检索结果-内蒙古大学图书馆

Convolutional neural networks for reconstruction of neutron tomography from incomplete data

NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION B-BEAM INTERACTIONS WITH MATERIALS AND ATOMS 2025年 563卷

作者： Bakirov, Bulat Kichanov, Sergey E. Kozlenko, Denis P. Joint Inst Nucl Res Frank Lab Neutron Phys Dubna 141980 Russia Russian Acad Sci Inst Archaeol Moscow 117292 Russia

To reduce the number of image projections in neutron tomography experiments, tomography reconstruction algorithms are used from an incomplete and limited number of neutron projections. The possibilities of a reconstruction algorithm based on convolutional neural networks are presented. It was found that only 72 projections are required for trained convolutional neural network for a qualitative reconstruction comparable to that from a complete dataset. Variations in the quality of the tomography reconstruction due to changes in training data and the number of input projections are considered. Examples of using convolutional neural networks for neutron tomography reconstructions of real experimental data includes the results of studies on archaeological metal materials from the "Volna-1 '' archaeological site.

关键词： CNNs Neutron imaging Neutron tomography reconstruction incomplete data Non-destructive analysis Archaeology

来源：评论

学校读者我要写书评

暂无评论

Overcomplete pre-learned dictionary for incomplete data SAR imaging towards pervasive aerial and satellite vision

引用

WIRELESS NETWORKS 2024年第5期30卷 3989-4001页

作者： Farhangkhah, Naghmeh Samadi, Sadegh Khosravi, Mohammad R. Mohseni, Reza Shiraz Univ Technol Dept Elect & Elect Engn Shiraz Iran

Nowadays, pervasive vision through synthetic aperture radar (SAR) imaging sensors is a crucial part of air-borne and space-borne platforms to reach the concept of internet of multimedia things over satellites and visual flying ad-hoc networks. SAR sensors always need high-performance data reconstruction techniques to provide quality of experience for end-users of the distributed surveillance nodes and ensuring reliable decision-making in the autonomous vehicles. Using prior information in SAR image reconstruction, improves the quality of reconstructed image. Many sparse regularization methods use pre information terms in which the image is sparsely presented based on a predefined dictionary. However, if the desired features of the real image have not a sparse representation based on the predefined dictionary, image reconstruction with enhanced interested features will be failed. Dictionary learning to better adapt with the underlying scene can lead to better image reconstruction. On the other hand, using the idea of dictionary learning in the image reconstruction problem, and considering that the data used to train the dictionary may be incomplete and noisy, will create limitations for this method. In this paper, a new idea based on the use of an overcomplete dictionary consisting of a learned dictionary and a predefined dictionary (pre-learned dictionary) for SAR image reconstruction problem is presented. Developing the necessary mathematical relations and providing the framework for SAR image reconstruction based on the use of the overcomplete pre-learned dictionary, to simultaneously enhance the features considered in advance and the features associated with the image, from incomplete and noisy SAR raw data is presented in this article. We also present an iterative algorithm for solving the corresponding optimization problem. Simulation results based on the real data of TerraSAR-X and the Lynx airborne system show the effectiveness of the proposed method.

关键词： Synthetic aperture radar (SAR) image reconstruction Distributed surveillance Dictionary learning

来源：评论

学校读者我要写书评

暂无评论

Siamese Cooperative Learning for Unsupervised image reconstruction from incomplete Measurements

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第7期46卷 4866-4879页

作者： Quan, Yuhui Qin, Xinran Pang, Tongyao Ji, Hui South China Univ Technol Sch Comp Sci & Engn Guangzhou 510000 Peoples R China Natl Univ Singapore Dept Math Singapore 119076 Singapore

image reconstruction from incomplete measurements is one basic task in imaging. While supervised deep learning has emerged as a powerful tool for image reconstruction in recent years, its applicability is limited by its prerequisite on a large number of latent images for model training. To extend the application of deep learning to the imaging tasks where acquisition of latent images is challenging, this article proposes an unsupervised deep learning method that trains a deep model for image reconstruction with the access limited to measurement data. We develop a Siamese network whose twin sub-networks perform reconstruction cooperatively on a pair of complementary spaces: the null space of the measurement matrix and the range space of its pseudo inverse. The Siamese network is trained by a self-supervised loss with three terms: a data consistency loss over available measurements in the range space, a data consistency loss between intermediate results in the null space, and a mutual consistency loss on the predictions of the twin sub-networks in the full space. The proposed method is applied to four imaging tasks from different applications, and extensive experiments have shown its advantages over existing unsupervised solutions.

