检索结果-内蒙古大学图书馆

Pneumoconiosis's Gross Tissue imaging Classification based on Morphological Feature Description

Pneumoconiosis's Gross Tissue Imaging Classification based o...

2012 Fifth International Symposium on Computational intelligence and Design [第五届计算智能与设计国际会议 ISCID 2012]

作者： Delie Ming Linying Yu Liping Xiao State Key Laboratory for Multi-spectral Information Processing Technology Huazhong University of Sci Beijing Aerospace Automatic Control Institute Laboratory of Aerospace Intelligence Control Technolog

Referring to pneumoconiosis's gross tissue imaging classification, it is fatal to know the importance of distinguishing lung nodule from macule and how many nodules and macule the pneumoconiosis's gross tissue image really get. In achieving the distinguishing and counting results, the morphology processing method and some auxiliary digital image processing methods are adopted. After processing, the statistic work begins. The statistic results of abundant candidate parameters give us the chance to pick the parameter performing extremely well. In that way, the classification of pneumoconiosis's gross tissue images is quite feasible.

关键词： pneumoconiosis morphology Otsu segmentation lung nodule and macule sobel center extraction

来源：评论

学校读者我要写书评

暂无评论

Anatomical Consistency Distillation and Inconsistency Synthesis for Brain Tumor Segmentation with Missing Modalities 27

Anatomical Consistency Distillation and Inconsistency Synthe...

引用

27th European Conference on Artificial intelligence, ECAI 2024

作者： Zhang, Zheyu Liu, Xinzhao Chen, Zheng Zhang, Yueyi Yue, Huanjing Ou, Yunwei Sun, Xiaoyan MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China Hefei China Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Tianjin University Tianjin China Beijing Tiantan Hospital Capital Medical University Beijing China

ISBN: (纸本)9781643685489

Multi-modal Magnetic Resonance imaging (MRI) is imperative for accurate brain tumor segmentation, offering indispensable complementary information. Nonetheless, the absence of modalities poses significant challenges in achieving precise segmentation. Recognizing the shared anatomical structures between mono-modal and multi-modal representations, it is noteworthy that mono-modal images typically exhibit limited features in specific regions and tissues. In response to this, we present Anatomical Consistency Distillation and Inconsistency Synthesis (ACDIS), a novel framework designed to transfer anatomical structures from multimodal to mono-modal representations and synthesize modality-specific features. ACDIS consists of two main components: Anatomical Consistency Distillation (ACD) and Modality Feature Synthesis Block (MFSB). ACD incorporates the Anatomical Feature Enhancement Block (AFEB), meticulously mining anatomical information. Simultaneously, Anatomical Consistency ConsTraints (ACCT) are employed to facilitate the consistent knowledge transfer, i.e., the richness of information and the similarity in anatomical structure, ensuring precise alignment of structural features across mono-modality and multi-modality. Complementarily, MFSB produces modality-specific features to rectify anatomical inconsistencies, thereby compensating for missing information in the segmented features. Through validation on the BraTS2018 and BraTS2020 datasets, ACDIS substantiates its efficacy in the segmentation of brain tumors with missing MRI modalities. © 2024 The Authors.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

3D TRUS image segmentation in prostate brachytherapy

3D TRUS image segmentation in prostate brachytherapy

引用

2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005

作者： Ding, Mingyue Gardi, Lori Wei, Zhouping Fenster, Aaron Key Laboratory Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China Imaging Research Laboratories Robarts Research Institute London Ont. N6A 5K8 Canada

ISBN: (纸本)0780387406

Brachytherapy is a minimally invasive interventional surgery used to treat prostate cancer. It is composed of three steps: dose pre-planning, implantation of radioactive seeds, and dose post-planning. In these procedures, it is crucial to determine the positions of needles and seeds, measure the volume of the prostate gland. Three-dimensional transrectal ultrasound (TRUS) imaging has been demonstrated to be a useful technique to perform such tasks. Compared to CT, MRI or X-ray imaging, US image suffers from low contrast, image speckle and shadows, making it challenging for segmentation of needles, the prostates and seeds in the 3D TRUS images. In this paper, we reviewed 3D TRUS image segmentation methods used in prostate brachytherapy including the segmentations of the needles, the prostate, as well as the seeds. Furthermore, some experimental results with agar phantom, turkey and chicken phantom, as well as the patient data are reported. © 2005 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Diffusion Network with controllable Variability for Medical Image Segmentation

