检索结果-内蒙古大学图书馆

URSI Asia-Pacific Radio Science Conference (URSI AP-RASC)

作者： Yurong Huang Jinhua Yu Yuanyuan Wang Shuying Li Yi Chen Department of Electronic Engineering Fudan University Shanghai China The key laboratory of medical imaging computing and computer assisted intervention of shanghai Shanghai China

Study of ultrasound contrast imaging is of great importance in recent years thanks to its wide application in ultrasonic diagnosis. Plane wave imaging has been considered as a good method with high frame rate and low mechanical index. High frame rate can improve the temporal resolution of contrast imaging. Meanwhile, low mechanical index is essential to contrast imaging since high mechanical index in traditional B-mode imaging could break micro-bubbles easily. However, plane wave contrast imaging suffers from low signal-to-noise ratio (SNR) and contrast (CR) which leads to poor image quality. In this paper, adaptive beamformer and pulse inversion (PI) technique were combined to solve the shortcomings of the plane wave contrast imaging. For the adaptive beamformer, eigenspace based minimum variance (ESBMV) with coherence factor (ESBMVCF) was proposed. Experimental results show that ESBMVCF offers an enhancement of 1.1dB, 13dB and 0.8dB in CR, contrast-to-tissue ratio (CTR) and contrast-to-noise ratio (CNR) respectively compared with minimum variance and coherence factor (MVCF). Besides, PI offers 1.5dB, 15dB and 15dB enhancement in CR, CTR and CNR compared with traditional pulse-echo imaging.

关键词： Radar imaging Meteorology imaging Meteorological radar Image resolution Radar antennas

来源：评论

学校读者我要写书评

暂无评论

The theoretical and experimental analysis of ultrasound contrast agent micro bubbles: The Sonovue

The theoretical and experimental analysis of ultrasound cont...

引用

International Conference on Biomedical Engineering and Informatics (BMEI)

作者： Shuying Li Yurong Huang Yi Cheng Jinhua Yu Yuanyuan Wang Department of Electronic Engineering Fudan University Shanghai China The key laboratory of medical imaging computing and computer assisted intervention of shanghai China

Sonovue is a kind of ultrasound contrast agent (UCA) with a stable shell made by lipid, within which is SF6. Due to the specific acoustic characteristics, UCA has been widely used in ultrasound diagnosis and therapy. In some cases, the 2nd harmonic wave of the scattered signal should be strong enough to help form a high quality image. To better utilize the bubbles to get enough intensity of the 2nd harmonic wave of the scattered signal, numerical simulation and corresponding experiments based on the several models proposed before have been analyzed to study the behavior of the bubbles. In this paper, we use the ratio of the second harmonic wave and fundamental wave to evaluate the oscillation of the bubbles. Besides, we have compared different simulation models and designed corresponding platform of phantom study. Finally, we find that the second harmonic wave will get a remarkable growth when the driving pressure is under 150KPa in the simulation or under 200KPa in the experiment.

关键词： Mathematical model Harmonic analysis Numerical models Acoustics Liquids Phantoms Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Evaluation of fatty proportion in fatty liver using least squares method with constraints

Evaluation of fatty proportion in fatty liver using least sq...

引用

作者： Li, Xingsong Deng, Yinhui Yu, Jinhua Wang, Yuanyuan Shamdasani, Vijay Department of Electronic Engineering Fudan University HenglongPhysic Building Room 212 Shanghai200433 China Department of Healthcare Philips Research China Shanghai200233 China Key Laboratory of Medical Imaging Computing Computer Assisted Intervention of Shanghai China Department of Healthcare Philips Research China Bothell United States

Backscatter and attenuation parameters are not easily measured in clinical applications due to tissue inhomogeneity in the region of interest (ROI). A least squares method(LSM) that fits the echo signal power spectra from a ROI to a 3- parameter tissue model was used to get attenuation coefficient imaging in fatty liver. Since fat's attenuation value is higher than normal liver parenchyma, a reasonable threshold was chosen to evaluate the fatty proportion in fatty liver. Experimental results using clinical data of fatty liver illustrate that the least squares method can get accurate attenuation estimates. It is proved that the attenuation values have a positive correlation with the fatty proportion, which can be used to evaluate the syndrome of fatty liver. © 2014 - IOS Press and the authors.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Chest-Diffusion: A Light-Weight Text-to-Image Model for Report-to-CXR Generation

Chest-Diffusion: A Light-Weight Text-to-Image Model for Repo...

引用

IEEE International Symposium on Biomedical imaging

作者： Peng Huang Xue Gao Lihong Huang Jing Jiao Xiaokang Li Yuanyuan Wang Yi Guo Department of Electronic Engineering Fudan University Shanghai China Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai Shanghai China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Text-to-image generation has important implications for generation of diverse and controllable images. Several attempts have been made to adapt Stable Diffusion (SD) to the medical domain. However, the large distribution difference between medical reports and natural texts, as well as high computational complexity in common stable diffusion limit the authenticity and feasibility of the generated medical images. To solve above problems, we propose a novel light-weight transformer-based diffusion model learning framework, Chest-Diffusion, for report-to-CXR generation. Chest-Diffusion employs a domain-specific text encoder to obtain accurate and expressive text features to guide image generation, improving the authenticity of the generated images. Meanwhile, we introduce a light-weight transformer architecture as the denoising model, reducing the computational complexity of the diffusion model. Experiments demonstrate that our Chest-Diffusion achieves the lowest FID score 24.456, under the computation budget of 118.918 GFLOPs, which is nearly one-third of the computational complexity of SD.

