Biomedical image segmentation algorithm based on dense atrous convolution.

Biomedical images have complex tissue structures, and there are great differences between images of the same part of different individuals. Although deep learning methods have made some progress in automatic segmentation of biomedical images, the segmentation accuracy is relatively low for biomedical images with significant changes in segmentation targets, and there are also problems of missegmentation and missed segmentation. To address these challenges, we proposed a biomedical image segmentation method based on dense atrous convolution.

A global optimization generation method of stitching dental panorama with anti-perspective transformation.

To address the limitation of narrow field-of-view in local oral cavity images that fail to capture large-area targets at once, this paper designs a method for generating natural dental panoramas based on oral endoscopic imaging that consists of two main stages: the anti-perspective transformation feature extraction and the coarse-to-fine global optimization matching. In the first stage, we increase the number of matched pairs and improve the robustness of the algorithm to viewpoint transformation by normalizing the anti-affine transformation region extracted from the Gaussian scale space and using log-polar coordinates to compute the gradient histogram of the octagonal region to obtain the set of perspective transformation resistant feature points. In the second stage, we design a coarse-to-fine global optimization matching strategy.

Intelligent crowd sensing pickpocketing group identification using remote sensing data for secure smart cities.

As a public infrastructure service, remote sensing data provided by smart cities will go deep into the safety field and realize the comprehensive improvement of urban management and services. However, it is challenging to detect criminal individuals with abnormal features from massive sensing data and identify groups composed of criminal individuals with similar behavioral characteristics. To address this issue, we study two research aspects: pickpocketing individual detection and pickpocketing group identification.

Research on rainy day traffic sign recognition algorithm based on PMRNet.

The recognition of traffic signs is of great significance to intelligent driving and traffic systems. Most current traffic sign recognition algorithms do not consider the impact of rainy weather. The rain marks will obscure the recognition target in the image, which will lead to the performance degradation of the algorithm, a problem that has yet to be solved.

Research on user recruitment algorithms based on user trajectory prediction with sparse mobile crowd sensing.

Sparse mobile crowd sensing saves perception cost by recruiting a small number of users to perceive data from a small number of sub-regions, and then inferring data from the remaining sub-regions. The data collected by different people on their respective trajectories have different values, and we can select participants who can collect high-value data based on their trajectory predictions. In this paper, we study two aspects of user trajectory prediction and user recruitment.

An improved pix2pix model based on Gabor filter for robust color image rendering.

In recent years, with the development of deep learning, image color rendering method has become a research hotspot once again. To overcome the detail problems of color overstepping and boundary blurring in the robust image color rendering method, as well as the problems of unstable training based on generative adversarial networks, we propose an color rendering method using Gabor filter based improved pix2pix for robust image. Firstly, the multi-direction/multi-scale selection characteristic of Gabor filter is used to preprocess the image to be rendered, which can retain the detailed features of the image while preprocessing to avoid the loss of features.

Neural Network-Based Mapping Mining of Image Style Transfer in Big Data Systems.

Image style transfer can realize the mutual transfer between different styles of images and is an essential application for big data systems. The use of neural network-based image data mining technology can effectively mine the useful information in the image and improve the utilization rate of information. However, when using the deep learning method to transform the image style, the content information is often lost.

A Novel 3D Reconstruction Algorithm of Motion-Blurred CT Image.

The majority of medical workers are eager to obtain realistic and real-time CT 3D reconstruction results. However, autonomous or involuntary motion of patients can cause blurring of CT images. For the 3D reconstruction scene of motion-blurred CT image, this paper consists of two parts: firstly, a GAN image translation network deblurring algorithm is proposed to remove blurred results.

A Multiscale Constraints Method Localization of 3D Facial Feature Points.

It is an important task to locate facial feature points due to the widespread application of 3D human face models in medical fields. In this paper, we propose a 3D facial feature point localization method that combines the relative angle histograms with multiscale constraints. Firstly, the relative angle histogram of each vertex in a 3D point distribution model is calculated; then the cluster set of the facial feature points is determined using the cluster algorithm.

Chromosomal imbalances revealed in primary renal cell carcinomas by comparative genomic hybridization.

Renal cell carcinoma (RCC) accounts for approximately 3% of all new cancer cases. Although the classification of RCC is based mainly on histology, this method is not always accurate. We applied comparative genomic hybridization (CGH) to determine genomic alterations in 46 cases of different RCC histological subtypes [10 cases of clear cell RCC (CCRCC), 13 cases of papillary RCC (PRCC), 12 cases of chromophobe RCC (CRCC), 9 cases of Xp11.

