Search

Your search keyword '"Du, Xiaohui"' showing total 854 results
Start Over Author "Du, Xiaohui"
854 results on '"Du, Xiaohui"'

1. UADSN: Uncertainty-Aware Dual-Stream Network for Facial Nerve Segmentation

Author

Zhu, Guanghao, Liu, Lin, Zhang, Jing, Du, Xiaohui, Hao, Ruqian, and Liu, Juanxiu

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

Facial nerve segmentation is crucial for preoperative path planning in cochlear implantation surgery. Recently, researchers have proposed some segmentation methods, such as atlas-based and deep learning-based methods. However, since the facial nerve is a tubular organ with a diameter of only 1.0-1.5mm, it is challenging to locate and segment the facial nerve in CT scans. In this work, we propose an uncertainty-aware dualstream network (UADSN). UADSN consists of a 2D segmentation stream and a 3D segmentation stream. Predictions from two streams are used to identify uncertain regions, and a consistency loss is employed to supervise the segmentation of these regions. In addition, we introduce channel squeeze & spatial excitation modules into the skip connections of U-shaped networks to extract meaningful spatial information. In order to consider topologypreservation, a clDice loss is introduced into the supervised loss function. Experimental results on the facial nerve dataset demonstrate the effectiveness of UADSN and our submodules.

Published
2024

2. AstMatch: Adversarial Self-training Consistency Framework for Semi-Supervised Medical Image Segmentation

Author

Zhu, Guanghao, Zhang, Jing, Liu, Juanxiu, Du, Xiaohui, Hao, Ruqian, Liu, Yong, and Liu, Lin

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

Semi-supervised learning (SSL) has shown considerable potential in medical image segmentation, primarily leveraging consistency regularization and pseudo-labeling. However, many SSL approaches only pay attention to low-level consistency and overlook the significance of pseudo-label reliability. Therefore, in this work, we propose an adversarial self-training consistency framework (AstMatch). Firstly, we design an adversarial consistency regularization (ACR) approach to enhance knowledge transfer and strengthen prediction consistency under varying perturbation intensities. Second, we apply a feature matching loss for adversarial training to incorporate high-level consistency regularization. Additionally, we present the pyramid channel attention (PCA) and efficient channel and spatial attention (ECSA) modules to improve the discriminator's performance. Finally, we propose an adaptive self-training (AST) approach to ensure the pseudo-labels' quality. The proposed AstMatch has been extensively evaluated with cutting-edge SSL methods on three public-available datasets. The experimental results under different labeled ratios indicate that AstMatch outperforms other existing methods, achieving new state-of-the-art performance. Our code will be available at https://github.com/GuanghaoZhu663/AstMatch.

Published
2024

3. Three-Stream Temporal-Shift Attention Network Based on Self-Knowledge Distillation for Micro-Expression Recognition

Author

Zhu, Guanghao, Liu, Lin, Hu, Yuhao, Sun, Haixin, Liu, Fang, Du, Xiaohui, Hao, Ruqian, Liu, Juanxiu, Liu, Yong, Deng, Hao, and Zhang, Jing

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Micro-expressions are subtle facial movements that occur spontaneously when people try to conceal real emotions. Micro-expression recognition is crucial in many fields, including criminal analysis and psychotherapy. However, micro-expression recognition is challenging since micro-expressions have low intensity and public datasets are small in size. To this end, a three-stream temporal-shift attention network based on self-knowledge distillation called SKD-TSTSAN is proposed in this paper. Firstly, to address the low intensity of muscle movements, we utilize learning-based motion magnification modules to enhance the intensity of muscle movements. Secondly, we employ efficient channel attention modules in the local-spatial stream to make the network focus on facial regions that are highly relevant to micro-expressions. In addition, temporal shift modules are used in the dynamic-temporal stream, which enables temporal modeling with no additional parameters by mixing motion information from two different temporal domains. Furthermore, we introduce self-knowledge distillation into the micro-expression recognition task by introducing auxiliary classifiers and using the deepest section of the network for supervision, encouraging all blocks to fully explore the features of the training set. Finally, extensive experiments are conducted on four public datasets: CASME II, SAMM, MMEW, and CAS(ME)3. The experimental results demonstrate that our SKD-TSTSAN outperforms other existing methods and achieves new state-of-the-art performance. Our code will be available at https://github.com/GuanghaoZhu663/SKD-TSTSAN.

