检索结果-内蒙古大学图书馆

IEEE EMBS International Conference on Information Technology Applications in Biomedicine (ITAB)

作者： Guangjian Tian Hong Fu David Dagan Feng Center for Multimedia Signal Processing Department of Electronic and Information Engineering Hong Kong Polytechnic University Kowloon Hong Kong China School of Information Technologies University of Sydney NSW Australia

This paper presents a global and local texture features combination as the description of medical images. The approaches use the block based Local Binary Pattern (LBP) texture histogram and MPEG-7 edge histogram together as the medical image description. The block histograms and the whole image texture histograms are accumulated to generate the image feature vector. Then, One-against-One SVM is adopted for automatic medical image annotation task in ImageCLEFmed2007. The experiments show that Local Binary Pattern texture and Edge Histogram are powerful for automatic medical image annotation.

关键词： Biomedical imaging MPEG 7 Standard Histograms Medical diagnostic imaging Image retrieval Pixel Binary codes signal processing Information technology Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Chinese Sentence Similarity Measure Based on Words and Structure Information

Chinese Sentence Similarity Measure Based on Words and Struc...

引用

International Conference on Advanced Language processing and Web Information Technology (ALPIT)

作者： Rongbo Wang Xiaohua Wang Zheru Chi Zhiqun Chen Institute of Computer Application Technology Hangzhou Dianzi University Hangzhou China Center for Multimedia Signal Processing Department of Electronic and Information Engineering Hong Kong Polytechnic University Hong Kong China

Example-based machine translation (EBMT) is an important branch of machine translation. Sentence similarity measure is certainly one of the most significant problems addressed in EBMT. For EBMT from Chinese to English, the performance of similarity measure of Chinese sentences greatly affects the final translation result of an input Chinese sentence. In this paper, we present an approach to Chinese sentence similarity measure (CSSM) together with word sequence and sentence structure information. The new method in our experiments yields a good efficiency and effectiveness without conducting a complex and deep syntactic analysis of Chinese sentences, which can be applied to an EBMT system for CSSM for a better performance in Chinese-to-English translation.

关键词： Joints Equations Information processing History Computers Flowcharts multimedia communication

来源：评论

学校读者我要写书评

暂无评论

Reliable Model and Cluster Aided Formation of Parametric Images in Functional Imaging

引用

IFAC Proceedings Volumes 2008年第2期41卷 6669-6674页

作者： Lingfeng Wen Stefan Eberl David Feng Biomedical & Multimedia Information Technology (BMIT) Group School of Information Technologies J12 University of Sydney NSW 2006 Australia Center for Multimedia Digital Signal Processing Dept. of Electronic & Information Engineering Hong Kong Polytechnic University Hung Hom Kowloon Hong Kong Department of PET & Nuclear Medicine Royal Prince Alfred Hospital Missenden Road Camperdown NSW 2050 Australia

Parameter estimation in functional imaging provides unique quantitative measures in clinical diagnosis, and in the evaluation of treatment response and new drugs. Voxel-by-voxel parameter estimations can construct parametric images which visualize the spatial distribution of functional parameters. The low signal-to-noise ratio in single photon emission computed tomography (SPECT) may cause physiologically meaningless estimates using the general linear least square method (GLLS). A proof-of-principle framework is proposed in this study for constructing simultaneously multiple parametric images using a model-aided GLLS method and fuzzy clustering for dynamic SPECT. Computer simulations were performed to evaluate the accuracy and reliability of estimates for the studied methods. The results show that the model-aided GLLS with fuzzy clustering did enhance reliability for voxel-by-voxel parameter estimation with a slight overestimation of the volume of distribution. The method employing normalization of TTAC was superior to the method without normalization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification of dementia from FDG-PET parametric images using data mining

Classification of dementia from FDG-PET parametric images us...

引用

IEEE International Symposium on Biomedical Imaging

作者： Lingfeng Wen Michael Bewley Stefan Eberl Michael Fulham Dagan Feng Department of PET and Nuclear Medicine Royal Prince Alfred Hospital Sydney Australia Biomedical and Multimedia Information Technology (BMIT) Research Group School of Information Technologies University of Sydney Australia School of Electrical and Information Engineering University of Sydney Australia Center for Multimedia Signal Processing (CMSP) Department of Electronic & Information Engineering Hong Kong Polytechnic University Hong Kong China

ISBN: (纸本)9781424420025

It remains a challenge to identify the different types of dementia and separate these from various subtypes from the normal effects of ageing. In this paper the potential of parametric images from FDG-PET studies to aid the classification of dementia using data mining techniques was investigated. Scalar, joint, histogram and voxel-level features were used in the investigation with principal component analysis (PCA) for dimensionality reduction. The logistic regression model and the additive logistic regression model were applied in the classification. The results show that cerebral metabolic rate of glucose consumption (CMRGlc) was efficient in the classification of dementia and data mining using voxel-level features with PCA and the logistic regression model method achieving the best classification.