关键词： Accuracy Computational modeling Noise reduction Text to image computer architecture Transformers Diffusion models

来源：评论

学校读者我要写书评

暂无评论

Local Implicit Wavelet Transformer for Arbitrary-Scale Super-Resolution

arXiv

引用

arXiv 2024年

作者： Duan, Minghong Qu, Linhao Liu, Shaolei Wang, Manning Digital Medical Research Center Fudan University Shanghai China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention China

Implicit neural representations have recently demonstrated promising potential in arbitrary-scale Super-Resolution (SR) of images. Most existing methods predict the pixel in the SR image based on the queried coordinate and ensemble nearby features, overlooking the importance of incorporating high-frequency prior information in images, which results in limited performance in reconstructing high-frequency texture details in images. To address this issue, we propose the Local Implicit Wavelet Transformer (LIWT) to enhance the restoration of high-frequency texture details. Specifically, we decompose the features extracted by an encoder into four sub-bands containing different frequency information using Discrete Wavelet Transform (DWT). We then introduce the Wavelet Enhanced Residual Module (WERM) to transform these four sub-bands into high-frequency priors, followed by utilizing the Wavelet Mutual Projected Fusion (WMPF) and the Wavelet-aware Implicit Attention (WIA) to fully exploit the high-frequency prior information for recovering high-frequency details in images. We conducted extensive experiments on benchmark datasets to validate the effectiveness of LIWT. Both qualitative and quantitative results demonstrate that LIWT achieves promising performance in arbitrary-scale SR tasks, outperforming other state-of-the-art methods. The code is available at https://***/dmhdmhdmh/LIWT. Copyright © 2024, The Authors. All rights reserved.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

CHEST-DIFFUSION: A LIGHT-WEIGHT TEXT-TO-IMAGE MODEL FOR REPORT-TO-CXR GENERATION

arXiv

引用

arXiv 2024年

作者： Huang, Peng Gao, Xue Huang, Lihong Jiao, Jing Li, Xiaokang Wang, Yuanyuan Guo, Yi Department of Electronic Engineering Fudan University Shanghai200433 China Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai Shanghai200032 China

Text-to-image generation has important implications for generation of diverse and controllable images. Several attempts have been made to adapt Stable Diffusion (SD) to the medical domain. However, the large distribution difference between medical reports and natural texts, as well as high computational complexity in common stable diffusion limit the authenticity and feasibility of the generated medical images. To solve above problems, we propose a novel lightweight transformer-based diffusion model learning framework, Chest-Diffusion, for report-to-CXR generation. Chest-Diffusion employs a domain-specific text encoder to obtain accurate and expressive text features to guide image generation, improving the authenticity of the generated images. Meanwhile, we introduce a light-weight transformer architecture as the denoising model, reducing the computational complexity of the diffusion model. Experiments demonstrate that our Chest-Diffusion achieves the lowest FID score 24.456, under the computation budget of 118.918 GFLOPs, which is nearly one-third of the computational complexity of SD. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification 38

FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Fu, Kexue Luo, Xiaoyuan Qu, Linhao Wang, Shuo Xiong, Ying Maglogiannis, Ilias Gao, Longxiang Wang, Manning Qilu University of Technology Shandong Academy of Sciences Jinan China Digital Medical Research Center School of Basic Medical Sciences Fudan University China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention China Fudan University China University of Piraeus Greece Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

The expensive fine-grained annotation and data scarcity have become the primary obstacles for the widespread adoption of deep learning-based Whole Slide Images (WSI) classification algorithms in clinical practice. Unlike few-shot learning methods in natural images that can leverage the labels of each image, existing few-shot WSI classification methods only utilize a small number of fine-grained labels or weakly supervised slide labels for training in order to avoid expensive fine-grained annotation. They lack sufficient mining of available WSIs, severely limiting WSI classification performance. To address the above issues, we propose a novel and efficient dual-tier few-shot learning paradigm for WSI classification, named FAST. FAST consists of a dual-level annotation strategy and a dual-branch classification framework. Firstly, to avoid expensive fine-grained annotation, we collect a very small number of WSIs at the slide level, and annotate an extremely small number of patches. Then, to fully mining the available WSIs, we use all the patches and available patch labels to build a cache branch, which utilizes the labeled patches to learn the labels of unlabeled patches and through knowledge retrieval for patch classification. In addition to the cache branch, we also construct a prior branch that includes learnable prompt vectors, using the text encoder of visual-language models for patch classification. Finally, we integrate the results from both branches to achieve WSI classification. Extensive experiments on binary and multi-class datasets demonstrate that our proposed method significantly surpasses existing few-shot classification methods and approaches the accuracy of fully supervised methods with only 0.22% annotation costs. All codes and models will be publicly available on https://***/fukexue/FAST. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Motion Classification Based on sEMG Signals Using Deep Learning 4th

Motion Classification Based on sEMG Signals Using Deep Learn...

