检索结果-内蒙古大学图书馆

RobNODDI: Robust NODDI Parameter Estimation with Adaptive Sampling under Continuous Representation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xiao, Taohui Cheng, Jian Fan, Wenxin Yang, Jing Li, Cheng Dong, Enqing Wang, Shanshan School of Mechanical Electrical & Information Engineering Shandong University Weihai264209 China State Key Laboratory of Software Development Environment Beihang University Beijing China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Zhejiang Hangzhou China Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Peng Cheng Laboratory Guangdong Shenzhen China

Neurite Orientation Dispersion and Density Imaging (NODDI) is an important imaging technology used to evaluate the microstructure of brain tissue, which is of great significance for the discovery and treatment of various neurological diseases. Current deep learning-based methods perform parameter estimation through diffusion magnetic resonance imaging (dMRI) with a small number of diffusion gradients. These methods speed up parameter estimation and improve accuracy. However, the diffusion directions used by most existing deep learning models during testing needs to be strictly consistent with the diffusion directions during training. This results in poor generalization and robustness of deep learning models in dMRI parameter estimation. In this work, we verify for the first time that the parameter estimation performance of current mainstream methods will significantly decrease when the testing diffusion directions and the training diffusion directions are inconsistent. A robust NODDI parameter estimation method with adaptive sampling under continuous representation (RobNODDI) is proposed. Furthermore, long short-term memory (LSTM) units and fully connected layers are selected to learn continuous representation signals. To this end, we use a total of 100 subjects to conduct experiments based on the Human Connectome Project (HCP) dataset, of which 60 are used for training, 20 are used for validation, and 20 are used for testing. The test results indicate that RobNODDI improves the generalization performance and robustness of the deep learning model, enhancing the stability and flexibility of deep learning NODDI parameter estimatimation applications. Copyright © 2024, The Authors. All rights reserved.

关键词：

Fast Heuristic Algorithms for the Multiple Strip Packing Problem 1

学校读者我要写书评

暂无评论

20th International Conference on Mathematical Optimization Theory and Operations research , MOTOR 2021

作者： Vasilyev, Igor Ushakov, Anton V. Barkova, Maria V. Zhang, Dong Ren, Jie Chen, Juan Matrosov Institute for System Dynamics and Control Theory of SB RAS 134 Lermontov Street Irkutsk664033 Russia Algorithm and Technology Development Department Global Technical Service Department Huawei Technologies Co. Ltd. Dongguan China Moscow Advanced Software Technology Lab Huawei Russian Research Institute Moscow Russia

ISBN: (数字)9783030864330

ISBN: (纸本)9783030864323

In this paper we address the so-called two-dimensional Multiple Strip Packing Problem (MSPP). There is a set of rectangles and a set of strips, where each strip has a pre-defined width. The problem is to find a feasible packing of all the rectangles into the strips so as the maximal height of the packing over all the strips is minimized. A packing is feasible if all the rectangles are placed into the strips and not overlapped. In case of only one strip, the problem is widely known as the Strip Packing Problem (SPP). Many effective constructive heuristics for SPP are based on the so-called skyline representation of a packing pattern. We generalized this approach for the case of multiple strips and developed a randomized local search, which embeds the proposed skyline heuristic to compute the objective value for a packing. We also introduced the two-dimensional level multiple strip packing problem and developed some level-based constructive heuristics. We report computational results on real-life problem instances arisen in an application of MSPP in scheduling computing jobs on multiple Spark computer clusters. © 2021, Springer Nature Switzerland AG.

关键词： Heuristic algorithms

3D ANATOMICAL STRUCTURE-GUIDED DEEP LEARNING FOR ACCURATE DIFFUSION MICROSTRUCTURE IMAGING

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ma, Xinrui Cheng, Jian Fan, Wenxin Wu, Ruoyou Ye, Yongquan Wang, Shanshan Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Zhejiang Hangzhou China Pengcheng Laboratory Guangdong Shenzhen China United Imaging Healthcare HoustonTX United States

Diffusion magnetic resonance imaging (dMRI) is a crucial noninvasive technique for exploring the microstructure of the living human brain. Traditional hand-crafted and model-based tissue microstructure reconstruction methods often require extensive diffusion gradient sampling, which can be time-consuming and limits the clinical applicability of tissue microstructure information. Recent advances in deep learning have shown promise in microstructure estimation;however, accurately estimating tissue microstructure from clinically feasible dMRI scans remains challenging without appropriate constraints. This paper introduces a novel framework that achieves high-fidelity and rapid diffusion microstructure imaging by simultaneously leveraging anatomical information from macro-level priors and mutual information across parameters. This approach enhances time efficiency while maintaining accuracy in microstructure estimation. Experimental results demonstrate that our method outperforms four state-of-the-art techniques, achieving a peak signal-to-noise ratio (PSNR) of 30.51±0.58 and a structural similarity index measure (SSIM) of 0.97±0.004 in estimating parametric maps of multiple diffusion models. Notably, our method achieves a 15× acceleration compared to the dense sampling approach, which typically utilizes 270 diffusion gradients. © 2025, CC BY-NC-ND.