关键词： image reconstruction Training Noise measurement Loss measurement Deep learning Imaging Task analysis image reconstruction siamese neural networks unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Deep image Prior-Based PET reconstruction from Partial data

引用

IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2024年第4期8卷 416-425页

作者： Shan, Qianxue Wang, Junwu Liu, Dong Univ Sci & Technol China Sch Phys Sci Hefei 230026 Peoples R China Univ Sci & Technol China Sch Math Sci Hefei 230026 Peoples R China Univ Sci & Technol China Div Life Sci & Med CAS Key Lab Microscale Magnet Resonance Hefei 230026 Peoples R China Univ Sci & Technol China Synerget Innovat Ctr Quantum Informat & Quantum Ph Hefei 230026 Peoples R China Univ Sci & Technol China Sch Biomed Engn Suzhou 215123 Peoples R China Univ Sci & Technol China Suzhou Inst Adv Res Suzhou 215123 Peoples R China

In this article, we propose an unsupervised deep learning method for positron emission tomography (PET) reconstruction from incomplete data. This method utilizes the so-called deep image prior (DIP) as an untrained deep convolutional neural network (CNN) to generate object reconstructions. The main idea is to reparameterize the image reconstruction problem as a neural network optimization problem. We show that the proposed method effectively addresses the incomplete data reconstruction problem, which otherwise degrades the image resolution and quality of standard reconstruction algorithms. Meanwhile, the proposed method does not require any pretraining procedures, i.e., it is not biased toward any particular dataset. Hence, it has the potential to be used in clinical situations, where training data would be infeasible or prohibitively expensive. The performance of the proposed approach is evaluated with noisy synthetic data based on the Shepp-Logan and brainweb phantoms, and clinical naive rat data. In addition, robustness studies of the approach with respect to regularization parameters are also carried out. We showcase that the proposed method considerably outperforms the state-of-the-art methods, leading to flexible reconstruction from incomplete PET data.

关键词： Contourlet transform deep image prior (DIP) incomplete data positron emission tomography (PET) unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A Review of Deep Learning CT reconstruction from incomplete Projection data

引用

IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2024年第2期8卷 138-152页

作者： Wang, Tao Xia, Wenjun Lu, Jingfeng Zhang, Yi Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Sichuan Univ Key Lab Data Protect & Intelligent Management Minist Educ Chengdu 610207 Peoples R China Sichuan Univ Sch Cyber Sci & Engn Chengdu 610065 Peoples R China

Computed tomography (CT) is a widely used imaging technique in both medical and industrial applications. However, accurate CT reconstruction requires complete projection data, while incomplete data can result in significant artifacts in the reconstructed images, compromising their reliability for subsequent detection and diagnosis. As a result, accurate CT reconstruction from incomplete projection data remains a challenging research area in radiology. With the rapid development of deep learning (DL) techniques, many DL-based methods have been proposed for CT reconstruction from incomplete projection data. However, there are limited comprehensive surveys that summarize recent advances in this field. This article provides a comprehensive overview of the current state-of-the-art DL-based CT reconstruction from incomplete projection data, including acrlong SV reconstruction, acrlong LA reconstruction, acrlong MAR, acrlong IT, and ring artifact reduction. This survey covers various DL-based solutions to the five problems, potential limitations of existing methods, and future research directions.

关键词： image reconstruction Computed tomography Metals Plasmas Medical diagnostic imaging X-ray imaging Iterative methods Computed tomography (CT) deep learning (DL) interior tomography (IT) limited angle (LA) metal artifact reduction (MAR) ring artifact reduction sparse view (SV)

来源：评论

学校读者我要写书评

暂无评论

reconstruction of Missing GPR data Using Multiple-Point Statistical Simulation

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷 1页

作者： Zhang, Chongmin Gravey, Mathieu Mariethoz, Gregoire Irving, James Univ Lausanne Inst Earth Sci CH-1015 Lausanne Switzerland Austrian Acad Sci Inst Interdisciplinary Mt Res A-6020 Innsbruck Austria Univ Lausanne Inst Earth Surface Dynam CH-1015 Lausanne Switzerland

