance scenarios, namely, the PETA and RAP pedestrian attributes datasets. On both benchmarks, our framework achieves superior results over the state-of-the-art methods by 88.2% on PETA and 83.25% on RAP, respectively.

Objective To seek a cerebral perfusion pressure (CPP) threshold that can reduce the occurrence of delayed cerebral ischemia (DCI) after aneurysmal subarachnoid hemorrhage (aSAH). Methods We analyzed the clinical data of patients with the diagnosis of aSAH and underwent CPP monitoring in our department from February 2014 to December 2015. CPP was divided into four specified thresholds by every 10 mmHg increments, which were from 50 mmHg to 80 mmHg. The totally time ratio of CPP below each threshold was calculated. The correlation between the time ratio and DCI were analyzed using binary logistic regression. And receiver operating characteristic curve was performed to identify the cutoff time ratios at higher risk of DCI. Results Finally, 17 patients developed DCI from 60 patients who were recruited. The time ratios of CPP which was below 50 mmHg, 60 mmHg and 70 mmHg were found predictors of DCI by the binary logistic regression. The cutoff time ratios were 0.4% (AUC = 0.777), 7.0% (AUC = 0.702), 28.7% (AUC = 0.696) respectively. While at the level of 80 mmHg, the cutoff time ratio was 65% (AUC = 0.595). It was not related to DCI (P = 0.167). Patients suffered from DCI had a worse outcome than who did not at 3 month after aSAH (P = 0.018). Conclusion Time ratios at higher risk of DCI had a positive relationship with the CPP thresholds. Keeping CPP above 70 mmHg may be helpful to prevent DCI after aSAH, but it still needs further investigation.

In this paper we address the problem of automatic clothing parsing in surveillance video with the information from user-generated tags such as “jeans” and “T-shirt”. Although clothing parsing has achieved great success in fashion clothing, it is quite challenging to parse clothing in practical surveillance conditions due to complicated environmental interferences, such as illumination change, scale zooming, viewpoint variation and etc. Our method is developed to capture the clothing information from the fashion field and apply it to surveillance domain by weakly-supervised transfer learning. Most of attribute labels in surveillance images convey strong location information, which can be considered as weak labels to deal with the transfer method. Both quantitative and qualitative experiments conducted on practical surveillance datasets have shown the effectiveness of the proposed method.

We propose a novel pedestrian detection approach in the extreme Low-Resolution (LR) images via sparse representation. Pedestrian detection in the extreme LR images is very important for some specific applications such as abnormal event detection and video forensics from surveillance videos. Although the pedestrian detection in High-Resolution (HR) images has achieved remarkable progress, it is still a challenging task in the LR images, because the discriminative information in the HR images usually disappear in the LR ones. It makes the precision of the detectors in the LR images decrease by a large margin. Most of the traditional methods enlarge the LR image by the linear interpolation methods. However, it can not preserve the high frequency information very well, which is very important for the detectors. For solving this problem, we reconstruct the LR image in the high resolution by sparse representation. In our model, the LR and HR dictionaries are established respectively in the training stage, and the representative coefficients mapping relations are determined. Moreover, for improving the speed of feature extraction, the feature reconstruction in the LR images is converted to the sparse linear combination between the coefficients and the response of the atoms in HR dictionary by the LR-HR mapping, no matter how complex the feature extraction is. Experiments on the four challenging datasets: Caltech, INRIA, ETH and TUD-Brussels, demonstrate that our proposed method outperforms the state-of-the-art approaches and is much efficient with more than 10 times speedup.