关键词： Dementia Data mining Positron emission tomography Principal component analysis Support vector machines Histograms Support vector machine classification Logistics Sugar Information technology

来源：评论

学校读者我要写书评

暂无评论

Lung segmentation and tumor detection from CT thorax volumes of FDG PET-CT scans by template registration and incorporation of functional information

Lung segmentation and tumor detection from CT thorax volumes...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： Cherry Ballangan Xiuying Wang Dagan Feng Stefan Eberl Michael Fulham Biomedical and Multimedia Information Technology (BMIT) Research Group School of Information Technologies University of Sydney Australia BMIT Research Group School of Information Technologies University of Sydney Australia Center for Multimedia Signal Processing (CMSP) Department of Electronic & Information Engineering Hong Kong Polytechnic University Hong Kong China Department of PET and Nuclear Medicine Royal Prince Alfred Hospital Sydney Australia

Automatic segmentation and detection of lungs and tumors in FDG PET-CT images is potentially beneficial in the diagnosis and staging of patients with non-small cell lung cancer (NSCLC). However, simultaneous lung segmentation and tumor detection is not a trivial task, particularly due to noise in the datasets, proximity of the lung lesion to the mediastinum and chest wall in certain instances, and disease involvement of non-enlarged lymph nodes.

关键词： Tumors Thorax Image segmentation Lung neoplasms Positron emission tomography Information technology Computed tomography Cancer Lesions Diseases

来源：评论

学校读者我要写书评

暂无评论

Interactive point-of-interest volume rendering visualization of PET-CT data

Interactive point-of-interest volume rendering visualization...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： Jinman Kim Ashnil Kumar Stefan Eberl Michael Fulham Dagan Feng Biomedical and Multimedia Information Technology (BMIT) Research Group School of Infonnation Technologies University of Sydney Australia Department of PET and Nuclear Medicine Royal Prince Alfred Hospital Sydney Australia BMIT Research Group University of Alfred Hospital (RPAH) Australia BMIT Research Group University of Sydney Australia Center for Multimedia Signal Processing (CMSP) Department of Electronic & Infonnation Engineering Hong Kong Polytechnic University Hong Kong China

Due to the rapid advances in dual-modality PET-CT scanners, the access to and assimilation of critical information within these data are becoming extremely difficult with conventional 2D and even with sophisticated 3D visualization. In this study, we propose an integration of maximum intensity projection (MIP) and direct volume rendering (DVR) algorithms to provide a comprehensive solution for PET-CT visualization. In this process, interactive selection of a point-of-interest (POI) from fused-MIP of PET-CT is used to automate the image enhancements, such as transfer function generation, for subsequent DVR visualization used in further image diagnosis. Such automation can significantly ease the required manual image enhancements/manipulation that must be performed during image visualization. We demonstrate the effectiveness of our proposed volume rendering visualization scheme with its application to clinical PET-CT tumor studies.

关键词： Data visualization Rendering (computer graphics) Positron emission tomography Image enhancement Neoplasms Computed tomography Transfer functions Automation signal processing algorithms Nuclear and plasma sciences

来源：评论

学校读者我要写书评

暂无评论

Medical image registration via steerable pyramid

Medical image registration via steerable pyramid

引用

29th Annual International Conference of IEEE-EMBS, Engineering in Medicine and Biology Society, EMBC'07

作者： Wang, X. Feng, D.D. IEEE School of Information Technologies University of Sydney NSW 2006 Australia Center for Multimedia Signal Processing Department of Electronic and Information Engineering Hong Kong Polytechnic University