Unclassified renal cell carcinoma: a clinicopathological, comparative genomic hybridization, and whole-genome exon sequencing study.

Unclassified renal cell carcinoma (URCC) is a rare variant of RCC, accounting for only 3-5% of all cases. Studies on the molecular genetics of URCC are limited, and hence, we report on 2 cases of URCC analyzed using comparative genome hybridization (CGH) and the genome-wide human exon GeneChip technique to identify the genomic alterations of URCC. Both URCC patients (mean age, 72 years) presented at an advanced stage and died within 30 months post-surgery.

Analysis of PTEN methylation patterns in soft tissue sarcomas by MassARRAY spectrometry.

Soft tissue sarcomas (STSs) are a rare and fascinating group of diseases that can be subdivided into specific reciprocal translocations in STSs (SRTSs) and nonspecific reciprocal translocations in STSs (NRTSs). PTEN mutations are rare in STSs, suggesting that PTEN expression may be lost by alternative mechanisms such as methylation. In order to reveal whether aberrant PTEN methylation occurs in STSs, MassARRAY Spectrometry was carried to detect methylation patterns of PTEN in STSs.

[Shengjing tablets for semen non-liquefaction: a clinical study of 100 cases].

Objective: To investigate the efficacy and action mechanism of Shengjing Tablets in the treatment liquefaction.

Methods: We randomly assigned 150 patients with semen non-liquefaction to receive Shengjing Tablets group, n = 100) and vitamin E capsules (control group, n = 50) for 2 courses of 45 days each, followed by observation liquefaction time and other semen parameters.

Results: After the first course, 68 of the patients in the treatment group 20 responded and 12 failed to respond; and after the second course, 84 were cured, 9 responded and 7 failed to respond, effective rate of 93.

Spatial estimation of antibiotic residues in surface soils in a typical intensive vegetable cultivation area in China.

Antibiotic residues in surface soils can lead to serious health risks and ecological hazards. Spatial mean concentration of antibiotic residues in the soil is the most important indicator of a region's environmental risk to antibiotic residues. Considerable estimation error would lead to an inefficient strategy of pollution control that happens when sample size is small and the estimation model does not match the spatial features of the object to be surveyed.

Mutational analysis of p53 and PTEN in soft tissue sarcoma.

p53 and PTEN are the two most frequently mutated tumor suppressors in human cancer. However, literature on the effect of the joint inactivation of tumor-suppressor genes in soft tissue sarcoma (STS) is lacking. The purpose of this study was to investigate whether p53 and PTEN mutations play a role in the carcinogenesis of STS, as well as to evaluate their mutual role in STS pathogenesis.

[Detection and clinical significance of Notch1 methylation in breast cancer and intraductal proliferative breast lesions].

Objective: To explore the relevance between the promoter methylation status of Notch1 gene and the invasive ductal carcinoma and ductal hyperplastic lesions of the breast.

Methods: Methylation status of Notch1 gene in human breast invasive ductal carcinoma (IDC, n = 89), ductal carcinoma in situ (DCIS, n = 20), atypical ductal hyperplasia (ADH, n = 11) and usual ductal hyperplasia (UDH, n = 20) were quantitatively evaluated by MALDI-TOF MS. The expression of Notch1 protein was detected by immunohistochemical stain (SP method).

[Correlation between HLA-DRB1*0901 and 1501, HLA-DQB1*0301 and 0602 alleles and esophageal squamous cell carcinoma of Kazakh in Xinjiang, China].

Objective: To investigate the polymorphism of HLA-DRB1 and DQB1 allele in esophageal squamous cell carcinomas of Kazakh in Xinjiang, and to characterize susceptible genes for the family of Kazakh esophageal squamous cell carcinoma.

Methods: HLA-DRB1*0901, DRB1*1501, DQB1*0301, DQB1*0602 alleles were genotyped by sequence specific primers using polymerase chain reaction (PCR-SSP) in 200 Kazakh esophageal squamous cell carcinoma and 177 normal esophageal mucosa.

Results: The frequency of HLA-DRB1*1501, HLA-DQB1*0301, HLA-DQB1*0602 alleles in 200 Kazakh esophageal squamous cell carcinoma (0.

[Notch1 mRNA and protein expression in human breast cancer and normal mammary gland tissues].

Objective: To explore the Notch1 mRNA and protein expression in human breast cancers and normal mammary tissues, and their relationship with the clinical indicators of breast cancers were analyzed.