Podocalyxin (PODXL) has been found to increase the aggressive phenotype of a number of cancers, including astrocytoma. In addition, the progression of astrocytoma has been associated with sperm‑associated antigen 9 (SPAG9), a recently characterized oncoprotein. In the present study, the association between SPAG9 and PODXL in human astrocytoma invasion and the underlying mechanisms were investigated for the first time, to the best of our knowledge. Overexpression and knockdown of SPAG9 were performed in SW1783 (grade III astrocytoma) and U87 (grade IV astrocytoma; glioblastoma) cells, respectively. PODXL expression at both the mRNA and the protein level, as well as the PODXL gene promoter activity, were significantly increased and decreased in parallel with the overexpression and knockdown of SPAG9 in astrocytoma cells; these effects were blocked by the selective c‑Jun N‑terminal kinase (JNK) inhibitor SP600125 (5 µM) and restored by the JNK agonist anisomycin (25 ng/ml), respectively. SPAG9 overexpression significantly increased cell invasion and matrix metalloproteinase‑9 (MMP‑9) expression in SW1783 cells, and this effect was reversed by knockdown of PODXL. In U87 cells, knockdown of SPAG9 markedly decreased cell invasion and MMP‑9 expression, which was completely restored by overexpression of PODXL. In conclusion, it was demonstrated in the present study that SPAG9 upregulates PODXL expression in human astrocytoma cells at the PODXL gene promoter/transcriptional level through a JNK‑dependent mechanism and that PODXL is a critical mediator of the promoting effect of SPAG9 on astrocytoma cell invasion, possibly through upregulation of MMP‑9 expression. This study provides novel insights into the molecular mechanisms involved in astrocytoma invasion.

Although the object detection and recognition has received growing attention for decades, a robust fire and flame detection method is rarely explored. This paper presents a novel solid solution based on sparse representation with spatial pyramid pooling. Traditional sparse representation, as one of prevalent feature learning methods, is successfully applied for object detection. But it has some intrinsic defects. Firstly, it requires fixed input image size. Secondly, the accuracy of detection heavily depends on discriminative dictionary learning and feature coding. At last, it is usually very time-consuming. In this paper, we have proposed a novel dictionary learning method with the structure sparsity constraint to train a discriminative dictionary. In feature coding stage, we compute sparse codes of each patch with dictionaries learned from data and pool them to form local histogram in spatial pyramid manner. At lat, the feature vector is pipelined into a linear SVM classifier to train the model. For improving the efficiency, we also adopt the selective search approach to generate the candidate region proposals in the preprocessing stage. In processing test images, our method achieved better or comparable accuracy to the state-of-the-art on FlameDetection2010 Dataset.

Recently many powerful complicated features have been used for pedestrian detection successfully but they are not fit for real applications because of heavily consuming time caused by production of complicate feature extraction and millions of candidate object probing. The formal is critical for pedestrian detection, so for solving this problem, effective region proposal strategy was proposed. Such approaches generate candidate regions either by segmentation or by shape classification, and they still generate several thousand regions each image, that is too many for fast pedestrian detection. In this paper, a novel search strategy, saliency prior based random partition, is proposed to generate nearly two hundred regions and consume less time than selective search at the same recall. And we prefer the Deformable Part Model [8], one of the most popular object detectors, as the pedestrian detector. At last, we combine the salient prior and the part based detector by Bayesian inference. Experiment results on INRIA person dataset and Caltech person dataset have demonstrated that our approach has outperformed the selective search method.

Car re-identification, searching a specific car object from a large-scale car image database, is investigated in this paper. Previous work mainly focuses on fixed pose and overlooks the special appearance. However, avoiding matching other poses would lead to coarse results of the car retrieval. And some special attributes like individual paintings which are greatly helpful for car retrieval have not drawn enough attention. This paper addresses these problems through multi-poses matching and re-ranking based on special attributes. Our core idea lies in query expansion method that can capture weighted attributes to build the retrieval model, which allows us to estimate invisible attributes by the visible ones to construct complete attributes vectors to car retrieval in any poses. Furthermore, we divide all attributes into two groups, special attributes and common attributes. Here special attributes represent the abnormal appearance like individual paintings or car damage while common attributes denote the intrinsic appearance of car. Using special attributes to re-rank results turns out to be beneficial to improve the retrieval performance. In the end, the experiments demonstrate the effectiveness of our approach on the car datasets.