关键词： Tissue

Review of the State-of-the-Art of Data Gloves

学校读者我要写书评

暂无评论

Review of the State-of-the-Art of Data Gloves

IEEE International Symposium on Smart Electronic systems (iSES)

作者： Mingzhang Pan Yingzhe Tang Hongqi Li Guangxi Key Laboratory of Manufacturing System & Advanced Manufacturing Technology School of Mechanical Engineering Guangxi University Nanning China Brain-Controlled Intelligent Systems Laboratory School of Software Northwestern Polytechnical University Xi'an China Yangtze River Delta Research Institute of NPU Taicang China

ISBN: (纸本)9798350399233

Human-machine interaction has been the focus of recent research, with data gloves as one of the approaches gaining popularity for their high accuracy and convenience. This paper summarizes the latest research status of data gloves with a focus on the area of glove-based gesture recognition. The core technology of gesture recognition is described in detail from data processing to classification, and a quantitative analysis of the recent research is conducted. We found that though studies on applications and algorithms are the mainstream, the hardware design also accounts for a pretty large proportion of about 30%. Moreover, the number of gestures, subjects, and algorithms for majority of relevant studies has been summarized.

关键词： Human computer interaction Statistical analysis Gesture recognition Data gloves Data processing Hardware Classification algorithms

Simultaneous Q-Space Sampling Optimization and Reconstruction for Fast and High-Fidelity Diffusion Magnetic Resonance Imaging

学校读者我要写书评

暂无评论

Simultaneous Q-Space Sampling Optimization and Reconstructio...

IEEE International Symposium on Biomedical Imaging

作者： Jing Yang Jian Cheng Cheng Li Wenxin Fan Juan Zou Ruoyou Wu Qiegen Liu Hairong Zheng Shanshan Wang Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Hangzhou China Department of Electronic Information Engineering Nanchang University Nanchang China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Diffusion Magnetic Resonance Imaging (dMRI) plays a crucial role in the noninvasive investigation of tissue microstructural properties and structural connectivity in the in vivo human brain. However, to effectively capture the intricate characteristics of water diffusion at various directions and scales, it is important to employ comprehensive q-space sampling. Unfortunately, this requirement leads to long scan times, limiting the clinical applicability of dMRI. To address this challenge, we propose SSOR, a Simultaneous q-Space sampling Optimization and Reconstruction framework. We jointly optimize a subset of q-space samples using a continuous representation of spherical harmonic functions and a reconstruction network. Additionally, we integrate the unique properties of diffusion magnetic resonance imaging (dMRI) in both the q-space and image domains by applying l1-norm and total-variation *** experiments conducted on HCP data demonstrate that SSOR has promising strengths both quantitatively and qualitatively and exhibits robustness to noise.

关键词： Water In vivo Limiting Magnetic resonance imaging Harmonic analysis Robustness Image reconstruction

Simultaneous q-Space Sampling Optimization and Reconstruction for Fast and High-fidelity Diffusion Magnetic Resonance Imaging

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Jing Cheng, Jian Li, Cheng Fan, Wenxin Zou, Juan Wu, Ruoyou Wang, Shanshan Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Peng Cheng Laboratory Guangdong Shenzhen China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Yuhang District Hangzhou China

关键词： Magnetic resonance imaging

AID-DTI: ACCELERATING HIGH-FIDELITY DIFFUSION TENSOR IMAGING WITH DETAIL-PRESERVING MODEL-BASED DEEP LEARNING

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fan, Wenxin Cheng, Jian Li, Cheng Ma, Xinrui Yang, Jing Zou, Juan Wu, Ruoyou Liu, Qiegen Wang, Shanshan Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Zhejiang Hangzhou China Peng Cheng Laboratory Guangdong Shenzhen China Nan Chang University Jiang Xi Nan Chang China

Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI). Nevertheless, existing methods tend to suffer from Rician noise and detail loss in reconstructing the DTI-derived parametric maps especially when sparsely sampled q-space data are used. This paper proposes a novel method, AID-DTI (Accelerating hIgh fiDelity Diffusion Tensor Imaging), to facilitate fast and accurate DTI with only six measurements. AID-DTI is equipped with a newly designed Singular Value Decomposition (SVD)-based regularizer, which can effectively capture fine details while suppressing noise during network training. Experimental results on Human Connectome Project (HCP) data consistently demonstrate that the proposed method estimates DTI parameter maps with fine-grained details and outperforms three state-of-the-art methods both quantitatively and qualitatively. Copyright © 2024, The Authors. All rights reserved.

