检索结果-内蒙古大学图书馆

Computational Intelligence (ICCI),International conference on

作者： Hia Yee May Ferda Ernawan Faculty of Computing Universiti Malaysia Pahang Gambang Kuantan Malaysia

ISBN: (数字)9781728184081

ISBN: (纸本)9781728184104

Vein visualization is one of the most researched biomedical technique. Although the concept behind the technique is not complicated, the vein pattern acquisition method and the design and implementation of image processing algorithms become challenging. Nowadays, the major challenge faced by the medical practitioners is the difficulty in accessing subcutaneous veins for intra-venous injections due to various factors like low visibility of vein by naked eyes and patients with too narrow veins. Failure during venipuncture may lead to several problems like bruises, bleeding and rashes. Therefore, the real time vein visualization system is developed accordance with the objective of visualizing subcutaneous veins which is to assist medical practitioners by providing them visual guidance during venipuncture process. This system is developed based on near-infrared imaging and is connected to the monitor screen. The development stage includes edge detection, vein segmentation and vein visualization. Evolutionary prototyping method is used to develop the system and to ensure the quality of the final system through a few prototype refinement cycles. OpenCV library is also used for its real-time functionalities. The functionality of the system is evaluated through a series of planned system tests. The experimental results show that the proposed system is able to show the veins pattern.

关键词： visualization Veins Prototypes Real-time systems Skin Monitoring biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Visual analysis of regional myocardial motion anomalies in longitudinal studies

引用

COMPUTERS & GRAPHICS-UK 2019年 83卷 62-76页

作者： Sheharyar, Ali Ruh, Alexander Aristova, Maria Scott, Michael Jarvis, Kelly Elbaz, Mohammed Dolan, Ryan Schnell, Susanne Lin, Kai Carr, James Markl, Michael Bouhali, Othmane Linsen, Lars Texas A&M Univ Qatar Doha Qatar Westfalische Wilhelms Univ Munster Munster Germany Northwestern Univ Feinberg Sch Med Chicago IL 60611 USA

A heart-transplanted patient is at risk of developing several complications such as rejection, which is one of the leading causes of deaths in the first year after the transplant. The regional myocardial motion is known to be depressed early on during rejection before the reduction in global systolic function. Therefore, early detection of regional anomalies is crucial. We use a magnetic resonance (MR) imaging method called tissue phase mapping (TPM) to capture regional myocardial motion of heart-transplanted patients in a longitudinal study. We compare the individual scans of the longitudinal study to a cohort of healthy volunteers to detect anomalies. We use a spatio-temporal visualization based on a radial layout where myocardial regions are laid out in an angular pattern similar to the American Heart Association (AHA) model and where the temporal dimension increases with increasing radius. We compute nested envelopes of central regions for the time series of each region and each of the three velocity directions using the concept of functional boxplots. We propose visual encodings to analyze regional anomalies of a scan of an individual patient dataset and perform a qualitative user study with medical experts. We extend this layout to the visual analysis of longitudinal data to monitor changes in regional anomalies of a patient for multiple scans taken at different times. We apply our approach to data from a longitudinal study of patients under observation after a heart-transplant procedure and evaluate this mechanism with medical and non-medical experts. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： biomedical visualization Myocardial motion Heart transplant

来源：评论

学校读者我要写书评

暂无评论

VRvisu++: A Tool for Virtual Reality-Based visualization of MRI Images

VRvisu++: A Tool for Virtual Reality-Based Visualization of ...

引用

IEEE Annual International Computer Software and Applications conference (COMPSAC)

作者： Sandeep Reddivari Jason Smith University of North Florida School of Computing

ISBN: (数字)9781728173030

ISBN: (纸本)9781728173047

With the emergence of sophisticated head-mounted displays (HMDs), virtual reality (VR) is gaining much interest in the field of medical science and diagnosis. There exist many software tools that support MRI imaging in 3D, however, limited attention has been paid to the VR domain. In this paper, we present a VR tool called VR visu++ which attempts to bring the spatial advantage that VR has to offer to MRI imaging. This tool allows doctors and medical practitioners to directly interact with MRI images in a VR environment thereby supporting surgical training and clinical decision making.

关键词： Rendering (computer graphics) Tools Magnetic resonance imaging biomedical imaging Three-dimensional displays Data visualization Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Medical Image Registration via Similarity Measure based on Convolutional Neural Network

Medical Image Registration via Similarity Measure based on C...

引用

International conference on Cloud Technologies and Applications (CloudTech)

作者： Li Dong Yongzheng Lin Yishen Pang Shandong Medical College Jinan China School of Information Science and Engineering University of Jinan Jinan China Dean’s Office Laiwu Technician College Laiwu China

ISBN: (数字)9781728161754

ISBN: (纸本)9781728161761

Registration, which is exploited to establish the corresponding relationship between a group of images, is of importance for medical applications. Within the image processing process, a similarity measure is an essential stage. To note that the effectiveness of similarity measure is to evaluate the discrepancy between a set of image slices, which greatly affects the performance of registration. Most of the previous algorithms can be categorized in model-based methods, which rely on their suitability to the images. Meanwhile, these similarity measures can not satisfy the requirements of efficiency and accuracy in medical image registration. To address the above-mentioned problems, one novel similarity measure is presented with a convolutional neural network. Experiments were conducted to evaluate the proposed similarity measure with two public DIARETDB1 and RIRE. The numerical and visual outcome both support our work.

