检索结果-内蒙古大学图书馆

2007 IEEE Nuclear Science Symposium Conference, vol.11

作者： Axel W. Weber Roland Haubner Bernhard Wolf Sibylle I. Ziegler Nuklearmedizinische Klinik und Poliklinik Klinikum rechts der Isar Technische Universität München Munchen Germany Medizinische Klinik Innsbruck Universitätsklinik für Nuklearmedizin Innsbruck Austria Heinz Nixdorf-Lehrstuhl für Medizinische Elektronik Technische Universität München Munchen Germany

So far FBP (Filtered Back Projection) is still the standard reconstruction method for kinetic modeling of PET data. Iterative reconstruction algorithms, such as OSEM (Ordered Subsets Expectation Maximization) or MAP (Maximum A Posteriori) create images with better signal-to-noise ratios and less streak artifacts. This is of special interest in the short-time frames with low statistics at the beginning of a dynamic acquisition. To determine if iteratively reconstructed PET data could be used for kinetic modeling of pre-clinical data, we compared OSEM2D and OSEM3D/MAP data with FBP data using microPET data. Nude mice (n=6) bearing a human melanoma tumor were imaged over 90 minutes with a FOCUS 120 microPET. We applied 18F-Galacto-RGD via a tail vein catheter into the animal (9-19 MBq). 18F-Galacto-RGD is used for imaging the α{sub}vβ{sub}3 expression during angiogenesis and on specific tumor cells. Each list mode dataset was binned into 19 frames and reconstructed with FBP, OSEM2D and OSEM3D/MAP. The data was not corrected for scatter and attenuation. Volumes of interest (VOIs) were drawn on the heart and tumor tissue. No corrections for spillover and partial volume effect were applied. For the kinetic modeling of the tumor data a standard 2-tissue-compartment model with reversible binding was used (fitting parameters: K{sub}1, k{sub}2, k{sub}3, k{sub}4 (rate constants) and D{sub}v (vascular blood fraction)). The input function TACs of the iteratively reconstructed data showed no considerable difference to the FBP data. Only the OSEM3D/MAP TACs for the tumor VOIs were clearly and consistently higher for all datasets than the corresponding FBP and OSEM2D TACs. Kinetic modeling shows negligible parameter changes for K{sub}1, k{sub}2, k{sub}3 and k{sub}4 for all reconstruction algorithms. The higher OSEM3D/MAP tumor values are compensated only with an overestimated D{sub}v (D{sub}v(FBP)=2.2%, D{sub}v(OSEM3D/MAP)=3.3%). Further work needs to be done on optimizing the iter

关键词： reconstruction algorithms Mice Neoplasms Kinetic theory Image reconstruction Positron emission tomography Signal to noise ratio Statistics Humans Malignant tumors

来源：评论

学校读者我要写书评

暂无评论

Performance comparison of wavefront reconstruction and control algorithms for Extremely Large Telescopes

引用

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION 2010年第11期27卷 A9-A18页

作者： Montilla, I. Bechet, C. Le Louarn, M. Reyes, M. Tallon, M. Inst Astrofis Canarias Santa Cruz de Tenerife 38205 Spain Univ Lyon F-69003 Lyon France ESO D-85748 Garching Germany Univ Lyon 1 Observ Lyon F-69230 St Genis Laval France Ecole Normale Super Lyon Ctr Rech Astrophys Lyon UMR 5574 CNRS F-69007 Lyon France

Extremely Large Telescopes (ELTs) are very challenging with respect to their adaptive optics (AO) requirements. Their diameters and the specifications required by the astronomical science for which they are being designed imply a huge increment in the number of degrees of freedom in the deformable mirrors. Faster algorithms are needed to implement the real-time reconstruction and control in AO at the required speed. We present the results of a study of the AO correction performance of three different algorithms applied to the case of a 42-m ELT: one considered as a reference, the matrix-vector multiply (MVM) algorithm;and two considered fast, the fractal iterative method (FrIM) and the Fourier transform reconstructor (FTR). The MVM and the FrIM both provide a maximum a posteriori estimation, while the FTR provides a least-squares one. The algorithms are tested on the European Southern Observatory (ESO) end-to-end simulator, OCTOPUS. The performance is compared using a natural guide star single-conjugate adaptive optics configuration. The results demonstrate that the methods have similar performance in a large variety of simulated conditions. However, with respect to system misregistrations, the fast algorithms demonstrate an interesting robustness. c 2010 Optical Society of America