Published
2024

6. Machine-Learning-based Colorectal Tissue Classification via Acoustic Resolution Photoacoustic Microscopy

Author

Tong, Shangqing, Ge, Peng, Jiao, Yanan, Ma, Zhaofu, Li, Ziye, Liu, Longhai, Gao, Feng, Du, Xiaohui, and Gao, Fei

Subjects
Statistics - Machine Learning, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Colorectal cancer is a deadly disease that has become increasingly prevalent in recent years. Early detection is crucial for saving lives, but traditional diagnostic methods such as colonoscopy and biopsy have limitations. Colonoscopy cannot provide detailed information within the tissues affected by cancer, while biopsy involves tissue removal, which can be painful and invasive. In order to improve diagnostic efficiency and reduce patient suffering, we studied machine-learningbased approach for colorectal tissue classification that uses acoustic resolution photoacoustic microscopy (ARPAM). With this tool, we were able to classify benign and malignant tissue using multiple machine learning methods. Our results were analyzed both quantitatively and qualitatively to evaluate the effectiveness of our approach.

Published
2023

8. 3D Reconstruction Method of Metal Pipe Inner Wall Based on Multi-camera Sequential Image Acquisition

Author

Zhou, Yuanhao, Chen, Dejun, Ye, Haobin, Wang, Xingguo, Deng, Hao, Wang, Dongdong, Liu, Juanxiu, Du, Xiaohui, Liu, Lin, Zhang, Ping, Zhang, Jing, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, 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, 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, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, 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, Tan, Kay Chen, Series Editor, and Chinese Institute of Command and Control, editor

Published
2024
Full Text
View/download PDF

9. RSTS-YOLOv5: An Improved Object Detector for Drone-Captured Images

Author

Liu, JuanXiu, Li, Jiachen, Hao, Ruqian, Yang, Yanlong, Zhang, JingMing, Wang, Xiangzhou, Lu, Guoming, Zhang, Ping, zhang, Jing, Liu, Yong, Liu, Lin, Wang, Xingguo, Deng, Hao, Wang, Dongdong, Du, Xiaohui, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, 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, 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, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, 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, Tan, Kay Chen, Series Editor, and Chinese Institute of Command and Control, editor

Published
2024
Full Text
View/download PDF

14. A Firefly Algorithm-based Spectral Fitting Technique for Wavelength Modulation Spectroscopy Systems

Author

Zhang, Tingting, Sun, Yongjie, Wang, Pengpeng, Qiu, Yufeng, Wang, Chenxi, Du, Xiaohui, Li, Shaokai, Liu, Haixu, Chu, Tongwei, and Zhu, Cunguang

Subjects
Physics - Instrumentation and Detectors, Physics - Optics
Abstract

This paper proposes a novel calibration-free wavelength modulated spectroscopy (WMS) spectral fitting technique based on the firefly algorithm. The technique by simulating the information interaction behavior between fireflies to achieve the retrieval of gas concentration and laser parameters. Contrasted with the spectral fitting technique based on the classical Levenberg-Marquardt (LM) algorithm, the retrieval of gas concentrations by this technique is weakly dependent on the pre-characterization of the laser parameters. We select the P(13) absorption line of C2H2 at 1532.82 nm as the target spectra and compare the performance of two optimization method (LM and firefly) on gas concentration and laser parameters retrieval by simulation. The simulation results show that the spectral fitting technique based on the firefly algorithm performs better in terms of convergence speed and fitting accuracy, especially in the multi-parameter model without exact characterization.

