检索结果-内蒙古大学图书馆

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Markus Perz Gijs Luijten Jens Kleesiek Dieter Schmalstieg Jan Egger Christina Gsaxner Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Institute for Artificial Intelligence in Medicine University Medicine Essen Essen Germany Cancer Research Center Cologne Essen West German Cancer Center Essen Germany Institute for Visualization and Interactive Systems University of Stuttgart Stuttgart Germany Virtual and Extended Reality in Medicine (ZvRM) University Hospital Essen Essen Germany

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

This paper addresses the growing integration of Augmented reality (AR) in biomedical sciences, emphasizing collaborative learning experiences. We present MultiAR, a versatile, domain-specific platform enabling multi-user interactions in AR for biomedical education. Unlike platform-specific solutions, MultiAR supports various AR devices, including handheld and head-mounted options. The framework extends across domains, augmenting biomedical education applications with collaborative capabilities. We define essential requirements for a multi-user AR framework in education, detail MultiAR’s design and implementation, and comprehensively evaluate it using anatomy education examples. Quantitative and qualitative analyses, covering system performance, accuracy metrics, and a user study with 20 participants, highlight the urgent need for a tailored collaborative AR platform in biomedical education. Results underscore enthusiasm for collaborative AR technology, endorsing MultiAR as an accessible, versatile solution for developers and end-users in biomedical education.

关键词： Measurement Accuracy Federated learning System performance Education Collaboration Anatomy Engineering in medicine and biology Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Generalisation of Segmentation Using Generative Adversarial Networks

Generalisation of Segmentation Using Generative Adversarial ...

引用

IEEE International Symposium on Biomedical Imaging

作者： André Ferreira Gijs Luijten Behrus Puladi Jens Kleesiek Victor Alves Jan Egger Institute for AI in Medicine (IKIM) University Hospital Essen (AöR) Essen Germany Center Algoritmi / LASI University of Minho Braga Portugal Computer Algorithms for Medicine Laboratory Graz Austria Institute of Medical Informatics University Hospital RWTH Aachen Aachen Germany Department of Oral and Maxillofacial Surgery University Hospital RWTH Aachen Aachen Germany Institute of Computer Graphics and Vision (ICG) Graz University of Technology Graz Austria Cancer Research Center Cologne Essen (CCCE) West German Cancer Center Essen (WTZ) University Hospital Essen (AöR) Essen Germany Partner Site Essen German Cancer Consortium (DKTK) Essen Germany Department of Physics TU Dortmund University Dortmund Germany Center for Virtual and Extended Reality in Medicine (ZvRM) University Hospital Essen Essen Germany

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

State-of-the-art deep learning algorithms are easily biased and evaluated in misleading scenarios, especially in the medical context, where scenarios change rapidly and diseases develop quickly. The BraTS 2024 GoAT challenge aims to evaluate how brain tumour segmentation algorithms can adapt to different circumstances when these are not available for training. Our solution utilises state-of-the-art conditional generative adversarial networks to generate realistic new cases and train a segmentation algorithm that takes advantage of the convolutions and attention mechanisms. Our solution achieved a DSC value of 0.855, 0.863, 0.883 and an HD95 value of 24.83, 24.10 and 21.72 for the enhancing tumour, the tumour core and the whole tumour in the validation set, respectively.

关键词： Training Knowledge engineering Deep learning Generative adversarial networks Robustness Inference algorithms Tumors

来源：评论

学校读者我要写书评

暂无评论

Evaluation of algorithms for multi-modality whole heart segmentation: An open-access grand challenge