关键词： Adaptive optics Deformable mirrors Fourier transforms Large telescopes reconstruction algorithms Spatial resolution

来源：评论

学校读者我要写书评

暂无评论

APG-Net: APG Optimization-Induced Multiscale Attention Network for MRI reconstruction From Undersampled k-Space Measurements

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Gan, Hongping Zhao, Zitong Chen, Yunong Shan, Shanshan Shi, Baoshun Liu, Chunyi Northwestern Polytech Univ Sch Software Xian 710072 Peoples R China Wuhan Univ State Key Lab Informat Engn Surveying Mapping & Re Wuhan 430072 Peoples R China Soochow Univ Sch Radiol & Interdisciplinary Sci State Key Lab Radiat Med & Protect Suzhou 215123 Peoples R China Yanshan Univ Sch Informat Sci & Engn Qinhuangdao 066004 Peoples R China

Compressed sensing magnetic resonance imaging (CS-MRI) can quickly reconstruct magnetic resonance (MR) images from undersampled k-space measurements, thereby accelerating MRI reconstruction. However, existing CS-MRI methods suffer from insufficient information interaction and an inability to adequately capture image features during the iterative reconstruction process, resulting in the reconstructed images having room for improvement in detail. Inspired by the accelerated proximal gradient (APG) algorithm, we propose an APG optimization-induced deep multiscale attention network, called APG-Net, for accelerating MRI reconstruction from k-space measurements. APG-Net transforms the traditional APG algorithm into a learnable network structure while introducing efficient feature extraction modules to effectively capture the features of the k-space data, resulting in high-quality MR image reconstruction. Specifically, it unrolls the iterative steps of the APG algorithm into a cascade block of fixed reconstruction phases, which include the iterative unfolding module (IUM) and multiscale dual-attention block (MDAB). The proposed IUM enhances feature fusion by leveraging information interaction between iterative phases. Moreover, the customized MDAB is utilized to extract multiscale feature information from the k-space measurements while enhancing attention to spatial and channel-related features in both dimensions, effectively boosting feature extraction capability. Extensive experiments demonstrate that our proposed APG-Net achieves remarkable performance on MRI reconstruction tasks in contrast to state-of-the-art methods. Our code is available at APG-Net.

关键词： Image reconstruction Feature extraction Magnetic resonance imaging Iterative algorithms Data mining Signal processing algorithms reconstruction algorithms Convergence Training Optimization Accelerated proximal gradient (APG) compressed sensing (CS) deep learning (DL) magnetic resonance (MR) imaging undersampled measurements

来源：评论

学校读者我要写书评

暂无评论

A U-Residual Local Window Transformer for Ultrasound Images Super-Resolution reconstruction

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Yan, Yadi Liu, Yingying Qiao, Xiaoyang Wang, Diya Xu, Lei Su, Xiao Wan, Mingxi Xi An Jiao Tong Univ Minist Educ Sch Life Sci & Technol Key Lab Biomed Informat Engn Xian 710049 Peoples R China Xi An Jiao Tong Univ Sch Life Sci & Technol Dept Biomed Engn Xian 710049 Peoples R China Xian Hosp Tradit Chinese Med Xian 710021 Peoples R China

Ultrasound images have inherent disadvantages, such as blurred details and high noise, and super-resolution (SR) reconstruction will improve the image quality and help for more accurate clinical diagnosis. In order to solve the problem that it is difficult to capture local feature information and lose important information in the process of downsampling, we propose an SR reconstruction method of ultrasound single image based on U-residual local window transformer (U-RLWT). Specifically, we construct a network encoder module that fuses two residual swim transformer blocks and a downsampling layer. It obtains more low-frequency information from ultrasound images by improving the receptive field of the feature extractor. Then, to combine the feature information between the layers and recover the feature map, the decoder module was constructed by using the residual swim transformer block and the upsampling layer. Finally, the reconstruction module was designed with convolution and Pixel-shuffle network to realize the SR reconstruction of ultrasound single images. Experimental results show that, compared with the advanced reconstruction methods, the proposed method can reconstruct the better results compared with the ground truth. When applied to larynx ultrasound images and PICMUS datasets, it achieves the highest peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) on the scale factors of x2 and x4 .