Published
2022

16. Dynamic Leaching Characteristics of Key Elements in Glass Solidified Body in Surrounding Rock Water

Author

SUN Qi, ZHANG Zhentao, WANG Chenyu, CHAO Hao, DU Xiaohui, ZHANG Yin, LIU Chang

Subjects
fissure filling, high-level glass solidified body, beishan pre-selection area, release of element, Nuclear engineering. Atomic power, TK9001-9401, Nuclear and particle physics. Atomic energy. Radioactivity, QC770-798
Abstract

During the construction stage of the repository, excavation redistributes the stress in the surrounding rock, causes disturbance in the surrounding rock, expands and connects the primary cracks in the rock mass, generates new micro-cracks, increases the permeability coefficient of the rock mass, and causes changes in the composition of groundwater flowing through the deep cracks in the surrounding rock mass, thus affecting the release and migration parameters of nuclides in the glass solidified body. Studies on the effects of multiple barrier media on the release of nuclides were carried out both at home and abroad, and valuable original data were obtained, but there is a lack of studies on the effects of rock fissure fillings on the release of nuclides. In order to obtain the change rule of nuclide release and migration parameters in high-level glass solidified body caused by groundwater intrusion into deep surrounding rock cracks, the migration behavior of nuclide in high-level glass solidified body in saturated water of quartz rock was taken as the research object, the dynamic leaching test was carried out, and the concentration changes of elements B, Re and Si in the leaching solution and the corrosion of high-level glass solidified body were focused. The results show that after 150 days of dynamic leaching test, the ion concentration increases with the increase of reaction time, and the element dissolution in high-level glass solidified body shows identity. Through the formula calculation it can be obtained that the order of the normalized leaching rate is NR(B)>NR(Si)>NR(Re), and the order of the normalized weight loss rate is NL(B)>NL(Si)>NL(Re). When the reaction temperature is 90 ℃, the corrosion rate of the high-level glass solidified body in the geological repository is 540 nm/a with the flow rate of 40 L/(m2·a). After 3 000 years, the corrosion depth of the high-level glass solidified body with a length of 1 350 mm, a diameter of 440 mm, a mass of 400 kg and a surface area of 17 m2 is 1.62 mm. B, Re and Si release 12.24%, 10.41% and 0.18% of total element content, respectively.

Published
2024
Full Text
View/download PDF

19. Advances in Duration of Untreated Psychosis and Its Early Intervention

Author

ZHANG Siyu, ZHOU Yuqiu, DU Xiaohui, WANG Zhengjun

Subjects
mental disorders, schizophrenia, duration of untreated psychosis, early medical intervention, prognosis, review, Medicine
Abstract

Mental illness usually involves a range of cognitive, behavioral, and affective symptoms associated with impaired occupational or social functioning. Duration of untreated psychosis (DUP) is considered as an important predictor and independent risk factor for the prognosis of patients with mental disorders, a longer DUP is associated with poor prognosis. Meanwhile, early intervention measures to shorten DUP have gradually attracted increasing attention from both domestic and international researchers. In this paper, the related studies on DUP were reviewed and analyzed, the concept, measurement tools, neurobiological mechanisms of DUP, the relationship between DUP and prognosis, and early intervention measures to shorten DUP were described, in order to provide ideas and reference for developing clinical intervention strategies for DUP.

Published
2023
Full Text
View/download PDF

24. Interaction analysis of high-risk pathological features on adjuvant chemotherapy survival benefit in stage II colon cancer patients: a multi-center, retrospective study

Author

Li, Kexuan, Zhao, Fuqiang, Guo, Yuchen, Wu, Qingbin, Luo, Shuangling, Zhang, Junling, Li, Heli, Hu, Shidong, Wu, Bin, Lin, Guole, Qiu, Huizhong, Niu, Beizhan, Sun, Xiyu, Xu, Lai, Lu, Junyang, Du, Xiaohui, Wang, Zheng, Wang, Xin, Kang, Liang, Wang, Ziqiang, Wang, Quan, Liu, Qian, and Xiao, Yi

Published
2023
Full Text
View/download PDF

41. Navigating sustainable development: Empirical analysis of corporate social responsibility, eco‐friendly production, and stakeholder green commitment through the lens of stakeholder theory.