arXiv

引用

arXiv 2019年

作者： Zhuang, Xiahai Li, Lei Payer, Christian Štern, Darko Urschler, Martin Heinrich, Mattias P. Oster, Julien Wang, Chunliang Smedby, Örjan Bian, Cheng Yang, Xin Heng, Pheng-Ann Mortazi, Aliasghar Bagci, Ulas Yang, Guanyu Sun, Chenchen Galisot, Gaetan Ramel, Jean-Yves Brouard, Thierry Tong, Qianqian Si, Weixin Liao, Xiangyun Zeng, Guodong Shi, Zenglin Zheng, Guoyan Wang, Chengjia MacGillivray, Tom Newby, David Rhode, Kawal Ourselin, Sebastien Mohiaddin, Raad Keegan, Jennifer Firmin, David Yang, Guang School of Data Science Fudan University Shanghai200433 China Fudan-Xinzailing Joint Research Center for Big Data Fudan University Shanghai200433 China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai200240 China Institute of Computer Graphics and Vision Graz University of Technology Graz8010 Austria Ludwig Boltzmann Institute for Clinical Forensic Imaging Graz8010 Austria Institute of Medical Informatics University of Lubeck Lubeck23562 Germany Inserm Université de Lorraine U1254 IADI Nancy France School for Technology and Health KTH Royal Institute of Technology StockholmSE-10044 Sweden School of Biomed. Eng. Health Science Centre Shenzhen University Shenzhen518060 China Dept. of Comp. Sci. and Eng. Chinese University of Hong Kong Hong Kong China University of Central Florida Orlando32816 United States School of Computer Science and Engineering Southeast University Nanjing210096 China Université de Tours 64 avenue Jean Portalis Tours37200 France School of Computer Science Wuhan University Wuhan430072 China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology SIAT Shenzhen China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Institute for Surgical Technology & Biomechanics University of Bern Bern3014 Switzerland BHF Centre for Cardiovascular Science University of Edinburgh Edinburgh United Kingdom Edinburgh Imaging Facility QMRI University of Edinburgh Edinburgh United Kingdom Department of Imaging Sciences & Biomedical Engineering Kings College London London United Kingdom Cardiovascular Research Centre Royal Brompton Hospital LondonSW3 6NP United Kingdom National Heart and Lung Institute Imperial College London London LondonSW7 2AZ United Kingdom

Knowledge of whole heart anatomy is a prerequisite for many clinical applications. Whole heart segmentation (WHS), which delineates substructures of the heart, can be very valuable for modeling and analysis of the anatomy and functions of the heart. However, automating this segmentation can be arduous due to the large variation of the heart shape, and different image qualities of the clinical data. To achieve this goal, a set of training data is generally needed for constructing priors or for training. In addition, it is difficult to perform comparisons between different methods, largely due to differences in the datasets and evaluation metrics used. This manuscript presents the methodologies and evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction with MICCAI 2017. The challenge provides 120 three-dimensional cardiac images covering the whole heart, including 60 CT and 60 MRI volumes, all acquired in clinical environments with manual delineation. Ten algorithms for CT data and eleven algorithms for MRI data, submitted from twelve groups, have been evaluated. The results show that many of the deep learning (DL) based methods achieved high accuracy, even though the number of training datasets were limited. A number of them also reported poor results in the blinded evaluation, probably due to overfitting in their training. The conventional algorithms, mainly based on multi-atlas segmentation, demonstrated robust and stable performance, even though the accuracy is not as good as the best DL method in CT segmentation. The challenge, including provision of the annotated training data and the blinded evaluation for submitted algorithms on the test data, continues as an ongoing benchmarking resource via its homepage (***/zhuangxiahai/0/mmwhs/). Copyright © 2019, The Authors. All rights reserved.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Adaptive camera-based color mapping for mixed-reality applications

Adaptive camera-based color mapping for mixed-reality applic...

引用

International Symposium on Mixed and Augmented reality (ISMAR)

作者： Martin Knecht Christoph Traxler Werner Purgathofer Michael Wimmer Institute of Computer Graphics and Algorithms University of Technology Vienna Austria VRVis Research Center for Virtual Reality and Visualization Austria

We present a novel adaptive color mapping method for virtual objects in mixed-reality environments. In several mixed-reality applications, added virtual objects should be visually indistinguishable from real objects. Recent mixed-reality methods use global-illumination algorithms to approach this goal. However, simulating the light distribution is not enough for visually plausible images. Since the observing camera has its very own transfer function from real-world radiance values to RGB colors, virtual objects look artificial just because their rendered colors do not match with those of the camera. Our approach combines an on-line camera characterization method with a heuristic to map colors of virtual objects to colors as they would be seen by the observing camera. Previous tone-mapping functions were not designed for use in mixed-reality systems and thus did not take the camera-specific behavior into account. In contrast, our method takes the camera into account and thus can also handle changes of its parameters during runtime. The results show that virtual objects look visually more plausible than by just applying tone-mapping operators.