关键词： Image reconstruction Feature extraction Ultrasonic imaging Superresolution Transformers Decoding Data mining reconstruction algorithms Convolution Vectors Deep learning residual super-resolution (SR) texture features transformer ultrasound images

来源：评论

学校读者我要写书评

暂无评论

Representation Model for Electromagnetic Maps reconstruction via Sparse Nodes

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Liu, Gongxu Liu, Xu-An Huang, Lu Li, Long Gao, Xinbo Xidian Univ Sch Elect Engn Key Lab High Speed Circuit Design & EMC Minist Educ Xian 710071 Peoples R China Xidian Univ Microelect Sch Xian 710071 Peoples R China State Key Lab Satellite Nav Syst & Equipment Techn Shijiazhuang Peoples R China Xidian Univ Sch Elect Engn Xian 710071 Peoples R China Chongqing Univ Posts & Telecommun Chongqing Key Lab Image Cognit Chongqing 400065 Peoples R China

Electromagnetic (EM) maps hold promise for providing strategic support for future localization and navigation. However, reconstruction of EM maps under sparse nodes conditions is a critical challenge, which constrains the reliable and rapid construction of EM maps. To address this issue, we absorb the concept of Moran's index and use location index, fingerprint index, and scaling index to quantify the topology, quality, and quantity of EM nodes, respectively. Besides, three node selection criteria were used: one based on random selection, another using the K-means clustering, and the third involving affinity propagation (AP) clustering. Under each criterion, the overall EM maps were reconstructed using four representative interpolation methods: inverse distance weighting (IDW), modified Shepard's method (MSM), Kriging algorithm (KGA), and biharmonic spline interpolation (v4). Extensive experiments were conducted to verify the representation model. Experimental results indicate that the node selection criterion based on AP clustering outperforms the K-means criterion, which itself is superior to random selection criterion. This is attributed to the fact that under the same conditions, the AP clustering node selection criterion can better take the quality and the topological relationship of EM nodes into account. Another significant finding is that with good node selection criterion and reconstruction algorithms, only approximately 0.3%-0.5% of the nodes are required to achieve the reconstruction performance that would otherwise require up to 20% or more of the nodes. The above conclusions are of good guidance for the reliable and rapid reconstruction of EM maps via sparse or limited nodes.

关键词： Location awareness Interpolation Navigation Affinity propagation reconstruction algorithms Topology Indexes Reliability Electromagnetics Splines (mathematics) Affinity propagation (AP) clustering electromagnetic (EM) map interpolation method localization and navigation reconstruction sparse node

来源：评论

学校读者我要写书评

暂无评论

Exploring Spatial Feature Regularization in Deep-Learning-Based TomoSAR reconstruction: A Preliminary Study and Performance Analysis

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Zeng, Tianjiao Zhan, Xu Ren, Yu Ma, Xiangdong Liu, Liang Shi, Jun Wei, Shunjun Wang, Mou Zhang, Xiaoling Univ Elect Sci & Technol China Sch Aeronaut & Astronaut Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China

Tomographic synthetic aperture radar (TomoSAR) shows great potential for high-quality 3-D mapping, especially in urban areas. As TomoSAR reconstruction methods advance into the deep learning (DL) era, current studies have demonstrated DL's strengths in both precision and efficiency. However, for reconstructing urban areas with prominent spatial features from building structures, current studies focus on pixel-by-pixel reconstruction without leveraging the potential benefits of these features. In this context, an exploratory study to introduce spatial feature regularization in DL reconstruction is proposed for the first time, focusing on feature description, modeling, and regularization. Spatial features are analyzed and summarized by sharp edges and regular geometric shapes within the scene. To model these features, 2-D slices are used as the basic reconstruction units, and a general intraslice and interslice strategy is proposed to harness features within and between slices. Two-dimensional slices are fused into the entire 3-D scene. Two methods of fusion are designed: parallel and serial. To regularize these features, a new computational framework called light reconstruction and enhancement is designed, which includes two stages: light reconstruction with sparsity feature regularization and enhancement with spatial feature regularization. Finally, to evaluate performance, we design an extensive evaluation framework. A newly self-constructed compound urban building simulation dataset, combined with two public measured data, forms six different tests ranging from a classical close point resolution test to a diverse urban landscape challenge test. Evaluation results reveal the effectiveness of the designs and the boost provided by spatial feature regularization, resulting in higher reconstruction precision, more complete building spatial structure retrieval, and fewer outliers.