引用

4th International Conference on Machine Learning and Intelligent Communications, MLICOM 2019

作者： Shen, Shu Gu, Kang Chen, Xinrong Wang, Ruchuan School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing210023 China Academy for Engineering and Technology Fudan University Shanghai200433 China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China

ISBN: (纸本)9783030323875

Nowadays, surface electromyography (sEMG) signal plays an important role in helping physically disabled people during daily life. The development of electronic information technology has also led to the emergence of low-cost, multi-channel, wearable sEMG signal acquisition devices. Therefore, this paper proposes a new motion recognition model based on deep learning to improve the accuracy of motion recognition of sEMG signals. The model uses architecture including 6 convolutional layers and 6 pooling layers which enables the Batch Normalization layer to enhance network performance and prevent overfitting. In the experiment, NinaPro DB5 data set was used for training and testing. The data set consists of sEMG signal data collected by the double Myo armbands which contains data of 52 movements for 10 subjects. The results show that the accuracy of about 90% can be achieved when using 52 sEMG signal data from every single subject or all subjects. © 2019, ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Distinct immune escape and microenvironment between RG-like and pri-OPC-like glioma revealed by single-cell RNA-seq analysis

引用

Frontiers of Medicine 2024年第1期18卷 147-168页

作者： Weiwei Xian Mohammad Asad Shuai Wu Zhixin Bai Fengjiao Li Junfeng Lu Gaoyu Zu Erin Brintnell Hong Chen Ying Mao Guomin Zhou Bo Liao Jinsong Wu Edwin Wang Linya You Department of Human Anatomy&Histoembryology School of Basic Medical SciencesFudan UniversityShanghai200032China Cumming School of Medicine University of CalgaryCalgaryAlbertaT2N 4N1Canada Glioma Surgery Division Department of NeurosurgeryHuashan HospitalFudan UniversityShanghai200040China Department of Pathology Huashan HospitalFudan UniversityShanghai200040China Department of Neurosurgery Huashan HospitalFudan UniversityShanghai200040China Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention Fudan UniversityShanghai200040China School of Mathematics and Statistics Hainan Normal UniversityHaikou570100China

The association of neurogenesis and gliogenesis with glioma remains *** conducting single-cell RNA-seq analyses on 26 gliomas,we reported their classification into primitive oligodendrocyte precursor cell(pri-OPC)-like and radial glia(RG)-like tumors and validated it in a public cohort and TCGA *** RG-like tumors exhibited wild-type isocitrate dehydrogenase and tended to carry EGFR mutations,and the pri-OPC-like ones were prone to carrying TP53 *** subclones only in pri-OPC-like tumors showed substantially down-regulated MHC-I genes,suggesting their distinct immune evasion ***,the two subgroups appeared to extensively modulate glioma-infiltrating lymphocytes in distinct *** specific genes not expressed in normal immune cells were found in glioma-infiltrating *** example,glial/glioma stem cell markers OLIG1/PTPRZ1 and B cell-specific receptors IGLC2/IGKC were expressed in pri-OPC-like and RG-like glioma-infiltrating lymphocytes,*** expression was positively correlated with those of immune checkpoint genes(e.g.,LGALS33)and poor survivals as validated by the increased expression of LGALS3 upon IGKC overexpression in Jurkat *** finding indicated a potential inhibitory role in tumor-infiltrating lymphocytes and could provide a new way of cancer immune evasion.

关键词： single-cell RNA-seq glioma radial glia primitive oligodendrocyte precursor cell immune escape

来源：评论

学校读者我要写书评

暂无评论

Efficient recursive methods for partial fraction expansion of general rational functions

引用

Journal of Applied Mathematics 2014年第1期2014卷

作者： Ma, Youneng Yu, Jinhua Wang, Yuanyuan Department of Electronic Engineering Fudan University Shanghai 200433 China Key Lab of Medical Imaging Computing Computer Assisted Intervention of Shanghai Shanghai 200433 China

Partial fraction expansion (pfe) is a classic technique used in many fields of pure or applied mathematics. The paper focuses on the pfe of general rational functions in both factorized and expanded form. Novel, simple, and recursive formulas for the computation of residues and residual polynomial coefficients are derived. The proposed pfe methods require only simple pure-algebraic operations in the whole computation process. They do not involve derivatives when tackling proper functions and require no polynomial division when dealing with improper functions. The methods are efficient and very easy to apply for both computer and manual calculation. Various numerical experiments confirm that the proposed methods can achieve quite desirable accuracy even for pfe of rational functions with multiple high-order poles or some tricky ill-conditioned poles. © 2014 Youneng Ma et al.

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：