ISBN: (纸本)1424407885

Image registration is enabling in integrating complementary and heterogeneous information from multiple images, and is particularly important for high-quality healthcare. To improve registration efficiency and accuracy, in this paper, a two-resolution-scale registration approach is proposed. Firstly, to speed up calculation, the images will be decomposed into multi-scale and multi-band representation by steerable pyramid that outweighs wavelets by providing invariance for both translation and rotation. Then, to avoid transformation error accumulation and magnification during the parameter transmission in the traditional multi-scale registration, the registration will be performed only in the lowest-resolution scale and the highest-resolution scale. In the former scale, the global rotation and scaling parameters will be calculated rapidly and accurately, which then will be directly used to initialize optimization in the latter scale, where, the translation differences will be corrected. The experiments on medicai images demonstrate that the proposed registration is of good performance. © 2007 IEEE.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Medical Image Registration via Steerable Pyramid

Medical Image Registration via Steerable Pyramid

引用

29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS 2007), vol.16

作者： X. Wang D. D. Feng School of Information Technologies University of Sydney NSW Australia Center for Multimedia Signal Processing Department of Electronic and Information Engineering Hong Kong Polytechnic University Hong Kong China

Image registration is enabling in integrating complementary and heterogeneous information from multiple images, and is particularly important for high-quality healthcare. To improve registration efficiency and accuracy, in this paper, a two-resolution-scale registration approach is proposed. Firstly, to speed up calculation, the images will be decomposed into multi-scale and multi-band representation by steerable pyramid that outweighs wavelets by providing invariance for both translation and rotation. Then, to avoid transformation error accumulation and magnification during the parameter transmission in the traditional multi-scale registration, the registration will be performed only in the lowest-resolution scale and the highest-resolution scale. In the former scale, the global rotation and scaling parameters will be calculated rapidly and accurately, which then will be directly used to initialize optimization in the latter scale, where, the translation differences will be corrected. The experiments on medical images demonstrate that the proposed registration is of good performance.

关键词： Biomedical imaging Image registration Medical diagnostic imaging Discrete wavelet transforms Medical services Diseases Australia Information technology Acceleration Frequency

来源：评论

学校读者我要写书评

暂无评论

Pre-classification Module for an All-Season Image Retrieval System

Pre-classification Module for an All-Season Image Retrieval ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Hong Fu Zheru Chi Dagan Feng Weibao Zou King Chuen Lo Xiaoyu Zhao Center for Multimedia Signal Processing Department of Electronic and Information Engineering Hong Kong Polytechnic University Hong Kong China School of Information Technologies University of Sydney NSW Australia

From the study of attention-driven image interpretation and retrieval, we have found that an attention-driven strategy is able to extract important objects from an image and then focus the attentive objects while retrieving images. However, besides the images with distinct objects, there are images which do not show distinct objects. In this paper, the classification of "attentive" and "non-attentive" image is proposed to be a pre-process module in an all-season image retrieval system which can tackle both kinds of images. In this pre-classification module, an image is represented by an adaptive tree structure with each node carrying normalized features that characterize the object/region with visual contrasts and spatial information. Then a neural network is trained to classify an image as an "attentive" or "non-attentive" category by using the Back Propagation Through Structure (BPTS) algorithm. Experimental results indicate the reliability and feasibility of the pre-classification module, which encourages us to conduct further investigations on the all-season image retrieval system.

关键词： Image retrieval signal processing algorithms Neural networks Tree data structures Fuses Focusing Humans Face Image processing Sea measurements

来源：评论

学校读者我要写书评

暂无评论

Chunk Segmentation of Chinese Sentences Using a Combined Statistical and Rule-based Approach (CSRA)

引用

International Journal of Computer processing of Languages 2007年第2N03期20卷 197-218页

作者： RONGBO WANG XIAOHUA WANG ZHIQUN CHEN ZHERU CHI Institute of Computer Application Technology School of Computer and Software Engineering Hangzhou Dianzi University Xiasha Higher Education Park Hangzhou Zhejiang China Center for Multimedia Signal Processing Department of Electronic and Information Engineering The Hong kong Polytechnic University Hong Kong

Deep parsing of Chinese sentences is a very challenging task due to their complexity such as ambiguous word boundaries and meanings. An alternative mode of Chinese language processing is to perform shallow parsing of Chinese sentences in which chunk segmentation plays an important role. In this paper, we present a chunk segmentation algorithm using a combined statistical and rule-based approach (CSRA). The decision rules for refining chunk segmentation are generated from incorrectly segmented chunks from a statistical model which is built on a training corpus. Experimental results show that the CSRA works well and produces satisfactory chunk segmentation results for subsequent processes such as chunk tagging and chunk collocation extraction.

关键词： Chinese language processing Chinese chunk segmentation Machine translation Language modeling Decision rules

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：