关键词： Image color analysis Cameras virtual reality Color Lighting Rendering (computer graphics) Visualization

来源：评论

学校读者我要写书评

暂无评论

System for inspection of large high-resolution radiography datasets

System for inspection of large high-resolution radiography d...

引用

IEEE Conference on Aerospace

作者： Tom Wypych So Yamaoka Kevin Ponto Falko Kuester San Diego Department of Computer Science and Engineering CalIT2 Center of Graphics Visualization and Virtual Reality (GRAVITY) University of California USA

High-resolution image collections pose unique challenges to analysts tasked with managing the associated data assets and deriving new information from them. While significant progress has been made towards rapid automated filtering, alignment, segmentation, characterization, and feature identification from image collections, the extraction of new insights still strongly depends on human intervention. In real-time capture and immediate-mode analysis environments where image data has to be continuously and interactively processed, a broad set of challenges in the image-driven verification and analysis cycle have to be addressed. A framework for interactive and intuitive inspection of large, high-resolution image data sets is presented, leveraging the strength of the human visual system for large-scale image processing. A case study is provided for an X-ray radiography system, covering the scanner-to-screen data management and representation pipeline, resulting in a visual analytics environment enabling analytical reasoning by means of interactive and intuitive visualization.

关键词： Imaging Inspection Data visualization X-ray imaging Visual analytics Pixel Radar imaging

来源：评论

学校读者我要写书评

暂无评论

Advanced illumination techniques for GPU-based volume raycasting 09

Advanced illumination techniques for GPU-based volume raycas...

引用

ACM SIGGRAPH 2009 Courses, SIGGRAPH '09

作者： Hadwiger, Markus Ljung, Patric Salama, Christof Rezk Ropinski, Timo VRVis Research Center for Virtual Reality and Visualization Donau-City-Straße 1 A-1220 Vienna Austria Siemens Corporate Research Imaging and Visualization Department 755 College Road East Princeton NJ 08540 United States Computer Graphics Group University of Siegen Hölderlinstr. 3 57068 Siegen Germany Visualization and Computer Graphics Research Group University of Münster Einsteinstr. 62 48149 Münster Germany

ISBN: (纸本)9781450379380

Volume raycasting techniques are important for both visual arts and visualization. They allow efficient generation of visual effects and visualization of scientific data obtained by tomography or numerical simulation. Volume-rendering techniques are also effective for direct rendering of implicit surfaces used for soft-body animation and constructive solid geometry. The focus of this course is on volumetric illumination techniques that approximate physically based light transport in participating media. Such techniques include interactive implementation of soft and hard shadows, ambient occlusion, and simple Monte Carlo-based approaches to global illumination, including translucency and scattering.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Delocalized unsteady vortex region detectors

Delocalized unsteady vortex region detectors

引用

13th International Fall Workshop Vision, Modeling, and Visualization 2008, VMV 2008

作者： Fuchs, Raphael Peikert, Ronald Sadlo, Filip Alsallakh, Bilal Gröller, Meister Eduard Institute of Computer Graphics and Algorithms TU Vienna Austria VRVis Research Center for Virtual Reality and Visualization Vienna Austria Computer Graphics Laboratory ETH Zurich Switzerland

ISBN: (纸本)9781586039219

In this paper we discuss generalizations of instantaneous, local vortex criteria. We incorporate information on spatial context and temporal development into the detection process. The presented method is generic in so far that it can extend any given Eulerian criterion to take the Lagrangian approach into account. Furthermore, we present a visual aid to understand and steer the feature extraction process. We show that the delocalized detectors are able to distinguish between connected vortices and help understanding regions of multiple interacting vortex structures. The delocalized detectors extract smoother structures and reduce noise in the vortex detection result.