Multi-modal Diffusion Network with Controllable Variability ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wang, Haoyu Zhang, Zheyu Zhang, Yueyi Zhang, Jing Ou, Yunwei Sun, Xiaoyan University of Science and Technology of China Hefei China Hefei Comprehensive National Science Center Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing Institute of Artificial Intelligence Hefei China Capital Medical University Beijing Tiantan Hospital Department of Neurosurgery Beijing China

ISBN: (纸本)9798350386226

In diffusion-based medical segmentation models, stochastic sampling is commonly used to generate multiple masks. However, the inherent variability in diffusion models can lead to significant biases in some masks, resulting in the fused mask deviating from the true mask. In this study, we propose a novel multi-modal diffusion segmentation network (MMDSN) with controllable variability, specifically designed to address the issue of variability in diffusion models. MMDSN achieves multi-modal conditional control through medical text annotations, thereby enhancing consistency of visual semantic representation and establishing a correspondence between vision and language for diffusion models. Additionally, MMDSN constrains the uncertainty distributions of multiple timesteps within the latent Gaussian space, controlling the variability at each denoising timestep. Extensive experiments on the Qata-Covid19 and MosMed datasets demonstrate that our proposed method surpasses existing state-of-the-art diffusion networks, producing a high-quality, controllable segmentation map with just a single reverse diffusion step and one sampling. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Impact of murine skull on transcranial photoacoustic imaging: a numerical study 15

Impact of murine skull on transcranial photoacoustic imaging...

引用

15th International Conference on Information Optics and Photonics, CIOP 2024

作者： Pan, Feiyang Wei, Xingyu Tian, Chao School of Engineering Science University of Science and Technology of China Anhui Hefei230026 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230088 China Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China

ISBN: (数字)9781510686175

ISBN: (纸本)9781510686168

Photoacoustic imaging (PAI) is a promising transcranial imaging technique for the mouse brain. However, the mouse skull imposes severe wavefront distortion to photoacoustic signals, thus reducing the quality of PAI. In this article, numerical simulations are implemented to study the influence of skull on PAI with respect to the distance of photoacoustic sources to skull. The k-Wave toolbox is adopted to simulate the photoacoustic wave propagation. The waveforms of shear and longitudinal waves within the skull layer are analyzed. Time reversal algorithm is applied to reconstruct the photoacoustic sources. Reconstruction results show that the mode conversion at the inner skull surface can cause streak artifacts around reconstructed point sources, and the artifacts are more obvious when the sources are near the skull. This study is expected to provide useful insights for transcranial photoacoustic imaging. © 2024 SPIE.

关键词： Mammals

来源：评论

学校读者我要写书评

暂无评论

A Super Performance Bandgap Voltage Reference with Adjustable Output for DC-DC Converter

引用

The Journal of China Universities of Posts and Telecommunications 2006年第1期13卷 75-78页

作者： YU Hua ZOU Xue-cheng CHEN Chao-yang Department of Electronics Science and Technology Huazhong University of Science and Technology Wuhan 430074 P.R. China State Key Laboratory for Image Processing and Intelligence Control Huazhong University of Science and Technology Wuhan 430074 P.R. China

This paper presents a super performance bandgap voltage reference for DC-DC converter with adjustable output. it generates a wide range of voltage reference ranging from sub- 1V to 1,221 7 V and has a low temperature coefficient of 2.3 × 10 ^5/K over the temperature variation using the current feedback and resistive subdivision. In addition, the power supply rejection ration of the proposed bandgap voltage reference is 78 dB. When supply voltage varies from 2.5 V to 6 V, output VREF is 1,221 685±0.055 mV.

关键词： bandgap voltage reference adjustable output DC-DC converter temperature coefficient PSRR

来源：评论

学校读者我要写书评

暂无评论

Point spread function modeling for coherent plane-wave compounding ultrasound imaging 15

Point spread function modeling for coherent plane-wave compo...

引用

15th International Conference on Information Optics and Photonics, CIOP 2024

作者： Zhou, Bowen Liu, Songde Tian, Chao School of Engineering Science University of Science and Technology of China Anhui Hefei230026 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230088 China Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China

