检索结果-内蒙古大学图书馆

Fetal MRI by Robust Deep Generative Prior reconstruction and Diffeomorphic Registration

IEEE TRANSACTIONS ON MEDICAL IMAGING 2023年第3期42卷 810-822页

作者： Cordero-Grande, Lucilio Enrique Ortuno-Fisac, Juan Aguado del Hoyo, Alejandra Uus, Alena Deprez, Maria Santos, Andres Hajnal, Joseph V. Ledesma-Carbayo, Maria J. Univ Politecn Madrid ETSI Telecomunicac Biomed Image Technol Madrid 28040 Spain ISCIII CIBER BBN Madrid 28029 Spain Kings Coll London Ctr Dev Brain Sch Biomed Engn & Imaging Sci Kings Hlth PartnersSt Thomas Hosp London SE1 7EH England Kings Coll London Sch Biomed Engn & Imaging Sci Biomed Engn Dept Kings Hlth PartnersSt Thomas Hosp London SE1 7EH England Mother & Child Hosp Gregorio Maranon Dept Pediat Radiol Madrid 28009 Spain

Magnetic resonance imaging of whole fetal body and placenta is limited by different sources of motion affecting the womb. Usual scanning techniques employ single-shot multi-slice sequences where anatomical information in different slices may be subject to different deformations, contrast variations or artifacts. Volumetric reconstruction formulations have been proposed to correct for these factors, but they must accommodate a non homogeneous and non-isotropic sampling, so regularization becomes necessary. Thus, in this paper we propose a deep generative prior for robust volumetric reconstructions integrated with a diffeomorphic volume to slice registration method. Experiments are performed to validate our contributions and compare with methods in the literature in a cohort of 72 fetal datasets in the range of 20-36 weeks gestational age. Quantitative as well as radiological assessment suggest improved image quality and more accurate prediction of gestational age at scan is obtained when comparing to state of the art reconstruction methods. In addition, gestational age prediction results from our volumetric reconstructions are competitive with existing brain-based approaches, with boosted accuracy when integrating information of organs other than the brain. Namely, a mean absolute error of 0.618 weeks (R-2 = 0.958) is achieved when combining fetal brain and trunk information.

关键词： Image reconstruction Strain Magnetic resonance imaging Estimation Brain modeling reconstruction algorithms Extraterrestrial measurements Fetal magnetic resonance imaging slice to volume reconstruction generative image priors diffeomorphic image registration gestational age prediction

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Light Field reconstruction Method Using View-Selective Angular Feature Extraction

引用

IEEE ACCESS 2023年 11卷 31157-31166页

作者： Zhou, Shubo Jiang, Xue-Qin Ding, Xiaoming Huang, Rong Donghua Univ Inst Informat Sci & Technol Shanghai 201620 Peoples R China Tianjin Normal Univ Coll Elect & Commun Engn Tianjin 300387 Peoples R China

Deep learning (DL) provides an effective approach for light field (LF) reconstruction that aims to synthesize novel views from sparsely-sampled views. However, it is challenging to address domain asymmetry when adopting spatial-angular interaction LF reconstruction methods. To overcome this problem, a view-selective angular feature extraction block (VS-LFAFE) is proposed to obtain full-resolution angular features that enumerate whole viewpoints in a macropixel. By applying the VS-LFAFE, a novel LF reconstruction method is proposed, consisting of two subblocks: a spatial-angular feature extraction and fusion block, and an angular upsampling block. Experimental results demonstrate the effectiveness of the VS-LFAFE, and validate that the proposed method can achieve superior performance compared with the state-of-the-art methods.

关键词： Feature extraction Image reconstruction Convolutional neural networks reconstruction algorithms Estimation Spatial resolution Interpolation Light field reconstruction light field imaging view-selective angular feature convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

A 3-D Chromosome Structure reconstruction Method With High Resolution Hi-C Data Using Nonlinear Dimensionality Reduction and Divide-and-Conquer Strategy

IEEE TRANSACTIONS ON NANOBIOSCIENCE

引用

IEEE TRANSACTIONS ON NANOBIOSCIENCE 2023年第4期22卷 716-727页

作者： Gong, Haiyan Ma, Fuqiang Zhang, Xiaotong Yang, Yi Li, Minghong Chen, Zhengyuan Zhang, Sichen Chen, Yang Beijing Adv Innovat Ctr Mat Genome Engn Natl Mat Corros & Protect Data Ctr Beijing 100083 Peoples R China Univ Sci & Technol Beijing Inst Adv Mat & Technol Beijing 100083 Peoples R China Inspur Grp Co Ltd Jinan 250101 Shandong Peoples R China Univ Sci & Technol Beijing Sch Comp & Commun Engn Beijing Key Lab Knowledge Engn Mat Sci Beijing 100083 Peoples R China Univ Sci & Technol Beijing Shunde Innovat Sch Foshan 528399 Peoples R China Chinese Acad Med Sci Inst Basic Med Sci Dept Biochem & Mol Biol Sch Basic MedState Key Lab Med Mol BiolPeking U Beijing 100005 Peoples R China

Chromosomes are fundamental components of genetic material, and their structural characteristics play an essential role in the regulation of gene expression. The advent of high-resolution Hi-C data has enabled scientists to explore the three-dimensional structure of chromosomes. However, most of the currently available methods for reconstructing chromosome structures are unable to achieve high resolutions, such as 5 Kilobase (KB). In this study, we present NeRV-3D, an innovative method that utilizes a nonlinear dimensionality reduction visualization algorithm to reconstruct 3D chromosome structures at low resolutions. Additionally, we introduce NeRV-3D-DC, which employs a divide-and-conquer technique to reconstruct and visualize 3D chromosome structures at high resolutions. Our results demonstrate that both NeRV-3D and NeRV-3D-DC outperform existing methods in terms of 3D visualization effects and evaluation metrics on simulated and actual Hi-C datasets. The implementation of NeRV-3D-DC can be found at https://***/ghaiyan/NeRV-3D-DC.

