Search

Your search keyword '"Xu, Xiangyang"' showing total 2,330 results
Start Over Author "Xu, Xiangyang"
2,330 results on '"Xu, Xiangyang"'

61. Dual-branch residual network for lung nodule segmentation

Author

Cao, Haichao, Liu, Hong, Song, Enmin, Hung, Chih-Cheng, Ma, Guangzhi, Xu, Xiangyang, Jin, Renchao, and Lu, Jianguo

Subjects
Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

An accurate segmentation of lung nodules in computed tomography (CT) images is critical to lung cancer analysis and diagnosis. However, due to the variety of lung nodules and the similarity of visual characteristics between nodules and their surroundings, a robust segmentation of nodules becomes a challenging problem. In this study, we propose the Dual-branch Residual Network (DB-ResNet) which is a data-driven model. Our approach integrates two new schemes to improve the generalization capability of the model: 1) the proposed model can simultaneously capture multi-view and multi-scale features of different nodules in CT images; 2) we combine the features of the intensity and the convolution neural networks (CNN). We propose a pooling method, called the central intensity-pooling layer (CIP), to extract the intensity features of the center voxel of the block, and then use the CNN to obtain the convolutional features of the center voxel of the block. In addition, we designed a weighted sampling strategy based on the boundary of nodules for the selection of those voxels using the weighting score, to increase the accuracy of the model. The proposed method has been extensively evaluated on the LIDC dataset containing 986 nodules. Experimental results show that the DB-ResNet achieves superior segmentation performance with an average dice score of 82.74% on the dataset. Moreover, we compared our results with those of four radiologists on the same dataset. The comparison showed that our average dice score was 0.49% higher than that of human experts. This proves that our proposed method is as good as the experienced radiologist., Comment: 24 pages, 6 figures

Published
2019

62. Two-Stage Convolutional Neural Network Architecture for Lung Nodule Detection

Author

Cao, Haichao, Liu, Hong, Song, Enmin, Ma, Guangzhi, Xu, Xiangyang, Jin, Renchao, Liu, Tengying, and Hung, Chih-Cheng

Subjects
Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Early detection of lung cancer is an effective way to improve the survival rate of patients. It is a critical step to have accurate detection of lung nodules in computed tomography (CT) images for the diagnosis of lung cancer. However, due to the heterogeneity of the lung nodules and the complexity of the surrounding environment, robust nodule detection has been a challenging task. In this study, we propose a two-stage convolutional neural network (TSCNN) architecture for lung nodule detection. The CNN architecture in the first stage is based on the improved UNet segmentation network to establish an initial detection of lung nodules. Simultaneously, in order to obtain a high recall rate without introducing excessive false positive nodules, we propose a novel sampling strategy, and use the offline hard mining idea for training and prediction according to the proposed cascaded prediction method. The CNN architecture in the second stage is based on the proposed dual pooling structure, which is built into three 3D CNN classification networks for false positive reduction. Since the network training requires a significant amount of training data, we adopt a data augmentation method based on random mask. Furthermore, we have improved the generalization ability of the false positive reduction model by means of ensemble learning. The proposed method has been experimentally verified on the LUNA dataset. Experimental results show that the proposed TSCNN architecture can obtain competitive detection performance., Comment: 29 pages, 10 figures

Published
2019

66. Research on Digital Process Technology of Radar Typical Parts Based on Model Definition

Author

Wang, Ning, Wang, Jikong, Wang, Guochao, Yu, Tao, Yu, Li, Xu, Xiangyang, Yang, Yang, 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, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, 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, Oneto, Luca, 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, Zamboni, Walter, Series Editor, Zhang, Junjie James, Series Editor, Duan, Baoyan, editor, Umeda, Kazunori, editor, and Kim, Chang-wan, editor

Published
2022
Full Text
View/download PDF

76. The crystal structure of 5-(2-fluoro-3-methoxyphenyl)-1-(2-fluoro-6-(trifluoromethyl)benzyl)-6-methylpyrimidine-2,4(1H,3H)-dione, C20H15F5N2O3

Author

Wu Yundeng, Xie Jun, Wan Hui, Xu Xiangyang, and Li Jian

Subjects
2203655, Physics, QC1-999, Crystallography, QD901-999
Abstract

C20H15F5N2O3, orthorhombic, Pbca (no. 61), a = 10.9913 (4) Å, b = 11.0451(5) Å, c = 30.3925(14) Å, V = 3689.6 (3) Å3, Z = 8, R gt(F) = 0.0360, wR ref(F 2) = 0.0927, T = 170 K.

Published
2022
Full Text
View/download PDF

100. Natural variation in genes potentially involved in plant architecture and adaptation in switchgrass (Panicum virgatum L.)

Author

Bahri, Bochra A, Daverdin, Guillaume, Xu, Xiangyang, Cheng, Jan-Fang, Barry, Kerrie W, Brummer, E Charles, and Devos, Katrien M

Subjects
Biological Sciences, Genetics, Human Genome, Adaptation, Physiological, Base Sequence, Biomass, Chromosome Mapping, Gene Flow, Genes, Plant, Genetic Variation, Genetics, Population, Mutation, Panicum, Phylogeography, Polymorphism, Single Nucleotide, Principal Component Analysis, United States, Single nucleotide polymorphisms, Biomass genes, Selection, Subgenome, Population structure, Evolution, Single nucleotide polymorphisms, Biomass genes, Selection, Subgenome, Population structure, Evolution
Abstract

BackgroundAdvances in genomic technologies have expanded our ability to accurately and exhaustively detect natural genomic variants that can be applied in crop improvement and to increase our knowledge of plant evolution and adaptation. Switchgrass (Panicum virgatum L.), an allotetraploid (2n = 4× = 36) perennial C4 grass (Poaceae family) native to North America and a feedstock crop for cellulosic biofuel production, has a large potential for genetic improvement due to its high genotypic and phenotypic variation. In this study, we analyzed single nucleotide polymorphism (SNP) variation in 372 switchgrass genotypes belonging to 36 accessions for 12 genes putatively involved in biomass production to investigate signatures of selection that could have led to ecotype differentiation and to population adaptation to geographic zones.ResultsA total of 11,682 SNPs were mined from ~ 15 Gb of sequence data, out of which 251 SNPs were retained after filtering. Population structure analysis largely grouped upland accessions into one subpopulation and lowland accessions into two additional subpopulations. The most frequent SNPs were in homozygous state within accessions. Sixty percent of the exonic SNPs were non-synonymous and, of these, 45% led to non-conservative amino acid changes. The non-conservative SNPs were largely in linkage disequilibrium with one haplotype being predominantly present in upland accessions while the other haplotype was commonly present in lowland accessions. Tajima's test of neutrality indicated that PHYB, a gene involved in photoperiod response, was under positive selection in the switchgrass population. PHYB carried a SNP leading to a non-conservative amino acid change in the PAS domain, a region that acts as a sensor for light and oxygen in signal transduction.ConclusionsSeveral non-conservative SNPs in genes potentially involved in plant architecture and adaptation have been identified and led to population structure and genetic differentiation of ecotypes in switchgrass. We suggest here that PHYB is a key gene involved in switchgrass natural selection. Further analyses are needed to determine whether any of the non-conservative SNPs identified play a role in the differential adaptation of upland and lowland switchgrass.

Published
2018

Catalog

Books, media, physical & digital resources
See catalog results