关键词： Image registration Cloud computing visualization biomedical equipment Medical services Convolutional neural networks biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Interactive Dendritic Spine Analysis Based on 3D Morphological Features

Interactive Dendritic Spine Analysis Based on 3D Morphologic...

引用

16th IEEE Symposium on visualization for Cyber Security (VizSec) / IEEE visualization conference (IEEE VIS)

作者： Choi, JunYoung Lee, Sang-Eun Cho, Eunji Kashiwagi, Yutaro Okabe, Shigeo Chang, Sunghoe Jeong, Won-Ki Ulsan Natl Inst Sci & Technol Ulsan South Korea Seoul Natl Univ Coll Med Seoul South Korea Univ Tokyo Tokyo Japan

ISBN: (纸本)9781728149417

Dendritic spines are submicron scale protrusions on neuronal dendrites that form the postsynaptic sites of excitatory neuronal inputs. The morphological changes of dendritic spines reflect alterations in physiological conditions and are further indicators of various neuropsychiatric conditions. However, due to the highly dynamic and heterogeneous nature of spines, accurate measurement and object analysis of spine morphology is a major challenge in neuroscience research. Here, we propose an interactive 3D dendritic spine analysis system that displays 3D rendering of spines and plots the high-dimensional features extracted from the 3D mesh of spines in three graph types (parallel coordinate plot, radar plot, and 2D scatter plot with t-Distributed Stochastic Neighbor Embedding). With this system, analysts can effectively explore and analyze the dendritic spine in a 3D manner with high-dimensional features. For the system, we have constructed a set of morphological high-dimensional features from the 3D mesh of dendritic spines.

关键词： biomedical and Medical visualization Coordinated and Multiple Views User Interfaces

来源：评论

学校读者我要写书评

暂无评论

Explainable Deep Learning Methods for Medical Imaging Applications

Explainable Deep Learning Methods for Medical Imaging Applic...

引用

International conference on computing, Communication & Automation (ICCCA)

作者： Sunil Kumar Vuppala Madhumita Behera He Jack Nagaraju Bussa Philips Research Philips India Ltd Bangalore India Philips USA Cambridge Philips India Ltd Bangalore India

ISBN: (数字)9781728163246

ISBN: (纸本)9781728163253

This paper discusses explainable deep learning approaches for medical imaging applications. This includes evaluation of three different feature visualization approaches for visualizing deep neural network models, developed with medical domain images. The idea behind using these approaches is to unbox the internals of deep neural network, specifically convolutional neural networks (CNN) by providing a step by step learning of these models. These approaches could help clinicians to have confidence in complex deep learning models, as opposed to treating those as black boxes as these approaches can generate a meaningful view of the model layers and their feature maps. Also, these approaches can be adopted by data scientists to improve their model performances by looking at the model behavior in each layer. We have implemented three approaches namely Activation Map, Deconvolution and Grad-CAM localization in Keras with Tensorflow background and have validated the results with CNN models developed with natural images. We have also been able to generate these visualizations for models with even filter sizes with activation map and deconvolution approaches. These methods play crucial role in getting approval from regulatory authorities.

关键词： Deep learning visualization Deconvolution Neural networks Tools Data models biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

BISR-RNAseq: an efficient and scalable RNAseq analysis workflow with interactive report generation

引用

BMC BIOINFORMATICS 2019年第1期20卷 1-7页

作者： Gadepalli, Venkat Sundar Ozer, Hatice Gulcin Yilmaz, Ayse Selen Pietrzak, Maciej Webb, Amy Ohio State Univ Biomed Informat Columbus OH 43210 USA Ohio State Univ James Comprehens Canc Ctr Columbus OH 43210 USA Ohio State Univ Bioinformat Shared Resource Grp Columbus OH 43210 USA

Background: RNA sequencing has become an increasingly affordable way to profile gene expression patterns. Here we introduce a workflow implementing several open-source softwares that can be run on a high performance computing environment. Results: Developed as a tool by the Bioinformatics Shared Resource Group (BISR) at the Ohio State University, we have applied the pipeline to a few publicly available RNAseq datasets downloaded from GEO in order to demonstrate the feasibility of this workflow. Source code is available here: workflow: https://***/gadepalli.3/BISR-RNAseq-ICIBM2019 and shiny: https://***/gadepalli.3/BISR_RNASeq_ICIBM19. Example dataset is demonstrated here: https://***/RNA_Seq/. Conclusion: The workflow allows for the analysis (alignment, QC, gene-wise counts generation) of raw RNAseq data and seamless integration of quality analysis and differential expression results into a configurable R shiny web application.