ISBN: (数字)9781510686175

ISBN: (纸本)9781510686168

Spatial resolution is a critical measure of the imaging performance of ultrasound imaging systems and is determined by various system factors. So far, no comprehensive studies have been reported to elucidate the impact of system factors on spatial resolution, which is generally defined as the full width at half maximum (FWHM) of the point spread function (PSF). This work aims to model the PSF of ultrasound imaging systems based on a linear transducer array and a coherent plane-wave compounding (CPWC) method and study how pulse-echo sequences, transducer parameters, and beamforming algorithms impact PSF. The Verasonics simulator and UltraSound ToolBox are used in numerical simulations for ultrasound signal generation and image reconstruction, respectively. Experiments are conducted to verify simulation results. Numerical and experimental results show that the value of axial resolution is negatively correlated with the center frequency of the ultrasonic transducer;the value of lateral resolution is positively correlated with the number of transmitted plane waves of the CPWC method and the element width of the ultrasonic transducer and is negatively correlated with the maximum steering angle of the CPWC method and the aperture size and center frequency of the ultrasonic transducer. Different beamforming algorithms show varying effects on spatial resolution and image quality. This work is expected to help predict and interpret the quality of ultrasound images produced by practical ultrasound imaging systems and is beneficial for the design and development of ultrasonic transducers, pulse-echo sequences, and beamforming algorithms for enhanced spatial resolution. © 2024 SPIE.

关键词： Optical transfer function

来源：评论

学校读者我要写书评

暂无评论

High-Precision Discrete Convolution Algorithm Based on Moments

High-Precision Discrete Convolution Algorithm Based on Momen...

引用

WRI International Conference on Communications and Mobile Computing, CMC

作者： Jianguo Liu Zhenbing Liu Guoyou Wang Key Laboratory of Education Ministry for Image Processing and Intelligent Control State Key Laboratory of Multispectral Information Processing Technologies Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

Convolution is an important and useful operation in the fields of digital signal processing. In this paper, based on the previous work of performing discrete Fourier transform (DFT) via linear sums of discrete moments, we have made development to eliminate multiplications in discrete Fourier transforms by performing appropriate bit operations and shift operations in binary system, which can be implemented by integer additions of fixed points; then using the convolution theorem with the DFT, we compute the convolution with two DFTs, a point-by-point product, and an inverse DFT. Our algorithm involves fewer multiplications and can deal with arbitrary length signals.

关键词： Convolution Signal processing algorithms Discrete Fourier transforms Very large scale integration Algorithm design and analysis Laboratories Educational technology Digital signal processing Mobile communication Mobile computing

来源：评论

学校读者我要写书评

暂无评论

RF-GNN: Random Forest Boosted Graph Neural Network for Social Bot Detection

arXiv

引用

arXiv 2023年

作者： Shi, Shuhao Qiao, Kai Yang, Jie Song, Baojie Chen, Jian Yan, Bin Henan Key Laboratory of Imaging and Intelligence Processing PLA strategy support force information engineering university Zhengzhou Henan45000 China

The presence of a large number of bots on social media leads to adverse effects. Although Random forest algorithm is widely used in bot detection and can significantly enhance the performance of weak classifiers, it cannot utilize the interaction between accounts. This paper proposes a Random Forest boosted Graph Neural Network for social bot detection, called RF-GNN, which employs graph neural networks (GNNs) as the base classifiers to construct a random forest, effectively combining the advantages of ensemble learning and GNNs to improve the accuracy and robustness of the model. Specifically, different subgraphs are constructed as different training sets through node sampling, feature selection, and edge dropout. Then, GNN base classifiers are trained using various subgraphs, and the remaining features are used for training Fully Connected Netural Network (FCN). The outputs of GNN and FCN are aligned in each branch. Finally, the outputs of all branches are aggregated to produce the final result. Moreover, RF-GNN is compatible with various widely-used GNNs for node classification. Extensive experimental results demonstrate that the proposed method obtains better performance than other state-of-the-art methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Modeling for Pneumatic Muscle Using Koopman-Based Kalman Filter

Data-Driven Modeling for Pneumatic Muscle Using Koopman-Base...

引用

IEEE International Conference on Development and Learning, ICDL

作者： Yu Caol Mengshi Zhang Bo Yang Jian Huang Key Laboratory for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

This paper presents a data-driven modeling approach for enhancing the understanding of pneumatic muscles (PMs) through Koopman kalman filter (KKF). The proposed method involves the construction of a comprehensive pneumatic muscle motion data-set, obtained by capturing extensive input-state-output data through the application of random inputs. Subsequently, the states of pneumatic muscle are lifted through a kernel-based technique. The nonlinear pneumatic muscle model is then transformed into a linear counterpart using the extended dynamic mode decomposition (EDMD). Then, a kalman filter is further used to improve the model accuracy. The effectiveness of this approach is demonstrated through simulation analysis, highlighting its capacity to yield superior pneumatic muscle modeling and state estimation results when compared to conventional Koopman operator methodologies.

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：