Ground-penetrating radar (GPR) is a powerful geophysical tool for efficient, high-resolution mapping of the shallow subsurface. Because of physical and economical limitations, a commonly encountered issue is that the corresponding profiles are incomplete in the sense that measurements are desired where they do not exist for data visualization, interpretation, and imaging. Such missing data may result, for example, from regions along the profile where surveying is not possible;from measurements being collected at a regular interval in time but not in space;or from the choice of a large measurement spacing to favor data coverage over quality. Although a number of methods have been proposed for the interpolation of GPR data to tackle this problem, they typically suffer from rather simplistic assumptions that are not satisfied for many GPR datasets. To address these shortcomings, we consider in this article a novel GPR data reconstruction strategy based on multiple-point geostatistics, where missing GPR data are stochastically simulated and conditioned on existing measurements and patterns observed in a representative training image. A key feature in our approach is the consideration of a multivariate image containing both continuous and categorical GPR reflection amplitude data, which helps to guide the simulations toward realistic structures. To demonstrate the power of this single strategy for multiple data reconstruction needs, we show its successful application to a variety of examples in the context of three problems: gap-filling, trace-spacing regularization, and trace densification.

关键词： image reconstruction Interpolation Geophysical measurements Training Three-dimensional displays Geologic measurements Uncertainty Ground-penetrating radar (GPR) interpolation multiple-point statistics (MPS) reconstruction simulation

来源：评论

学校读者我要写书评

暂无评论

Design of an Iterative Model for Incremental Enhancements in Quantum image Processing Using Reinforcement Learning-Based Optimizations

引用

IEEE ACCESS 2025年 13卷 20491-20511页

作者： Pappala, Lalitha Kumari Veesam, Sai Babu Chattu, Kannaiah Krishna, Janapati Venkata Bodapati, Jyostna Devi Rao, B. Tarakeswara VIT AP Univ Sch Comp Sci & Engn Amaravati 522237 Andhra Pradesh India Srinivas Univ IoT & Robot Inst Engn & Technol Mangaluru 574146 India Srinivas Univ AI Dept Inst Engn & Technol Mangaluru 574146 India Srinivas Univ AR&VR Dept Inst Engn & Technol Mangaluru 574146 India Vignans Fdn Sci Technol & Res Dept Adv Comp Sci & Engn Vadlamudi 522213 Andhra Pradesh India Kallam Haranadhareddy Inst Technol Dept CSE Guntur 522019 Andhra Pradesh India

In this text we propose a collection of enhanced quantum methods that would drastically enhance the efficiency and accuracy of biomedical image processing. There are four key methodologies that have been proposed in this work: Quantum Support Vector Machines with Enhanced Feature Extraction, Quantum Generative Adversarial Networks for data Augmentation, Quantum Entanglement and Correlation Analysis for Feature Detection, and Quantum-Enhanced image reconstruction for Noisy data Samples. Q-SVM-EFE is a Quantum Support Vector Machine-based framework that incorporates advanced feature extraction to map classical image data into high-dimensional quantum states, which should capture intricate patterns and therefore be more accurate for classification. This approach scored more than 95 percent in terms of classification accuracy and tenfold increased the speed of training compared to classical SVMs. QGAN-DA generates high-quality synthetic images to alleviate the scarcity of labeled medical data. It trains a generator network through quantum circuits for the generation of new samples and a discriminator network for real image and sample classification, thus ensuring high diversity and quality in synthetic data with SSIM values above 0.90. QECA-FD applies quantum entanglement in the analysis of biomedical image correlations and is therefore very effective in detecting subtle features and anomalies. This resulted in over 95% sensitivity in anomaly detection and increased the speed of the correlation analysis by five times. QIR-ND enables enhanced image reconstruction from sullied or incomplete data through quantum noise reduction and reconstruction techniques. This new approach gave a PSNR greater than 40 dB and an eightfold improvement in reconstruction delays.

关键词： Accuracy Biomedical imaging Quantum entanglement Quantum computing Feature extraction image reconstruction Biomedical image processing Correlation Training Noise measurement generative adversarial networks image reconstruction quantum computing support vector machines

来源：评论

学校读者我要写书评

暂无评论

Analysis of Deep image Prior and Exploiting Self-Guidance for image reconstruction

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING

引用

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2025年 11卷 435-451页

作者： Liang, Shijun Bell, Evan Qu, Qing Wang, Rongrong Ravishankar, Saiprasad Michigan State Univ Dept Biomed Engn E Lansing MI USA Michigan State Univ Dept Math E Lansing MI 48824 USA Univ Michigan Dept Elect Engn & Comp Sci Ann Arbor MI 48901 USA Michigan State Univ Dept Computat Math Sci & Engn E Lansing MI 48824 USA Michigan State Univ Dept Biomed Engn E Lansing MI 48824 USA