关键词： Singular value decomposition

An Ultrasensitive Aptasensor for 8-Hydroxy-2′-Deoxyguanosine of Human Urine Detection Based on Coftapb-Dmtp@Mwcnt-Cooh Nanocomposites and Cefeox-C@Au@Apt Nanoprobe

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Wang, Jinhao Zhou, Qing Li, Zhanchao Ming, Pingtao Sun, Duanping Zhai, Haiyun College of Pharmacy Guangdong Pharmaceutical University Guangzhou510006 China School of Chemistry and Chemical Engineering Guangdong Pharmaceutical University Zhongshan528458 China Guangdong Provincial Key Laboratory of Pharmaceutical Bioactive Substances Center for Drug Research and Development Guangdong Pharmaceutical University Guangzhou510006 China Guangdong Provincial Key Laboratory of Advanced Drug Delivery Guangdong Provincial Engineering Center of Topical Precise Drug Delivery System Guangdong Pharmaceutical University Guangzhou510006 China

An ultrasensitive electrochemical aptasensor was proposed for quantitative detection of 8-hydroxy-2′-deoxyguanosine (8-OHdG). Covalent organic framework (COFTAPB-DMTP) and carboxylated multi-walled carbon nanotubes (MWCNT-COOH) were used to prepare COFTAPB-DMTP@MWCNT-COOH (TAPB, 1,3,5-tris(4-aminopheny) benzene;DMTP, 5-dimethoxybenzene-1,4-dicarboxaldehyde) nanocomposites as the electrode sensing platform. COFTAPB-DMTP@MWCNT-COOH displayed excellent biocompatibility, a large specific surface area, and efficient conductivity, facilitating accelerated electron transfer rates. Furthermore, the cerium iron oxide-carbon nanocomposites (CeFeOx-C) derived from UiO-66-CeFe bimetallic organic framework showed outstanding peroxidase-like activity. Gold nanoparticles-modified CeFeOx-C effectively loads 8-OHdG-aptamer, yielding novel CeFeOx-C@Au@Apt nanoprobes. CeFeOx-C@Au@Apt nanoprobes were immobilized on the electrode via base pairing to thiolated cDNA and the signal change was detected in the environment of hydroquinone and H2O2. In the presence of 8-OHdG, Apt-cDNA unwound, leading to CeFeOx-C@Au@Apt to fall off the electrode, thereby causing distinguishable electrochemical variations. The optimized aptasensor for 8-OHdG showed a wide linear range from 10 fg/mL to 50 ng/mL, with a low detection limit of 1.06 fg/mL. The reliability of this aptasensor was confirmed using human urine samples, yielding satisfactory results, highlighting its potential in evaluating the extent of oxidative DNA damage. Crucially, the aptasensor's ideal performance position it as a promising approach for detecting various biomolecules through modifications the aptamers sequence modifications. © 2024, The Authors. All rights reserved.

关键词： Nanocomposites

An Ultrasensitive Aptasensor for 8-Hydroxy-2′-Deoxyguanosine of Human Urine Detection Based on CofTAPB-DMTP@Mwcnt-Cooh Nanocomposites and CeFeOx-C@Au@Apt Nanoprobe

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Zhai, Haiyun Wang, Jinhao Zhou, Qing Li, Zhanchao Ming, Pingtao Sun, Duanping College of Pharmacy Guangdong Pharmaceutical University Guangzhou510006 China School of Chemistry and Chemical Engineering Guangdong Pharmaceutical University Zhongshan528458 China Guangdong Provincial Key Laboratory of Pharmaceutical Bioactive Substances Center for Drug Research and Development Guangdong Pharmaceutical University Guangzhou510006 China Guangdong Provincial Key Laboratory of Advanced Drug Delivery Guangdong Provincial Engineering Center of Topical Precise Drug Delivery System Guangdong Pharmaceutical University Guangzhou510006 China

关键词： Nanocomposites