Methods: Notch1 gene of human breast invasive ductal carcinoma (IDC) and normal mammary gland tissues were amplified by RT-PCR, and the expression of Notch1 protein was detected by immunohistochemical Streptavidin-Biotin Complex (SP) stain in 60 IDC, 30 ductal carcinoma in situ (DCIS) and 60 normal mammary tissues.

Results: Notch1 gene of human IDC and normal mammary tissues both could express in a transcription level; the positive rates of Notch1 protein expression in normal mammary tissues and DCIS were 55% and 70%.

Phenotypic changes of human cells in human-rat liver during partial hepatectomy-induced regeneration.

Aim: To examine the human hepatic parenchymal and stromal components in rat liver and the phenotypic changes of human cells in liver of human-rat chimera (HRC) generated by in utero transplantation of human cells during partial hepatectomy (PHx)-induced liver regeneration.

Methods: Human hepatic parenchymal and stromal components and phenotypic changes of human cells during liver regeneration were examined by flow cytometry, in situ hybridization and immunohistochemistry.

Results: ISH analysis demonstrated human Alu-positive cells in hepatic parenchyma and stroma of recipient liver.

Chromosomal imbalances revealed in primary rhabdomyo-sarcomas by comparative genomic hybridization.

Background: Previous cytogenetic studies revealed aberrations varied among the three subtypes of rhabdomyosarcoma. We profiled chromosomal imbalances in the different subtypes and investigated the relationships between clinical parameters and genomic aberrations.

Methods: Comparative genomic hybridization was used to investigate genomic imbalances in 25 cases of primary rhabdomyosarcomas and two rhabdomyosarcoma cell lines.

[The effect of formalin-induced pain on CCK in rat spinal cord neurons].

Aim: CCK is one of the strongest endogenous anti-opioid substances and suppresses morphine tolerance which results from long term use of morphine. This study explores the modulatory effect of CCK on pain formalin-induced.

Methods: The effect of formalin-induced pain on CCK immunoreactivity in rat sensory neurons was observed through immunohistochemistry technique.

[Study on clinicopathologic features and immunophenotype of 114 cases of renal cell carcinoma].

Objective: To study the clinicopathologic features and immunophenotype of renal cell carcinomas, and to discuss their diagnostic value.

Methods: The clinicopathologic features of 114 cases of renal cell carcinoma were reviewed and categorized on the basis of 2004 WHO classification. Immunohistochemical study for a panel of antibodies (including CK, CD10, vimentin, CD117, AMACR, CK7 and TFE3) was carried out.

[Comparative genomic hybridization: the profile of chromosomal imbalances in rhabdomyosarcoma].

Objective: To characterize the profile of chromosomal imbalances of rhabdomyosarcoma(RMS).

Methods: Comparative genomic hybridization (CGH) was used to investigate genomic imbalances in 25 cases of primary RMS including 10 cases of alveolar rhabdomyosarcoma (ARM), 12 cases of embryonic rhabdomyosarcoma (ERMS), 3 cases of polymorphic rhabdomyosarcoma (PRMS) and 2 RMS cell lines (A240 originated from ARMS and RD from PRMS), with correlation to histological type, pathologic grading, clinical staging, gender and age, respectively.

Results: All twenty-five rhabdomyosarcomas showed evidence of increased or decreased DNA sequence copy numbers involving one or more regions of the genome.

PAX--FKHR fusion genes and AChR-gamma in Chinese patients with rhabdomyosarcoma: diagnosis using formalin-fixed archival tissues.

The majority of alveolar RMSs have t(2;13)(q35;q14) or (1:13)(p36;q14),which generate PAX3/7 -FKHR fusion genes. Here, the authors detected the PAX3/7-FKHR fusion transcripts in 17 formalin-fixed, paraffin-embedded RMSs and 26 other SRCTs using one-step RT-PCR. PAX3 -FKHR and PAX7-FKHR transcripts were positive in 4/8 and 2/8 cases of ARMS, respectively.

Ethnicity determines association of p53Arg72Pro alleles with cervical cancer in China.

Minority Uigur women residing in Xinjiang, in the northwest of China, have a high incidence of cervical carcinoma (CC; 527/100 000) and are often diagnosed young. We favor the hypothesis that Uigur women may carry different genetic factor(s) making them more susceptible to CC than majority Han (Chinese) women living in the same region. Using PCR-restriction fragment length polymorphism, we investigated associations of a p53Arg72Pro polymorphism with CC in Uigur women compared with those in Han women.