关键词： Image reconstruction Three-dimensional displays Tensors Buildings reconstruction algorithms Urban areas Discrete Fourier transforms Deep learning Vectors Spatial resolution Deep learning (DL) deep unfolding model-driven spatial regularization tomographic synthetic aperture radar (TomoSAR) reconstruction

来源：评论

学校读者我要写书评

暂无评论

Joint Edge Optimization Deep Unfolding Network for Accelerated MRI reconstruction

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING

引用

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2025年 11卷 11-23页

作者： Luo, Yu Cai, Yue Ling, Jie Ji, Yingdan Tie, Yanmei Yao, Shun Guangdong Univ Technol Sch Comp Sci Guangzhou 510006 Peoples R China Guangdong Univ Technol Sch Math & Stat Guangzhou 510520 Peoples R China Harvard Med Sch Brigham & Womens Hosp Dept Neurosurg Boston MA 02115 USA Sun Yat Sen Univ Affiliated Hosp 1 Dept Neurosurg Guangzhou 510080 Peoples R China

Magnetic Resonance Imaging (MRI) is a widely used imaging technique, however it has the limitation of long scanning time. Though previous model-based and learning-based MRI reconstruction methods have shown promising performance, most of them have not fully utilized the edge prior of MR images, and there is still much room for improvement. In this paper, we build a joint edge optimization model that not only incorporates individual regularizers specific to both the MR image and the edges, but also enforces a co-regularizer to effectively establish a stronger correlation between them. Specifically, the edge information is defined through a non-edge probability map to guide the image reconstruction during the optimization process. Meanwhile, the regularizers pertaining to images and edges are incorporated into a deep unfolding network to automatically learn their respective inherent a-priori information. Numerical experiments, consisting of multi-coil and single-coil MRI data with different sampling schemes at a variety of sampling factors, demonstrate that the proposed method outperforms other state-of-the-art methods.

关键词： Image edge detection Image reconstruction Magnetic resonance imaging Imaging Optimization Neural networks Adaptation models Iterative methods reconstruction algorithms Compressed sensing Accelerated MRI edge prior deep unfolding inverse problem parallel imaging

来源：评论

学校读者我要写书评

暂无评论

reconstruction of Fan Beam X-Ray Fluorescence Computed Tomography Based on Parallel Hole Collimator via Total Variation and Ordered Subsets

引用

IEEE ACCESS 2025年 13卷 7793-7800页

作者： Jiang, Shanghai Chen, Le Zhong, Jie Ai, Li Yang, Hua Lu, Hong Chongqing Univ Technol Cent Hosp Peoples Hosp Chongqing 7 Dept Radiol Chongqing 400054 Peoples R China Chongqing Tradit Chinese Med Hosp Dept Med Imaging Chongqing 400021 Peoples R China Chongqing Univ Technol Chongqing Key Lab Opt Fiber Sensor & Photoelect De Chongqing 400054 Peoples R China

In this paper, an Ordered Subsets Expectation Maximization (OSEM) reconstruction algorithm based on Total Variation (TV) constraint was applied for sparse reconstruction of X-ray fluorescence CT. First, the Geant4 Monte Carlo code was used to simulate the imaging process of fan beam X-ray fluorescence CT imaging system based on parallel hole collimator. Then, the reconstructed image quality of the proposed algorithm with varying numbers of projections was evaluated using RMSE and CNR. Finally, the relationship between the number of subsets of the algorithm and the quality of the reconstructed image and the reconstruction time was explored. The results demonstrated that, compared with the conventional OSEM algorithm, the proposed OSEM algorithm based on Total Variation constraint has higher quality of reconstructed images at different projection numbers, and the reconstruction time of the algorithm decreases with the increase of subset, which achieves the purpose of improving the quality of the reconstructed image and reducing the reconstruction time when sparse reconstruction.