We propose a novel object detection framework in extreme Low-Resolution (LR) images via sparse representation. Object detection in extreme LR images is very important for some specific applications such as abnormal event detection, automatic criminal investigation from surveillance videos. Object detection has achieved much progress in computer vision, but it is still a challenging task in LR image, because traditional discriminative features in high resolution usually disappear in low resolution. The precision of the detector in LR will decrease by a large margin. Our model uses sparse coding of part filters to represent each filter as a sparse linear combination of shared dictionary elements. The main contribution of this paper: 1) the object detection framework in extreme LR is proposed by detecting objects in reconstructed HR image; 2) a mapping function from LR patches to High-Resolution (HR) patches will be learned by a local regression algorithm called sparse support regression, which can be constructed from the support based of the LR-HR dictionary; 3) a novel feature extraction method is proposed to accelerate by extracting visual features from HR dictionary atoms. Our approach has produced better performance for object detection than state-of-the-art methods. Testing our method from INRIA and PASCAL VOC 2007 datasets has revealed similar improvements, suggesting that our approach is suitable for general object detection applications.

To explore the eff ect of lavage with artificial cerebrospinal fluid on neural cell apoptosis and the extracellular regulated kinase (ERK) pathway aft er traumatic brain injury.A total of 192 SD rats were randomly divided into a sham group, a traumatic brain injury model group, a local artificial cerebrospinal fluid group, and a local saline group. Each group was divided into 4 sub-groups by the sacrificed time at 6 h, 12 h, 1 d and 3 d aft er the operation. Th e phosphorylation of extracellular regulated kinase 2 (P-ERK2), TNF-α and cellular apoptosis were examined.Th e levels of P-ERK2 protein and TNF-α protein, as well as the number of apoptotic cells at each time point in the local artificial cerebrospinal fluid group were lower than those in the model group or in the saline group (P0.05).Lavage with artificial cerebrospinal fluid can reduce apoptosis of neural cells after brain injury through the ERK pathway.

Classic algorithms of pedestrian detection usually locate the latent position via sliding window techniques, which resize the matching window and/or original images at different scales and scan the image. However, this method has two main drawbacks. First, resizing at a fix rate cannot search through the whole scale space, resulting in the failure of accurate object location. Second, resizing and scanning at various scales is usually time-consuming, which is improper for practical applications. To conquer the above difficulties, a novel pedestrian detection method with salient information is proposed. In this paper, the salient detection model and the traditional covariance matrix descriptor are combined in a Bayesian framework to detect pedestrians in the still image. Finally, the efficiency of our approach compared with state-of-the-art results is demonstrated on the public INRIA dataset.

Pedestrian detection has been seen huge progress in recent years, much thanks to the Histograms of Oriented Gradients (HOG) features. However, this method (HOG and SVM) has a large number of false detections. To conquer the problem, we provide an affirmative answer by proposing and investigating a salience representation for pedestrian detection, Histograms-Of-Salience (HOS). We extracted saliency map learned from data by using Histogram Based Contrast, and aggregate salient value and oriented gradients to form local HOS. We intentionally keep true to the sliding window framework and only change the underlying features. By learning and using local HOS feature that are much more expressive than HOG, we demonstrate large improvements on the public INRIA dataset.

Pedestrian detection, which is to identify category pedestrian of object and give the position information in the image, is an important and yet challenging task due to the intra-class variation of pedestrians in clothing and articulation. Previous researches mainly focus on feature extraction and sliding window, where the former aims to find robust feature representation while the latter seeks to locate the latent position. However, most of sliding windows are based on scale transformation and traverse the entire image. Therefore, it will bring computational complexity and false detection which is not necessary. To conquer the above difficulties, we propose a novel Saliency-Based Deformable Model SBDM method for pedestrian detection. In SBDM method we present that, besides the local features, the saliency in the image provides important constraints that are not yet well utilized. And a probabilistic framework is proposed to model the relationship between Saliency detection and the feature Deformable Model via a Bayesian rule to detect pedestrians in the still image.

