Search

Your search keyword '"Zhang, Xueli"' showing total 1,165 results
Start Over Author "Zhang, Xueli" Search Limiters Full Text
1,165 results on '"Zhang, Xueli"'

9. miR-let-7a inhibits sympathetic nerve remodeling after myocardial infarction by downregulating the expression of nerve growth factor

Author

Jing Yanyan, Qi Lei, Zhang Xueli, Zheng Lu, Yang Peijin, Yin Jie, Shi Yugen, and Yan Suhua

Subjects
mir-let-7a, nerve growth factor, macrophages, sympathetic neural remodeling, myocardial infarction, Medicine
Abstract

Sympathetic hyperinnervation following myocardial infarction (MI) is one of the primary causes of ventricular arrhythmias (VAs) after MI. Nerve growth factor (NGF) is a key molecule that induces sympathetic nerve remodeling. Previous studies have confirmed that microRNA (miR)-let-7a interacts with NGF. However, whether miR-let-7a is involved in sympathetic remodeling after MI remains unknown. We aimed to investigate whether miR-let-7a was associated with the occurrence of VA after MI.

Published
2024
Full Text
View/download PDF

12. A Computer-Aided Diagnosis System for Breast Pathology: A Deep Learning Approach with Model Interpretability from Pathological Perspective

Author

Hsu, Wei-Wen, Wu, Yongfang, Hao, Chang, Hou, Yu-Ling, Gao, Xiang, Shao, Yun, Zhang, Xueli, He, Tao, and Tai, Yanhong

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

Objective: We develop a computer-aided diagnosis (CAD) system using deep learning approaches for lesion detection and classification on whole-slide images (WSIs) with breast cancer. The deep features being distinguishing in classification from the convolutional neural networks (CNN) are demonstrated in this study to provide comprehensive interpretability for the proposed CAD system using pathological knowledge. Methods: In the experiment, a total of 186 slides of WSIs were collected and classified into three categories: Non-Carcinoma, Ductal Carcinoma in Situ (DCIS), and Invasive Ductal Carcinoma (IDC). Instead of conducting pixel-wise classification into three classes directly, we designed a hierarchical framework with the multi-view scheme that performs lesion detection for region proposal at higher magnification first and then conducts lesion classification at lower magnification for each detected lesion. Results: The slide-level accuracy rate for three-category classification reaches 90.8% (99/109) through 5-fold cross-validation and achieves 94.8% (73/77) on the testing set. The experimental results show that the morphological characteristics and co-occurrence properties learned by the deep learning models for lesion classification are accordant with the clinical rules in diagnosis. Conclusion: The pathological interpretability of the deep features not only enhances the reliability of the proposed CAD system to gain acceptance from medical specialists, but also facilitates the development of deep learning frameworks for various tasks in pathology. Significance: This paper presents a CAD system for pathological image analysis, which fills the clinical requirements and can be accepted by medical specialists with providing its interpretability from the pathological perspective.

Published
2021

35. Combustion performance of sub-nanometer Pd/S-1 catalyst for ventilation air methane

Author

Zhang Xueli, Zhu Tao, Yuan Bo, Li Chen, Wang Meidan, and Zhang Baixuan

Subjects
methane catalytic oxidation, pd cluster catalyst, silicalite-1 molecular sieve, catalytic mechanism, Engineering geology. Rock mechanics. Soil mechanics. Underground construction, TA703-712, Mining engineering. Metallurgy, TN1-997
Abstract

Coal mining leads to ventilation air methane emission, which not only pollutes the environment but also runs counter to "carbon neutral, carbon peaking" in China.This study prepared a sub-nanometer Pd cluster catalyst encapsulated in the Silicalite-1 molecular sieve support by the one-pot hydrothermal method, which has excellent catalytic activity and stability in methane catalytic oxidation reaction.The physical phase composition, pore structure parameters, microscopic morphology, chemical state and the present state of the active component Pd of the catalytic material were characterized by XRD, BET, SEM, XPS and TEM.This study then investigated the effects of active component loading, air velocity, reaction temperature and other conditions on the catalytic performance.The experimental results showed that the one-pot hydrothermal method successfully encapsulate Pd clusters within the pores of Silicalite-1 molecular sieve carriers to prepare highly dispersed sub-nanometer Pd cluster catalysts; the catalytic performance first increases and then decreases with the increase of Pd loading.This was due to the agglomeration effect between Pd atoms, resulting in the encapsulation of some Pd atoms and reducing the contact area between the active component and the reactants; in addition, using Silicalite-1 molecular sieve as a carrier can promote the conversion of active site skeletal oxygen to surface hydroxyl groups, which contributes to the catalytic oxidation of methane.The catalyst in this study excels existing methane catalytic process for its high catalytic activity, simple preparation, and low processing cost.

Published
2023
Full Text
View/download PDF

40. Understanding the Mechanism of Deep Learning Framework for Lesion Detection in Pathological Images with Breast Cancer

Author

Hsu, Wei-Wen, Chen, Chung-Hao, Hoa, Chang, Hou, Yu-Ling, Gao, Xiang, Shao, Yun, Zhang, Xueli, Wang, Jingjing, He, Tao, and Tai, Yanghong

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

The computer-aided detection (CADe) systems are developed to assist pathologists in slide assessment, increasing diagnosis efficiency and reducing missing inspections. Many studies have shown such a CADe system with deep learning approaches outperforms the one using conventional methods that rely on hand-crafted features based on field-knowledge. However, most developers who adopted deep learning models directly focused on the efficacy of outcomes, without providing comprehensive explanations on why their proposed frameworks can work effectively. In this study, we designed four experiments to verify the consecutive concepts, showing that the deep features learned from pathological patches are interpretable by domain knowledge of pathology and enlightening for clinical diagnosis in the task of lesion detection. The experimental results show the activation features work as morphological descriptors for specific cells or tissues, which agree with the clinical rules in classification. That is, the deep learning framework not only detects the distribution of tumor cells but also recognizes lymphocytes, collagen fibers, and some other non-cell structural tissues. Most of the characteristics learned by the deep learning models have summarized the detection rules that can be recognized by the experienced pathologists, whereas there are still some features may not be intuitive to domain experts but discriminative in classification for machines. Those features are worthy to be further studied in order to find out the reasonable correlations to pathological knowledge, from which pathological experts may draw inspirations for exploring new characteristics in diagnosis., Comment: v1

Published
2019

48. Featured Cover

Author

Shang, Xianwen, primary, Liu, Jiahao, additional, Zhu, Zhuoting, additional, Zhang, Xueli, additional, Huang, Yu, additional, Liu, Shunming, additional, Wang, Wei, additional, Zhang, Xiayin, additional, Ma, Shuo, additional, Tang, Shulin, additional, Hu, Yijun, additional, Ge, Zongyuan, additional, Yu, Honghua, additional, and He, Mingguang, additional

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results