检索结果-内蒙古大学图书馆

Corner detection using the point-to-centroid distance technique

IET IMAGE PROCESSING 2020年第14期14卷 3385-3392页

作者： Zhang, Shizheng huangfu, luwen Zhang, Zhifeng huang, Sheng Li, Pu Wang, Heng Zhengzhou Univ Light Ind Software Engn Coll Zhengzhou 450000 Peoples R China San Diego State Univ Fowler Coll Business 5500 Campanile Dr San Diego CA 92182 USA Chongqing Univ Sch Big Data & Software Engn Chongqing 400044 Peoples R China Henan Agr Univ Coll Mech & Elect Engn Zhengzhou 450000 Peoples R China

Corners, highly important local features of images and corner finding, play a crucial role in computer vision and image processing, such as object tracking and vehicle detection. Proposing effective and efficient corner detectors is the aim of corner detection. In this study, the authors first present a new measure of corner sharpness termed as the point-to-centroid distance (PCD) and then examine its behaviours, which display beneficial characteristics that help distinguish corners from non-corners. Based on PCD behaviours, the authors propose a novel corner detector. Extensive experimental results demonstrate that the PCD technique is effective and simultaneously efficient for corner detection compared with six other contour-based corner detectors in terms of two commonly used evaluation metrics - average repeatability and localisation error.

关键词： computer vision edge detection object tracking corner detection corner sharpness corner detector contour-based corner detectors point-to-centroid distance technique corner finding object tracking vehicle detection efficient corner detectors

来源：评论

学校读者我要写书评

暂无评论

Learning to Recognize Thoracic Disease in Chest X-Rays With Knowledge-Guided Deep Zoom Neural Networks

引用

IEEE ACCESS 2020年 8卷 159790-159805页

作者： Wang, Kun Zhang, Xiaohong huang, Sheng Chen, Feiyu Zhang, Xiangbo huangfu, luwen Chongqing Univ Key Lab Dependable Serv Comp Cyber Phys Soc Minist Educ Chongqing 400030 Peoples R China Chongqing Univ Sch Big Data & Software Engn Chongqing 400030 Peoples R China San Diego State Univ Fowler Coll Business San Diego CA 92182 USA

Automatic and accurate thorax disease diagnosis in Chest X-ray (CXR) image plays an essential role in clinical assist analysis. However, due to its imaging noise regions and the similarity of visual features between diseases and their surroundings, the precise analysis of thoracic disease becomes a challenging problem. In this study, we propose a novel knowledge-guided deep zoom neural network (KGZNet) which is a data-driven model. Our approach leverage prior medical knowledge to guide its training process, due to thoracic diseases typically limit within the lung regions. Also, we utilized weakly-supervised learning (WSL) to search for finer regions without using annotated samples. Learning on each scale consists of a classification sub-network. The KGZNet starts from global images, and iteratively generates discriminative part from coarse to fine;while a finer scale sub-network takes as input an amplified attended discriminative region from previous scales in a recurrent way. Specifically, we first train a robust modified U-Net model of lung segmentation and capture the lung area from the original CXR image through the Lung Region Generator. Then, guided by the attention heatmap, we obtain a finer discriminative lesion region from the lung region images by the Lesion Region Generator. Lastly, the most discriminative features knowledge is fused, and the complementary features information is learned for final disease prediction. Extensive experiments demonstrate that our method can effectively leverage discriminative region information, and significantly outperforms the other state-of-the-art methods in the thoracic disease recognition task. Furthermore, the proposed KGZNet can gradually learn the discriminative region from coarse to fine in a mutually reinforced way. The code is will available at: https://***/ISSE-AILab/KGZNet.

关键词： Diseases Lung Feature extraction Lesions X-rays Neural networks Visualization Chest X-ray thoracic disease recognition weakly-supervised learning discriminative feature learning biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Sialic Acid-Functionalized Pyroptosis Nanotuner for Epigenetic Regulation and Enhanced Cancer Immunotherapy

引用

SMALL 2024年第10期20卷 2306905-2306905页

作者： Hu, Jiahao You, Yuchan Zhu, luwen Zhang, Jucong Song, Yanling Lu, Jingyi Xu, Xinyi Wu, Xiaochuan huang, Xiajie Xu, Xiaoling Du, Yongzhong Zhejiang Univ Inst Pharmaceut Coll Pharmaceut Sci 866 Yu-Hang-Tang Rd Hangzhou 310058 Peoples R China Zhejiang Shuren Univ Shulan Int Med Coll 8 Shuren St Hangzhou 310015 Peoples R China Zhejiang Univ Jinhua Inst Innovat Ctr Translat Pharm Jinhua 321299 Peoples R China