Vehicle re-identification, retrieving a vehicle detected by one camera with the same vehicle by another camera, is an important problem in the video investigation application which is a technology for criminal investigation. In this task, it not only needs to classify the vehicle category, but also to identify a specific object in the category. Previous methods mainly focus on the vehicle categorization, which cannot identify the specific vehicle. In this paper, a two-stage strategy is proposed to accomplish vehicle re-identification in realistic surveillance videos. Specifically, in the first stage, a part-based appearance model fusing multiple visual features is proposed to represent the vehicle object, and then a coarse ranking list is generated by comparing appearance models of the probe and gallery vehicles. In the second stage, the temporal-spatial relation is introduced to re-rank the above visual-based ranking list, where vehicles of the same category and reasonable spatial-temporal relations are placed in top positions while those of mismatched types or relations are placed in rear positions. Both quantitative and qualitative experiments conducted on a real world dataset have validated the effectiveness of the proposed method.

To detect the impact of artificial cerebrospinal fluid lavage time on the edema of traumatic brain injury.A total of 240 SD rats were randomly divided into a sham group, a traumatic brain injury model group, 3 artificial cerebrospinal fluid lavage groups (3 h, 6 h and 9 h). Each group was divided into 4 sub-groups by time of sacrifice namely 12 h, 1 d, 3 d and 7 d postoperatively. We detected the content of brain water, sodium, and potassium, and the VEGF expression to confirm whether the duration of lavage could reduce the traumatic brain edema.Compared with the sham group and the traumatic brain injury model group, brain water content and sodium content were decreased, while the potassium content and the VEGF levels were increased in the artificial cerebrospinal fluid lavage groups. Significant difference was found at 12 h, 1 d, and 3 d after the injury (P0.05). With the increase of artificial cerebrospinal fluid lavage time, the difference was more obvious.Artificial cerebrospinal fluid lavage can reduce the brain edema after traumatic brain injury. The longer the lavage, the more obvious the effect.

To evaluate the efficacy of dural tenting suture and epidural drainage in craniotomy.In 145 cases of intracranial lesions, dural tenting suture and epidural drainage were performed to prevent epidural hematoma.Postoperative computed tomography (CT) showed no epidural hematoma required surgery in both groups.Both dural tenting suture and epidural drainage are effective in preventing epidural hematoma. Hemostasis is the key step. Dural tenting suture without epidural drainage relieves psychological stress. It decreases the risk of intracranial infection and avoids some unusual complications.

To establish high resolution, reproducible 2-dimensional electrophoresis (2-DE) profiles of invasive and non-invasive pituitary adenoma tissues and to identify differentially expressed proteins between the invasive and non-invasive tissues.The proteome from invasive and non-invasive pituitary adenomas tissues was dissected and analyzed by: (1) immobilized pH gradient two-dimensional polyacrylamide gel electrophoresis, (2) silver staining, (3) imageMaster 2-D software analysis, (4) peptide mass fingerprint based (PMS) on matrix-assisted laser desorption/ionization time of flight mass spectrometry (MALDI-TOF-MS), and (5) database comparison.High-resolution 2-D patterns of invasive and non-invasive pituitary adenoma tissues were successfully produced and repeated 3 times for each sample. An average of 1 080+/-24 and 1 035+/-28 spots were detected for invasive and non-invasive pituitary adenoma tissues, respectively. Additionally, 975+/-45 and 918+/-56 spots were found to have an average matching rate of 90.3% and 88.7% for invasive and non-invasive tissues, respectively. The spot positional deviation was (1.563+/-0.259) mm for IEF and (1.088+/-0.206) mm for SDS-PAGE. A total of 99 spots of differential expression were matched between the invasive and non-invasive pituitary adenoma tissues. Thirty differential proteins, some of which were involved in the regulation of cells cycle and signal transduction, were initially characterized by PMS.The acquisition of well-resolved and reproducible 2-D patterns of invasive and non-invasive pituitary adenoma tissues and the identification of differentially expressed proteins provides a proteome database for invasive pituitary adenomas.