关键词： Vortex flow

来源：评论

学校读者我要写书评

暂无评论

Advanced illumination for gpu volume

Advanced illumination for gpu volume

引用

ACM SIGGRAPH ASIA 2008 Courses, SIGGRAPH Asia'08

作者： Salama, Christof Rezk Ropinski, Timo Hadwiger, Markus Ljung, Patric Computer Graphics Group University of Siegen Hölderlinstr. 3 57068 Siegen Germany Visualization and Computer Graphics Research Group University of Münster Einsteinstr. 62 48149 Münster Germany VRVis Research Center for Virtual Reality and Visualization Donau-City-StraBe A-1220 Vienna Austria Siemens Corporate Research Imaging and Visualization Department 755 College Road East Princeton NJ 08540 United States

Volume raycasting techniques are important for both visual arts and. They allow an efficient generation of visual effects and visualization of scientific data obtained by tomography or numerical. Thanks to their flexibility, experts agree that GPU-based is the state-of-the art technique for interactive volume *** most likely replace existing slice-based techniques in the near. Volume rendering techniques are also effective for the direct rendering implicit surfaces used for soft body animation and constructive *** starts off with an in-depth introduction to the concepts GPU-based ray-casting to provide a common base for the following. The focus of this course is on advanced illumination techniques approximate the physically-based light transport more convincingly. techniques include interactive implementation of soft hard shadows, ambient occlusion and simple Monte-Carlo based approaches global illumination including translucency and scattering. the proposed techniques, users are le to interactively create images from volumetric data whose visual quality goes far traditional approaches. The optical properties in participating are defined using the phase function. Many approximations to the based light transport applied for rendering natural phenomena as clouds or smoke assume a rather homogenous phase function. For rendering volumetric scans on the other hand different phase models are required to account for both surface-like structures fuzzy boundaries in the data. Using volume rendering techniques,who create medical visualization for science magazines may now work on tomographic scans directly, without the necessity to fall back to creating polygonal models of anatomical structures.

关键词： Volume rendering

来源：评论

学校读者我要写书评

暂无评论

On-line boosting for car detection from aerial images

On-line boosting for car detection from aerial images

引用

2007 IEEE International Conference on Research, Innovation and Vision for the Future, RIVF 2007

作者： Nguyen, Thuy Thi Grabner, Helmut Bischof, Horst Gruber, Barbara Institute for Computer Graphics and Vision Graz University of Technology Austria VRVis Research Center for Virtual Reality and Visualization Graz Austria

ISBN: (纸本)1424406943

In this paper, we present a new approach for automatic car detection from aerial images. The system exploits a robust machine learning method known as boosting for efficient car detection from high resolution aerial images. We propose to use on-line boosting with interactive training framework to efficiently train and improve the detector. We use integral images for fast computation of features. This also allows to perform exhaustive search for detection of cars after training. For post processing, we employ a mean shift clustering method, which improves the detection rate significantly. In contrast to related work, our framework does not rely on any priori knowledge of the image like a site-model or contextual information, but if necessary this information can be incorporated. An extensive set of experiments on high resolution aerial images using the new UltraCamD shows the superiority of our approach. © 2007 IEEE.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

self-CD: Interactive self-collision detection for deformable body simulation using GPUs

self-CD: Interactive self-collision detection for deformable...

引用

Third Asian Simulation Conference, Asiasim 2004

作者： Choi, Yoo-Joo Kim, Young J. Kim, Myoung-Hee Department of Computer Science and Engineering Ewha Womans University Seoul Korea Republic of Center for Computer Graphics and Virtual Reality Ewha Womans Univesity Seoul Korea Republic of

This paper presents an efficient self-collision detection algorithm for deformable body simulation using programmable graphics processing units (GPUs). The proposed approach stores a triangular mesh representation of a deformable model as ID textures and rapidly detects self-collisions between all pairs of triangular primitives using the programmable SIMD capability of GPUs [1]. Since pre-computed spatial structure such as bounding volume hierarchy is not used in our algorithm, our algorithm does not require expensive runtime updates to such complex structure as the underlying model deforms. Moreover, in order to overcome a potential bottleneck between CPU and GPU, we propose a hierarchical encoding/decoding scheme using multiple off-screen buffers and multi-pass rendering techniques, which reads only a region of interests in the resulting off-screen buffer. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Algorithms

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：