The efficacy of immune checkpoint blockade (ICB) in promoting an immune response against tumors still encounters challenges such as low response rates and off-target effects. Pyroptosis, an immunogenic cell death (ICD) mechanism, holds the potential to overcome the limitations of ICB by activating and recruiting immune cells. However, the expression of the pyroptosis-related protein Gasdermin-E(GSDME) in some tumors is limited due to mRNA methylation. To overcome this obstacle, sialic acid-functionalized liposomes coloaded with decitabine, a demethylation drug, and triclabendazole, a pyroptosis-inducing drug are developed. This nanosystem primarily accumulates at tumor sites via sialic acid and the Siglec receptor, elevating liposome accumulation in tumors up to 3.84-fold at 24 h and leading to the upregulation of pyroptosis-related proteins and caspase-3/GSDME-dependent pyroptosis. Consequently, it facilitates the infiltration of CD8+ T cells into the tumor microenvironment and enhances the efficacy of ICB therapy. The tumor inhibition rate of the treatment group is 89.1% at 21 days. This study highlights the potential of sialic acid-functionalized pyroptosis nanotuners as a promising approach for improving the efficacy of ICB therapy in tumors with low GSDME expression through epigenetic alteration and ICD. In this research, an sialic acid-modified coloaded drug liposome encapsulating decitabine and triclabendazole (referred to as SLDT) for tumor immunotherapy is designed. The synergistic effect of this combination therapy is demonstrated. And the further combination therapy using PD-1 antibody and SLDT holds promise in alleviating resistance to immune checkpoint blockade and prolonging survival ***

关键词： cancer immunotherapy combination therapy epigenetics pyroptosis tumor targeting

来源：评论

学校读者我要写书评

暂无评论

Crosstalk between the Gut and Brain in Ischemic Stroke: Mechanistic Insights and Therapeutic Options

引用

MEDIATORS OF INFLAMMATION 2022年第0期2022卷 6508046页

作者： huang, Wenjing Zhu, luwen Song, Wenjing Zhang, Mei Teng, Lili Wu, Minmin Heilongjiang Adm Tradit Chinese Med Harbin 150000 Peoples R China Heilongjiang Univ Chinese Med Hosp 2 Harbin 150000 Peoples R China Heilongjiang Univ Chinese Med Harbin 150000 Peoples R China

There has been a significant amount of interest in the past two decades in the study of the evolution of the gut microbiota, its internal and external impacts on the gut, and risk factors for cerebrovascular disorders such as cerebral ischemic stroke. The network of bidirectional communication between gut microorganisms and their host is known as the microbiota-gut-brain axis (MGBA). There is mounting evidence that maintaining gut microbiota homeostasis can frequently enhance the effectiveness of ischemic stroke treatment by modulating immune, metabolic, and inflammatory responses through MGBA. To effectively monitor and cure ischemic stroke, restoring a healthy microbial ecology in the gut may be a critical therapeutic focus. This review highlights mechanistic insights on the MGBA in disease pathophysiology. This review summarizes the role of MGBA signaling in the development of stroke risk factors such as aging, hypertension, obesity, diabetes, and atherosclerosis, as well as changes in the microbiota in experimental or clinical populations. In addition, this review also examines dietary changes, the administration of probiotics and prebiotics, and fecal microbiota transplantation as treatment options for ischemic stroke as potential health benefits. It will become more apparent how the MGBA affects human health and disease with continuing advancements in this emerging field of biomedical sciences.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Out-of-Distribution Detection Via Exploiting Sparsity and Co-Occurrence of Labels

SSRN

引用

SSRN 2022年

作者： Wang, Lei huang, Sheng huangfu, luwen Liu, Bo Zhang, Xiaohong School of Big Data and Software Engineering Chongqing University Chonqqing 400044 China Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing 400044 China Fowler College of Business Center for Human Dynamics in the Mobile Age San Diego State University San DiegoCA92182 United States JD Finance America Corporation Mountain ViewCA94043 United States

Although Out-Of-Distribution (OOD) detection has been extensively studied, the OOD detection under multi-label settings, which is closer to the real world, is still in its infancy. The pioneer work ignores some unique properties of multi-label images, such as the sparsity and co-occurrence of labels. Here, we empirically observe that these properties readily distinguish OOD and in-distribution data. Motivated by this observation, we propose a novel multi-label OOD detection approach named Sparse Label Co-occurrence Scoring (SLCS) to exploit the sparsity and co-occurrence information of labels. SLCS follows conventions and deems the logits outputted by the penultimate layer of the trained multi-label image classification model as the prediction confidences of a sample to categories in the training label set. A logit sparse filtering process is employed to filter out the low-confidence logits for avoiding the interference of low-confidence predictions while preserving the high-confidence logits to obtain the label sparsity. Then, the label co-occurrence pairs are counted for each sample based on its predicted categories and the label co-occurrence matrix constructed on the training set. Finally, the preserved logits are weighted by the label co-occurrence information and accumulated to produce the OOD detection score for each sample. Extensive experimental results on three well-known multi-label image datasets demonstrate the discriminating power of SLCS, which achieves greatly improved performances compared with the only multi-label OOD detection approach - JointEnergry and the state-of-the-art single-label OOD detection approaches. The performance improvements of SLCS over JointEnergy in FPR95 are 12.85%, 12.41%, and 9.50% on MS-COCO, VOC 2012, and NUS-WIDE datasets *** Out-Of-Distribution (OOD) detection has been extensively studied, the OOD detection under multi-label settings, which is closer to the real world, is still in its infancy. The pione