Author

Du, Xiaohui, Li, Zhiyong, Bai, Long, and Pan, Lifang

Subjects
SOCIAL responsibility of business, STAKEHOLDER theory, INTERNATIONAL business enterprises, SUSTAINABLE development, CONSUMERS
Abstract

It is enormously crucial to bring sustainable development for multinational corporations by incorporating distinct methods to productively drive businesses sustainably by aligning the corporation's and stakeholders' interests. The study explores the connections among corporate social responsibility, ecological manufacturing, and green buying intentions of external stakeholders such as consumers drawing on the descriptive approach of stakeholder theory. First, this study examines the relationships between corporate social responsibility (CSR) and green purchase intention (GPI). Second, the aim is to explore the moderating connection of ecological manufacturing (EcM) between CSR and GPI. Therefore, data were analyzed based on six hundred and fifty‐five responses being obtained between January 2023 to March 2023 for empirical multidirectional analysis. A positive nexus between CSR and GPI was revealed at the present instant. In addition, the study found a positive moderating influence of ecological manufacturing between the connection of CSR and green purchase intention, respectively. The outcomes spotlight the insights by substantiating that CSR and ecological manufacturing techniques may augment the strength of GPI and can support acquiring ultimate output. Furthermore, this study is equipped with several intriguing and fruitful suggestions for management along with implications. Similarly, some potential possibilities are reported for future investigators by assuming the present imperfections along with additional offerings to execute more research worldwide. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

42. Modeling the Propagation of Extremely Low Frequency Electromagnetic Emissions From the Power Lines to the Inner Magnetosphere in a Dipole Field.

Author

Xu, Xiang, Zhou, Chen, Wang, Zhuangkai, and Du, Xiaohui

Subjects
ELECTRIC lines, MAGNETOSPHERE, COLLISIONLESS plasmas, SPACE plasmas, ELECTRON density, PLASMA density, COLLISIONAL plasma, ATMOSPHERE
Abstract

Different from power line harmonic radiation (PLHR) events at high harmonics (∼kHz) in the ionosphere and inner magnetosphere, the wave dynamics of power line emission (PLE) (the fundamental frequency 50/60 Hz or PLHR at low harmonics) can be significantly affected by various ion species. In order to investigate the evolution of the wave properties of PLE from power lines to satellite altitudes in a dipole field, a numerical model is developed to perform full‐wave simulations, in which the lithosphere and atmosphere are characterized by electrical conductivity and the ionosphere (inner magnetosphere) is treated as collisional (collisionless) cold plasma consisting of electron, H+, He+, O+, and NO+. Our simulation results show that the spatial distribution and wave properties of PLE are determined by the magnetic latitudes of power lines and plasma densities. PLE from power lines at middle and high magnetic latitudes (|MLAT| > 40°) can propagate to high L shells as whistler waves; PLE from power lines at |MLAT| < 30° usually propagate at low L shells below local He+ cyclotron frequency as left‐handedly polarized or right‐handedly He+ band electromagnetic ion cyclotron (EMIC) waves. The amplitude of PLE is usually stronger with smaller electron density in the space plasma medium. With power lines at |MLAT| < 30°, the coupling efficiency between different right‐handedly polarized EMIC wave modes of PLE decreases significantly with electron density. Wave properties of PLE including Poynting vector direction, wave normal angle and wave polarization obtained from our simulation results are consistent with some of the recent observations using Van Allen Probes. Key Points: Model incorporating the effects of lithosphere, atmosphere and space plasma is developed to study the propagation of PLE in a dipole fieldPLE propagate to high L shells as whistlers at |MLAT| > 40° while propagate as left (or right)‐handedly polarized He+ band EMIC at |MLAT| < 30°The PLE amplitude and the coupling efficiency of EMIC wave modes at |MLAT| < 30° decrease with electron density in the space plasma medium [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