关键词： RNAseq Transcriptome Workflow visualization

来源：评论

学校读者我要写书评

暂无评论

Topology Control in Power System Using visualization

Topology Control in Power System Using Visualization

引用

IEEE Milan PowerTech conference

作者： Fu, Rao Oh, Hyungscon Grinberg, Ilya SUNY Univ Buffalo Dept Elect Engn Buffalo NY 14260 USA SUNY Buffalo State Engn Technol Dept Buffalo NY USA

ISBN: (纸本)9781538647226

Topology control (TC) issues would require applying mixed integer linear programming (MILP) or mixed integer non-linear programming (MINLP) to resolve. This paper strives to explore a new way to solve the TC problem. visualization in scientific computing aims to provide visualized interaction between simulation and computation so that researchers can more intuitively observe the science laws of the object. Relying on humans powerful visual ability, valuable information can be found from the graphical results, and ultimately lead to the best solution. In transmission network, it is proposed that, from the parallel coordinates of the load changing, all the possible switching options can be obtained. Among these options, the best switching line is included, and possible switching options can be greatly reduced. IEEE 30-bus case for transmission system is utilized in this research. Contour plots for voltage profiles are applied to verify selections from parallel coordinates out of all 41 branches.

关键词： parallel coordinates optimal topology control visualization voltage contour plot

来源：评论

学校读者我要写书评

暂无评论

Mobile Trolley for Medical Applications

Mobile Trolley for Medical Applications

引用

International conference on computing, Engineering, and Design (ICCED)

作者： N. M. Saad R. Sudirman A. R. Abdullah N. A. Hamid C. Omar M. I. A. Sabri Fakulti Teknologi Kejuruteraan Elektrik & Elektronik Universiti Teknikal Malaysia Melaka Melaka Malaysia Fakulti Kejuruteraan Sekolah Kejuruteraan Elektrik Universiti Teknologi Malaysia Skudai Johor Malaysia Fakulti Keiuruteraan Elektrik Universiti Teknikal Malaysia Melaka Melaka Malaysia Fakulti Kejuruteraan Elektronik & Kejuruteraan Komputer Universiti Teknikal Malaysia Melaka Melaka Malaysia Lönge Medikal Sdn. Bhd. Lab 1Co9P MTDC-UPM Serdang Selangor Malaysia

This paper provides a mobile apparatus for medical application which comprises a medical trolley, automatic guidance, a wireless controller, human follower using ultrasonic sensors, an obstacle avoiding detection device, an IP camera, a smartphone touch screen controller, an integrated power supply, and a processor. The trolley with stainless steel shelves is ideal for use in clinical environments and operation theatres. The wireless remote drives the trolley to move forward and backward. An IP camera is attached to the trolley to provide visual guidance controlled using a smartphone. The system uses ultrasonic sensors for human follower. Arduino Development Board is used as the processor for the automated mobile trolley system. The implementation of the system can save a large amount of space. The workload of medical workers will be greatly relieved and the working efficiency can be improved.

关键词： Wireless communication Wireless sensor networks biomedical equipment visualization Surgery Medical services Cameras

来源：评论

学校读者我要写书评

暂无评论

computing conference, 2019

Computing Conference, 2019

引用

computing conference, 2019

ISBN: (纸本)9783030228675

The proceedings contain 78 papers. The special focus in this conference is on computing. The topics include: Performance Analysis of Square-Shaped and Star-Shaped Hierarchically Modulated Signals Generated Using All-Optical Techniques;Dynamic Bit Loading with the OGFDM Waveform Maximises Bit-Rate of Future Mobile Communications;n-means: Adaptive Clustering Microaggregation of Categorical Medical Data;The Two Separate Optical Fibres Approach in computing with 3NLSE–Domain Optical Solitons;Intra-channel Interference Avoidance with the OGFDM Boosts Channel Capacity of Future Wireless Mobile Communication;decomposition of a Non-stationary Process Using Time-Dependent Components;open Source Firmware Customization Problem: Experimentation and Challenges;an Entity-Based Black-Box Specification Approach for Modeling Wireless Community Network Services;Downlink High Quality 72 GHz Millimeter;study the Performance of Optical Millimetre Wave Based on Carrier Suppressed by Using an Inverted Optical Filter;visualization: A Tool to Study Nodes in Multi-dimensional Networks;the Nigerian E-Waste Problem: Way Forward;high-Throughput Electronic Band Structure Calculations for Hexaborides;an Efficient Density-Based Clustering Algorithm Using Reverse Nearest Neighbour;Switched-Current Sampled and Hold Circuit with Digital Noise Cancellation Circuit for 2+2 MASH ƩΔ Modulator;refinement and Trust Modeling of Spatio-Temporal Big Data;data Analytics: A Demographic and Socioeconomic Analysis of American Cigarette Smoking;designing a System for Integration of Macroeconomic and Statistical Data Based on Ontology;a Modified Cultural Algorithm for Feature Selection of biomedical Data;Exploring Scientists’ Research Behaviors Based on LDA;hybrid of Filters and Genetic Algorithm - Random Forests Based Wrapper Approach for Feature Selection and Prediction;a New Arabic Dataset for Emotion Recognition;capabilities of Email Forensic Tools.

关键词：

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：