The ability of deep image prior (DIP) to recover high-quality images from incomplete or corrupted measurements has made it popular in inverse problems in image restoration and medical imaging, including magnetic resonance imaging (MRI). However, conventional DIP suffers from severe overfitting and spectral bias effects. In this work, we first provide an analysis of how DIP recovers information from undersampled imaging measurements by analyzing the training dynamics of the underlying networks in the kernel regime for different architectures. This study sheds light on important underlying properties for DIP-based recovery. Current research suggests that incorporating a reference image as network input can enhance DIP's performance in image reconstruction compared to using random inputs. However, obtaining suitable reference images requires supervision and raises practical difficulties. In an attempt to overcome this obstacle, we further introduce a self-driven reconstruction process that concurrently optimizes both the network weights and the input while eliminating the need for training data. Our method incorporates a novel denoiser regularization term which enables robust and stable joint estimation of both the network input and reconstructed image. We demonstrate that our self-guided method surpasses both the original DIP and modern supervised methods in terms of MR image reconstruction performance and outperforms previous DIP-based schemes for image inpainting.

关键词： image reconstruction Electronics packaging Training Magnetic resonance imaging Noise reduction Kernel Overfitting Convolutional neural networks Inverse problems Information filters Compressed sensing deep image prior deep learning machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing passive gamma emission tomography data with deep learning

引用

ANNALS OF NUCLEAR ENERGY 2024年 204卷

作者： Sanchez-Belenguer, Carlos Casado-Coscolla, Alvaro Wolfart, Erik Joint Res Ctr European Commiss Via Enrico Fermi 2749 I-21027 Ispra VA Italy Seidor Italy SRL Contract European Commiss Ispra Italy

In this paper, we address the problem of generating and enhancing Passive Gamma Emission Tomography (PGET) data from a deep learning perspective. The PGET instrument has been developed for the verification of spent nuclear fuel and relies on image reconstruction and analysis algorithms to detect missing or substituted fuel pins. Such techniques are sensitive to the quality of the input data: noisy or incomplete sinograms yield to poor reconstructions and, consequently, to low-confidence results. The development and validation of these algorithms is based on complex Monte Carlo simulations that are time-consuming and computationally-demanding. We propose the use of Convolutional Neural Networks (CNNs) for enhancing PGET data. Our technique learns the mapping between incomplete or noisy sinograms and their corresponding full representation. It effectively exploits the high degree of redundancy of the measurements, i.e . the contribution of a single pin can be observed from many different directions, to learn the underlying model of the data and to make informed predictions. The two main applications of our approach are: (1) accelerating Monte Carlo simulations and (2) pre-processing real measurements to enhance them before running the standard image reconstruction and analysis techniques. The experimental evaluation was performed with both, simulated and real measurements. Results show how effectively CNNs can learn and exploit the structure of the data. For the two use cases evaluated, denoising sinograms and inpainting incomplete ones, our technique achieved state-of-the-art performance with execution times in the order of milliseconds.

关键词： Passive gamma emission tomography Deep learning Monte Carlo simulations

来源：评论

学校读者我要写书评

暂无评论

Driving mutual advancement of 3D reconstruction and inpainting for masked faces

引用

PATTERN RECOGNITION 2025年 158卷

作者： Zhu, Guosong Qin, Zhen Zhou, Erqiang Ding, Yi Qin, Zhiguang Univ Elect Sci & Technol China Network & Data Secur Key Lab Sichuan Prov Chengdu 610054 Sichuan Peoples R China Southwestern Univ Finance & Econ Sch Comp & Artificial Intelligence Chengdu 611130 Sichuan Peoples R China

Target occlusion or pollution has always been a common and difficult problem in 3D reconstruction, seriously affecting the reconstruction effect, especially in single image scenario. To address the issues of incomplete reconstruction caused by pixel missing, a novel framework promoting mutual enhancement between 3D reconstruction and inpainting is proposed, which is capable of reconstructing a realistic 3D face with pixel completion from single image without prior assumptions. The framework is composed of an inpainting module for facial pixel completion and a reconstruction module for 3D face modeling. The inpainting module provides complete texture and accurate 3D geometry inferring premise for 3D reconstruction, and the reconstruction module is also involved in face inpainting, constraining the inpainting module to fill plausible pixels that are closer to the ground truth. Experiments show that the accurate 3D faces with complete and fine texture can be reconstructed by the proposed framework from largely masked images, with a competitive performance even surpassing most of state-of-the-art methods with unmasked images as input. Furthermore, this framework has achieved state-of-the-art performance in image inpainting on multiple face datasets.

关键词： 3D face reconstruction image inpainting

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：