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Kernel Inversed Pyramidal Resizing Network for Efficient Pavement Distress Recognition

arXiv

引用

arXiv 2022年

作者： Qin, Rong huangfu, luwen Hood, Devon Ma, James huang, Sheng School of Big Data & Software Engineering Chongqing University Chongqing400044 China Fowler College of Business San Diego State University San DiegoCA92182 United States Center for Human Dynamics in the Mobile Age San Diego State University San DiegoCA92182 United States College of Science San Diego State University San DiegoCA92182 United States Department of Business Analysis University of Colorado Colorado SpringsCO80918 United States Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Chongqing400044 China

Pavement Distress Recognition (PDR) is an important step in pavement inspection and can be powered by image-based automation to expedite the process and reduce labor costs. Pavement images are often in high-resolution with a low ratio of distressed to non-distressed areas. Advanced approaches leverage these properties via dividing images into patches and explore discriminative features in the scale space. However, these approaches usually suffer from information loss during image resizing and low efficiency due to complex learning frameworks. In this paper, we propose a novel and efficient method for PDR. A light network named the Kernel Inversed Pyramidal Resizing Network (KIPRN) is introduced for image resizing, and can be flexibly plugged into the image classification network as a pre-network to exploit resolution and scale information. In KIPRN, pyramidal convolution and kernel inversed convolution are specifically designed to mine discriminative information across different feature granularities and scales. The mined information is passed along to the resized images to yield an informative image pyramid to assist the image classification network for PDR. We applied our method to three well-known Convolutional Neural Networks (CNNs), and conducted an evaluation on a large-scale pavement image dataset named CQU-BPDD. Extensive results demonstrate that KIPRN can generally improve the pavement distress recognition of these CNN models and show that the simple combination of KIPRN and EfficientNetB3 significantly outperforms the state-of-the-art patch-based method in both performance and efficiency. © 2022, CC BY-NC-SA.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

The changes of different restriction level adjustments on antibiotic use in China

引用

INTERNATIONAL JOURNAL OF ANTIMICROBIAL AGENTS 2024年第2期63卷 107073-107073页

作者： Du, Kexin Wushouer, Haishaerjiang huang, Tao Zhou, Yue Hu, Lin Yang, Yaoyao Deng, Yanping Zheng, Bo Guan, Xiaodong Shi, luwen Peking Univ Sch Pharmaceut Sci Dept Pharm Adm & Clin Pharm Beijing Peoples R China Peking Univ Int Res Ctr Med Adm IRCMA Beijing Peoples R China Peking Univ Natl Inst Drug Dependence Dept Clin Pharmacol Beijing Peoples R China Peking Univ First Hosp Inst Clin Pharmacol Beijing Peoples R China Peking Univ Sch Pharmaceut Sci Dept Pharm Adm & Clin Pharm 38 Xueyuan Rd Beijing 100191 Peoples R China

This quasi-experimental study aimed to investigate the changes in antibiotic use tailored by adjusting provincial antibiotic restriction lists in China using interrupted time-series analysis from 2013 to 2019. Antibiotic use was assessed as defined daily dose (DDD) per 10 0 0 patients per day. Trends and level changes were analysed with segmented regression. The study identified 19 antibiotic formulations in four provinces with adjusted restriction levels (intervention group) and 110 formulations in the rest provinces without adjustments (comparison group). Antibiotics restriction level changed between two categories: (1) between 'highly-restricted' and 'restricted' and (2) between 'restricted' and 'non-restricted'. Analysis revealed distinct trend changes for antibiotics moving between 'highly-restricted' and 'restricted' ( beta = 0.0211, P = 0.003) and 'restricted' to 'highly-restricted' ( beta = -0.0039, P = 0.128) compared to the comparison group. After a 2-y adjustment period, when moving from 'restricted' to 'highly-restricted', absolute antibiotic utilisation significantly decreased ( P < 0.001), with a relative decrease of 100.8% ( P < 0.001) compared to the comparison group. Besides, individual antibiotics with higher consumption displayed greater responsiveness to adjustment. These findings underscore the changes in restriction level adjustments on antibiotics, highlighting antibiotic restriction list policies as crucial tools for antimicrobial stewardship.

