Search

Your search keyword '"Liu, Wenjin"' showing total 781 results
Start Over Author "Liu, Wenjin"
781 results on '"Liu, Wenjin"'

5. Heterogeneous Graph-Based Multimodal Brain Network Learning

Author

Shi, Gen, Zhu, Yifan, Liu, Wenjin, Yao, Quanming, and Li, Xuesong

Subjects
Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing, Quantitative Biology - Neurons and Cognition
Abstract

Graph neural networks (GNNs) provide powerful insights for brain neuroimaging technology from the view of graphical networks. However, most existing GNN-based models assume that the neuroimaging-produced brain connectome network is a homogeneous graph with single types of nodes and edges. In fact, emerging studies have reported and emphasized the significance of heterogeneity among human brain activities, especially between the two cerebral hemispheres. Thus, homogeneous-structured brain network-based graph methods are insufficient for modelling complicated cerebral activity states. To overcome this problem, in this paper, we present a heterogeneous graph neural network (HebrainGNN) for multimodal brain neuroimaging fusion learning. We first model the brain network as a heterogeneous graph with multitype nodes (i.e., left and right hemispheric nodes) and multitype edges (i.e., intra- and interhemispheric edges). Then, we propose a self-supervised pretraining strategy based on a heterogeneous brain network to address the potential overfitting problem caused by the conflict between a large parameter size and a small medical data sample size. Our results show the superiority of the proposed model over other existing methods in brain-related disease prediction tasks. Ablation experiments show that our heterogeneous graph-based model attaches more importance to hemispheric connections that may be neglected due to their low strength by previous homogeneous graph models. Other experiments also indicate that our proposed model with a pretraining strategy alleviates the problem of limited labelled data and yields a significant improvement in accuracy.

Published
2021

7. Deep Open Snake Tracker for Vessel Tracing

Author

Chen, Li, Liu, Wenjin, Balu, Niranjan, Mossa-Basha, Mahmud, Hatsukami, Thomas S., Hwang, Jenq-Neng, and Yuan, Chun

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

Vessel tracing by modeling vascular structures in 3D medical images with centerlines and radii can provide useful information for vascular health. Existing algorithms have been developed but there are certain persistent problems such as incomplete or inaccurate vessel tracing, especially in complicated vascular beds like the intracranial arteries. We propose here a deep learning based open curve active contour model (DOST) to trace vessels in 3D images. Initial curves were proposed from a centerline segmentation neural network. Then data-driven machine knowledge was used to predict the stretching direction and vessel radius of the initial curve, while the active contour model (as human knowledge) maintained smoothness and intensity fitness of curves. Finally, considering the nonloop topology of most vasculatures, individually traced vessels were connected into a tree topology by applying a minimum spanning tree algorithm on a global connection graph. We evaluated DOST on a Time-of-Flight (TOF) MRA intracranial artery dataset and demonstrated its superior performance over existing segmentation-based and tracking-based vessel tracing methods. In addition, DOST showed strong adaptability on different imaging modalities (CTA, MR T1 SPACE) and vascular beds (coronary arteries)., Comment: MICCAI 2021

Published
2021

19. Landscape of somatic alterations in large-scale solid tumors from an Asian population

Author

Wu, Liqun, Yao, Herui, Chen, Hui, Wang, Aodi, Guo, Kun, Gou, Wenli, Yu, Yanfei, Li, Xiang, Yao, Ming, Yuan, Shaohua, Pang, Fei, Hu, Jinwei, Chen, Lijuan, Liu, Wenjin, Yao, Jicheng, Zhang, Shuirong, Dong, Xiaowei, Wang, Weifeng, Hu, Jing, Ling, Qi, Ding, Songming, Wei, Yan, Li, Qiang, Cao, Weichun, Wang, Shuang, Di, Yang, Feng, Feiling, Zhao, Gang, Zhang, Jian, Huang, Ling, Xu, Jia, Yan, Wangjun, Tong, Zhongsheng, Jiang, Da, Ji, Tao, Li, Qiao, Xu, Ling, He, Huiying, Shang, Liang, Liu, Jin, Wang, Kefeng, Wu, Duoguang, Shen, Jingnan, Liu, Ye, Zhang, Ting, Liang, Chaojie, Wang, Yusheng, Shang, Yanhong, Guo, Jianji, Liang, Guanbiao, Xu, Shifeng, Liu, Junfeng, Wang, Kai, and Wang, Minghui

Published
2022
Full Text
View/download PDF

33. A Fast Tacho-Less Order Tracking Method for Gear Fault Diagnosis Under Large Rotational Speed Variation Conditions Based on Multi-stage Generalized Demodulation

Author

Zhou, Qi, Liu, Wenjin, Wu, Chaoqun, Ceccarelli, Marco, Series Editor, Hernandez, Alfonso, Editorial Board Member, Huang, Tian, Editorial Board Member, Takeda, Yukio, Editorial Board Member, Corves, Burkhard, Editorial Board Member, Agrawal, Sunil, Editorial Board Member, and Tan, Jianrong, editor

Published
2020
Full Text
View/download PDF

39. Discovery of N-Substituted Acetamide Derivatives as Promising P2Y14R Antagonists Using Molecular Hybridization Based on Crystallographic Overlay

Author

Liu, Wenjin, Mao, Shuqiang, Wang, Yuyang, Wang, Mingzhu, Li, Mengyu, Sun, Moran, Yao, Yongfang, Song, Chuanjun, and Duan, Yongtao

Abstract

P2Y14receptor (P2Y14R) is activated by uridine 5′-diphosphate-glucose, which is involved in many human inflammatory diseases. Based on the molecular docking analysis of currently reported P2Y14R antagonists and the crystallographic overlap study between the reported P2Y14R antagonist compounds 6and 9, a series of N-substituted-acetamide derivatives were designed, synthesized, and identified as novel and potent P2Y14R antagonists. The most potent antagonist, compound I-17(N-(1H-benzo[d]imidazol-6-yl)-2-(4-bromophenoxy)acetamide, IC50= 0.6 nM) without zwitterionic character, showed strong binding ability to P2Y14R, high selectivity, moderate oral bioactivity, and improved pharmacokinetic profiles. In vitroand in vivoevaluation demonstrated that compound I-17had satisfactory inhibitory activity on the inflammatory response of monosodium urate (MSU)-induced acute gouty arthritis. I-17decreased inflammatory factor release and cell pyroptosis through the NOD-like receptor family pyrin domain-containing 3 (NLRP3)/gasdermin D (GSDMD) signaling pathway. Thus, compound I-17, with potent P2Y14R antagonistic activity, in vitroand in vivoefficacy, and favorable bioavailability (F= 75%), could be a promising lead compound for acute gouty arthritis.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results