关键词： Image reconstruction Fluorescence X-ray imaging Phantoms Computed tomography TV Photonics Fans Imaging reconstruction algorithms X-ray fluorescence CT image reconstruction Monte Carlo simulation sparse projection total variation

来源：评论

学校读者我要写书评

暂无评论

A New Algebraic Approach for String reconstruction From Substring Compositions

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2025年第1期71卷 125-137页

作者： Gupta, Utkarsh Mahdavifar, Hessam Northeastern Univ Dept Elect & Comp Engn Boston MA 02115 USA

In this paper, we propose a new algorithm for the problem of string reconstruction from its substring composition multiset. Motivated by applications in polymer-based data storage for recovering strings from tandem mass-spectrometry sequencing, the proposed algorithm leverages the equivalent polynomial formulation of the problem which facilitates efficient parallel implementation. The computational complexity of the proposed reconstruction algorithm is upper bounded by 6.5n(2) finite field operations, where the field size is upper bounded by 10n , implying that the computational complexity is upper bounded by 6.5n(2)(3.22+log n) binary operations. Furthermore, it allows parallelization leading to O(n log n) reconstruction latency. We characterize sufficient conditions for a length n binary string that guarantee the string's reconstruction time complexity to be bounded polynomially. Moreover, the sufficient conditions on binary strings that guarantee reconstruction in polynomial time are more general than the conditions for the algorithm by Acharya et al. This is used to construct new codebooks of reconstruction codes that have efficient encoding procedures, and are larger, by at least a linear factor in size, compared to the previously best known construction by Pattabiraman et al., (2023).

关键词： Plastics Codes Polynomials Backtracking reconstruction algorithms DNA Proteins Encoding Sufficient conditions Memory reconstruction codes substring compositions algebraic decoding

来源：评论

学校读者我要写书评

暂无评论

A 3-D Track reconstruction Algorithm for Preresearch of the STCF MDC L1 Trigger

引用

IEEE TRANSACTIONS ON NUCLEAR SCIENCE 2025年第3期72卷 429-437页

作者： Hao, Yidi Feng, Changqing Zhou, Zixuan Dong, Wenhao Fang, Zhujun Hu, Xueye Zhou, Hang Liu, Shubin Univ Sci & Technol China State Key Lab Particle Detect & Elect Hefei 230026 Peoples R China Univ Sci & Technol China Dept Modern Phys Hefei 230026 Peoples R China

The proposed Super Tau Charm Facility (STCF) is an electron-positron collider with high luminosity. Under the conditions of a high radiation, high counting-rate environment, and a pure physics event rate of up to 400 kHz, for a Level 1 (L1) trigger system, it is crucial to suppress background events to an acceptable rate. To this end, this study presents a 3-D track reconstruction algorithm for the preresearch of the STCF main drift chamber (MDC) L1 trigger. The proposed algorithm can reject tracks outside the interaction region and provide 3-D track information to the global trigger logic (GTL) of an L1 trigger for further analysis with other subdetectors. By using hit information from the MDC and the transverse momentum ( p(T)) and azimuthal angle (phi) from previous research on 2-D reconstruction, this study reconstructs the z (longitudinal) position for the track vertex using a neural network-based method with an innovative stereo track segment (TS) design. The neural network is trained using high granularity quantization (HGQ) to reduce resource consumption while maintaining resolution. The proposed method is implemented into a field-programmable gate array (FPGA) using the hls4ml. The achieved resolution of the z-vertex reconstruction of a single track ( z is an element of [-50, 50] cm) is approximately 2.8 cm, which can ensure rejecting 97% beam background tracks in a +/- 3 sigma interval.

关键词： Wires Three-dimensional displays reconstruction algorithms Detectors Physics Data acquisition Neural networks Approximation algorithms Monte Carlo methods Logic Hls4ml Level 1 (L1) trigger algorithm main drift chamber (MDC) multilayer perceptron (MLP) neural network Super Tau Charm Facility (STCF)

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：