关键词： Antibiotic restriction lists Antibiotic clinical use Interrupted time-series analysis China Antimicrobial stewardship

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Patch Label Inference Network with Image Pyramid for Pavement Diseases Recognition in the Wild

Weakly Supervised Patch Label Inference Network with Image P...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Guixin huang Sheng huang luwen huangfu Dan Yang Chongqing University Chongqing China Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing China San Diego State University San Diego CA USA

ISBN: (纸本)9781728176055;9781728176062

Automatic pavement disease recognition is vital for pavement maintenance and management. In this paper, we present an end-to-end deep learning approach named Weakly Super-vised Patch Label Inference Network with Image Pyramid (WSPLIN-IP) for recognizing various types of pavement diseases that are not just limited to the specific ones, such as crack and pothole. WSPLIN-IP first divides the pavement image into patches with an image pyramid for fully exploiting the resolution and scale information. Then, a Patch Label Inference Network (PLIN) is employed for inferring the labels of these patches constrained with a patch label sparsity loss. Finally, the patch labels are fed into a Comprehensive Decision Network (CDN) for disease recognition. Since only the image label is available during whole training, the training of PLIN is conducted in a weakly supervised way under the guidance of CDN and the trained PLIN can provide the interpretable intermediate information. We evaluate our method on a large-scale Bituminous Pavement Disease Dataset named CQU-BPDD whose samples are acquired in the real world. Extensive results demonstrate the superiority of our method over baselines.

关键词： Training Deep learning Image recognition Image resolution Supervised learning Speech recognition Maintenance engineering

来源：评论

学校读者我要写书评

暂无评论

Network models for mapping educational data

引用

DESIGN SCIENCE 2017年 3卷 e18-e18页

作者： Willcox, Karen E. huang, luwen MIT Dept Aeronaut & Astronaut Cambridge MA 02139 USA

Educational mapping is the process of analyzing an educational system to identify entities, relationships and attributes. This paper proposes a network modeling approach to educational mapping. Current mapping processes in education typically represent data in forms that do not support scalable learning analytics. For example, a curriculum map is usually a table, where relationships among curricular elements are represented implicitly in the rows of the table. The proposed network modeling approach overcomes this limitation through explicit modeling of these relationships in a graph structure, which in turn unlocks the ability to perform scalable analyses on the dataset. The paper presents network models for educational use cases, with concrete examples in curriculum mapping, accreditation mapping and concept mapping. Illustrative examples demonstrate how the formal modeling approach enables visualization and learning analytics. The analysis provides insight into learning pathways, supporting design of adaptive learning systems. It also permits gap analysis of curriculum coverage, supporting student advising, student degree planning and curricular design at scales ranging from an entire institution to an individual course.

关键词： educational mapping curriculum mapping learning analytics concept mapping curriculum design

来源：评论

学校读者我要写书评

暂无评论

2003–2020年中国仿制药上市和新药市场独占期研究

引用

Journal of Chinese Pharmaceutical Sciences 2024年第1期33卷 57-62页

作者：周从亚黄涛顾佳慧李黄倩玉史录文管晓东北京大学药学院药事管理与临床药学系北京100191 北京大学医药管理国际研究中心北京100191

中国近期提出给予新药、孤儿药和儿科药物6年的数据保护期,以鼓励相关药物的研发创新。本研究评估了2003至2020年在中国批准上市的356种新小分子药物的仿制药上市情况和市场独占期。所有新药中,155个(43.5%)新药有仿制药上市,市场独占... 详细信息

中国近期提出给予新药、孤儿药和儿科药物6年的数据保护期,以鼓励相关药物的研发创新。本研究评估了2003至2020年在中国批准上市的356种新小分子药物的仿制药上市情况和市场独占期。所有新药中,155个(43.5%)新药有仿制药上市,市场独占期中位数为5.6(四分位数:2.4–9.4)年。进口药物、口服缓释药物和神经系统药物比其它药物的仿制药上市比例更高(P<0.001,P=0.039,P<0.001)。国产药品的市场独占期中位数比进口药品更长(8.4 vs 5.7年)。市场独占期中位数从抗肿瘤和免疫调节剂的3.6年到消化道和代谢药物的6.8年不等。如果获得6年的数据保护期,新药的市场独占期中位数预计将增加一倍。较长的市场独占期可能降低患者药品可及性,政府在制定相关政策时应考虑在鼓励创新和确保药品可及性间寻求平衡。

关键词：仿制药市场独占期小分子药物新药研发

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：