Search

Your search keyword '"Zheng, Junfeng"' showing total 327 results
Start Over Author "Zheng, Junfeng"
327 results on '"Zheng, Junfeng"'

20. 3D Dilated Multi-Fiber Network for Real-time Brain Tumor Segmentation in MRI

Author

Chen, Chen, Liu, Xiaopeng, Ding, Meng, Zheng, Junfeng, and Li, Jiangyun

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Brain tumor segmentation plays a pivotal role in medical image processing. In this work, we aim to segment brain MRI volumes. 3D convolution neural networks (CNN) such as 3D U-Net and V-Net employing 3D convolutions to capture the correlation between adjacent slices have achieved impressive segmentation results. However, these 3D CNN architectures come with high computational overheads due to multiple layers of 3D convolutions, which may make these models prohibitive for practical large-scale applications. To this end, we propose a highly efficient 3D CNN to achieve real-time dense volumetric segmentation. The network leverages the 3D multi-fiber unit which consists of an ensemble of lightweight 3D convolutional networks to significantly reduce the computational cost. Moreover, 3D dilated convolutions are used to build multi-scale feature representations. Extensive experimental results on the BraTS-2018 challenge dataset show that the proposed architecture greatly reduces computation cost while maintaining high accuracy for brain tumor segmentation. The source code can be found at https://github.com/China-LiuXiaopeng/BraTS-DMFNet

Published
2019

29. The autoimmune disease risk variant NCF1-His90 is associated with a reduced risk of tuberculosis in women.

Author

Hu, Xinjun, Li, Shasha, Huang, Renliang, Fu, Ziwei, Ma, Chenyu, Cheng, Zheng, Hu, Hongjun, Zhou, Qiaomiao, Petersen, Frank, Yu, Xinhua, and Zheng, Junfeng

Subjects
LEUKOCYTES, SYSTEMIC lupus erythematosus, SJOGREN'S syndrome, COMMUNICABLE diseases, NADPH oxidase
Abstract

Introduction: The neutrophil cytosolic factor 1 (NCF1) rs201802880 polymorphism is a missense mutation resulting in an amino acid substitution from arginine to histidine at position 90, which impairs the function of NADPH oxidase. This casual variant confers an increased risk for multiple autoimmune disorders, including primary Sjögren's syndrome and systemic lupus erythematosus. Given the high prevalence of this autoimmune disease risk variant in East Asia, we hypothesized that it may confer an evolutionary advantage by providing protection against infectious diseases. Methods: To test this hypothesis, we investigated whether the NCF1 rs201802880 variant offers a protective effect against tuberculosis (TB), a historically significant and deadly infectious disease. Our study included 490 healthy controls and 492 TB patients who were genotyped for the NCF1 rs201802880 polymorphism. Results: Our results showed that the NCF1 rs201802880 AA genotype was associated with a reduced risk of TB in women (OR= 0.25, 95% CI: 0.09-0.68, p =0.0023). Additionally, healthy individuals with the NCF1 rs201802880 AA genotype had significantly lower circulating white blood cell (5.56 ± 1.78 vs 6.43 ± 1.59, p =0.003) and neutrophil (3.23 ± 1.20 vs 3.74 ± 1.23, p = 0.02) counts compared to those with the GG or GA genotypes, with this difference being more pronounced in women than in men. Conclusion: This study demonstrates that the autoimmune disease-causal NCF1 variant is associated with a protective effect against TB infection. [ABSTRACT FROM AUTHOR]

Published
2025
Full Text
View/download PDF

38. Real-Time Semantic Segmentation Network for Edge Deployment

Author

Zheng, Junfeng, Li, Jiangyun, Liu, Yan, Zhang, Weicun, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Liang, Qilian, Series Editor, Martin, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zhang, Junjie James, Series Editor, Jia, Yingmin, editor, Du, Junping, editor, and Zhang, Weicun, editor