48. Remote Sensing Image On-Board Restoration Based on Adaptive Wiener Filter

Author

Wang, Yunsen, Mu, Wenxiu, Du, Xiaohui, Ma, Chengzhi, Shen, Xuejin, 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, 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, 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, Wang, Liheng, editor, Wu, Yirong, editor, and Gong, Jianya, editor

Published
2020
Full Text
View/download PDF

49. Short-term outcomes of complete mesocolic excision versus D2 dissection in patients undergoing laparoscopic colectomy for right colon cancer (RELARC): a randomised, controlled, phase 3, superiority trial

Author

Xu, Lai, Su, Xiangqian, He, Zirui, Zhang, Chenghai, Lu, Junyang, Chen, Lei, Zhang, Guannan, Feng, Bo, Zang, Lu, Ma, Junjun, Sun, Yueming, Feng, Yifei, Ji, Dongjian, Du, Xiaohui, He, Changzheng, Fu, Ze, Chi, Pan, Huang, Ying, Jiang, Weizhong, Wang, Ziqiang, Wu, Qingbin, Zhong, Ming, Yu, Minhao, Wu, Aiwen, Chen, Pengju, Zhu, Anlong, Guan, Wenlong, Wu, Bin, Li, Fei, Li, Ang, Xu, Jianmin, He, Guodong, Kang, Liang, He, Xiaowen, Suo, Jian, Wang, Daguang, Deng, Haijun, Wang, Yanan, Ye, Yingjiang, Shen, Kai, Lin, Guole, Yao, Hongwei, Qiu, Huizhong, Ding, Kefeng, Xu, Tao, Liang, Zhiyong, Zhou, Weixun, Xue, Huadan, Li, Bin, Zhang, Zhongtao, Zheng, Minhua, and Xiao, Yi

Published
2021
Full Text
View/download PDF

50. DIMINISHED EXPRESSION OF GLS IN CD4+T CELLS SERVES AS A PROGNOSTIC INDICATOR ASSOCIATED WITH CUPROPTOSIS IN SEPTIC PATIENTS

Author

Yang, Jiaqi, Chen, Ning, Zhao, Pengyue, Yang, Xingpeng, Li, Yuxuan, Fu, Ze, Yan, Yang, Dong, Ning, Li, Songyan, Yao, Renqi, Du, Xiaohui, and Yao, Yongming

Abstract

Objectives:Sepsis is defined as a life-threatening disease associated with a dysfunctional host immune response. Stratified identification of critically ill patients might significantly improve the survival rate. The present study sought to probe molecular markers associated with cuproptosis in septic patients to aid in stratification and improve prognosis. Methods:We studied expression of cuproptosis-related genes (CRGs) using peripheral blood samples from septic patients. Further classification was made by examining levels of expression of these potential CRGs in patients. Coexpression networks were constructed using the Weighted Gene Coexpression Network Analysis (WGCNA) method to identify crucial prognostic CRGs. Additionally, we utilized immune cell infiltration analysis to further examine the immune status of septic patients with different subtypes and its association with the CRGs. scRNA-seq data were also analyzed to verify expression of key CRGs among specific immune cells. Finally, immunoblotting, flow cytometry, immunofluorescence, and CFSE analysis were used to investigate possible regulatory mechanisms. Results:We classified septic patients based on CRG expression levels and found significant differences in prognosis and gene expression patterns. Three key CRGs that may influence the prognosis of septic patients were identified. A decrease in GLS expression was subsequently verified in Jurkat cells, accompanied by a reduction in O-GlcNAc levels, and chelation of copper by tetrathiomolybdate could not rescue the reduction in GLS and O-GLcNAc levels. Moreover, immoderate chelation of copper was detrimental to mitochondrial function, cell viability, and cell proliferation, as well as the immune status of the host. Conclusion:We have identified novel molecular markers associated with cuproptosis, which could potentially function as diagnostic indicators for septic patients. The reversible nature of the observed alterations in FDX1 and LIAS was demonstrated through copper chelation, whereas the correlation between copper and the observed changes in GLS requires further investigation.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results