Published
2020
Full Text
View/download PDF

44. Quasispecies characteristics of hepatitis B virus full genome in Tibetans studied by the third-generation sequencing

Author

CAI Lin, ZHENG Junfeng, TAN Wenting, and SUN Fengming

Subjects
hepatitis virus b, high-throughput sequencing, third-generation, quasispecies, tibetan nationality, Medicine (General), R5-920
Abstract

Objective To investigate the quasispecies variation characteristics of HBV in Tibetan population based on the third-generation sequencing. Methods An epidemiological investigation of hepatitis B virus was conducted by our department of infectious disease in southern Tibet from May 2016 to July 2017. A total of 24 HBsAg positive subjects were obtained in this investigation and were assignd into the plateau Tibetan group, and then another 24 cases subjected from our outpatient department were recruited and served as the plain Han control group. Their HBV DNA was extracted, and the full virus sequence was amplified to build a whole genome sequencing library, and then sequenced on the third-generation sequencing platform PacBio RSⅡ. Biological information tools such as ClustalW, MEGA and SimPlot were used to analyze the quasispecies characteristics. Results Totally 29 samples were successfully amplified and sequenced finally, including 9 cases from the Tibetan group with an average of 65 quasispecies sequences per sample, and 20 cases from the control group with an average of 124 quasispecies sequences per sample. After comparative analysis, 7 cases (7/9, 77.8%) of typeC/D1 HBV were found in the Tibetan group with recombining at 750 nt by type D4 and type C2 HBV, 1 case of type C/D2 HBV was recombined by type D3 and type C2 HBV at 1 500 nt, and the rest 1 was type C2. The quasispecies complexity and nonsynonymous mutation ratio of HBV preC/C gen was highere in the Tibetan group than the control group. Variation spectrums of nucleic acid were different between the recombinant HBV and the control. The nucleic acid mutation of the C/D recombinant HBV was mainly in EnhⅡ, BCP, and preS regions, while the HBV sequences in the control group were dominated by mutations in preC, S, and X regions besides BCP and preS regions. Conclusion The C/D recombinant strain is the dominant strain of HBV in Tibetans, and C/D1 HBV is more common. The quasispecies complexity and nonsynonymous mutation ratio of HBV preC/C in Tibetans are higher than those of the Han, While the variants of nucleotide mainly occur in the Enh Ⅱ, BCP, and preS regions

Published
2019
Full Text
View/download PDF

46. Image-Based Iron Slag Segmentation via Graph Convolutional Networks

Author

Wang Long, Zheng Junfeng, Yu Hong, Ding Meng, and Li Jiangyun

Subjects
Electronic computers. Computer science, QA75.5-76.95
Abstract

Slagging-off (i.e., slag removal) is an important preprocessing operation of steel-making to improve the purity of iron. Current manual-operated slag removal schemes are inefficient and labor-intensive. Automatic slagging-off is desirable but challenging as the reliable recognition of iron and slag is difficult. This work focuses on realizing an efficient and accurate recognition algorithm of iron and slag, which is conducive to realize automatic slagging-off operation. Motivated by the recent success of deep learning techniques in smart manufacturing, we introduce deep learning methods to this field for the first time. The monotonous gray value of industry images, poor image quality, and nonrigid feature of iron and slag challenge the existing fully convolutional networks (FCNs). To this end, we propose a novel spatial and feature graph convolutional network (SFGCN) module. SFGCN module can be easily inserted in FCNs to improve the reasoning ability of global contextual information, which is helpful to enhance the segmentation accuracy of small objects and isolated areas. To verify the validity of the SFGCN module, we create an industrial dataset and conduct extensive experiments. Finally, the results show that our SFGCN module brings a consistent performance boost for a wide range of FCNs. Moreover, by adopting a lightweight network as backbone, our method achieves real-time iron and slag segmentation. In the future work, we will dedicate our efforts to the weakly supervised learning for quick annotation of big data stream to improve the generalization ability of current models.

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results