关键词： Biological cells Three-dimensional displays Genomics Bioinformatics Nanobioscience Fish reconstruction algorithms Hi-C high-resolution 3D chromosome structure nonlinear dimensionality reduction visualization divide-and-conquer

来源：评论

学校读者我要写书评

暂无评论

SSRNet: Scalable 3D Surface reconstruction Network

引用

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 2023年第12期29卷 4906-4919页

作者： Yuan, Ganzhangqin Fu, Qiancheng Mi, Zhenxing Luo, Yiming Tao, Wenbing Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Natl Key Lab Sci & Technol Multispectral Informat Wuhan 430074 Hubei Peoples R China Hong Kong Univ Sci & Technol Kowloon Tong Hong Kong Peoples R China Imperial Coll London London SW7 2AZ England

Learning-based surface reconstruction methods have received considerable attention in recent years due to their excellent expressiveness. However, existing learning-based methods lack scalability in processing large-scale point clouds. This paper proposes a novel scalable learning-based 3D surface reconstruction method based on octree, called SSRNet. SSRNet works in a scalable reconstruction pipeline, which divides oriented point clouds into different local parts and then processes them in parallel. Accommodating this scalable design pattern, SSRNet constructs local geometric features for octree vertices. Such features comprise the relation between the vertices and the implicit surface, ensuring geometric perception. Focusing on local geometric information also enables the network to avoid the overfitting problem and generalize well on different datasets. Finally, as a learning-based method, SSRNet can process large-scale point clouds in a short time. And to further solve the efficiency problem, we provide a lightweight and efficient version that is about five times faster while maintaining reconstruction performance. Experiments show that our methods achieve state-of-the-art performance with outstanding efficiency.

关键词： Surface reconstruction Point cloud compression Octrees Surface treatment Learning systems Three-dimensional displays reconstruction algorithms implicit function oriented point clouds large-scale point clouds

来源：评论

学校读者我要写书评

暂无评论

Dual-step reconstruction algorithm to improve microscopy resolution by deep learning

引用

APPLIED OPTICS 2023年第13期62卷 3439-3444页

作者： Deng, Qisheng Zhu, Zece Shu, Xuewen Huazhong Univ Sci & Technol Wuhan Natl Lab Optoelect Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Opt & Elect Informat Wuhan 430074 Peoples R China Wuhan Text Univ Dept Chem & Chem Engn Wuhan 430200 Peoples R China

Deep learning plays an important role in the field of machine learning, which has been developed and used in a wide range of areas. Many deep-learning-based methods have been proposed to improve image resolution, most of which are based on image-to-image translation algorithms. The performance of neural networks used to achieve image translation always depends on the feature difference between input and output images. Therefore, these deep-learning-based methods sometimes do not have good performance when the feature differences between low-resolution and high-resolution images are too large. In this paper, we introduce a dual-step neural network algorithm to improve image resolution step by step. Compared with conventional deep-learning methods that use input and output images with huge differences for training, this algorithm learning from input and output images with fewer differences can improve the performance of neural networks. This method was used to reconstruct high-resolution images of fluorescence nanoparticles in cells. (c) 2023 Optica Publishing Group

关键词： Image processing Image reconstruction Image resolution Neural networks reconstruction algorithms Stochastic gradient descent

来源：评论

学校读者我要写书评

暂无评论

Fast modal reconstruction of large plane wavefronts from sparse measurements using Shack-Hartmann sensors

引用

APPLIED OPTICS 2023年第26期62卷 6986-6992页

作者： Berlakovich, Nikolaus Csencsics, Ernst Senoner, Damian Schitter, Georg TU Wien Automat & Control Inst ACIN A-1040 Vienna Austria

A concept for the fast measurement and reconstruction of optical wavefronts using Shack-Hartmann sensors (SHSs) is presented. For wavefronts with a diameter at the scale of several tens of millimeters, hundreds of measurements with an SHS may be necessary to cover the wavefront. In the proposed concept, a few SHSs are used to measure about 2% of the entire wavefront, providing sufficient measurement data for its successful reconstruction. The small number of SHSs mounted in parallel makes the concept suitable for time-critical applications. A simulation analysis is performed, and an experimental validation of the concept is presented, demonstrating that the wavefront can be reconstructed with an RMS error of about 100 nm.(c) 2023 Optica Publishing Group

关键词： Optical measurement Optical systems Position sensing equipment reconstruction algorithms Sensor performance Wavefronts

来源：评论

学校读者我要写书评

暂无评论

Single-slice rebinning reconstruction method for segmented helical computed tomography

引用

OPTICS EXPRESS 2023年第19期31卷 30514-30528页

作者： Wang, Zhisheng Cui, Junning Bian, Xingyuan Tang, Ran Li, Zongfeng Li, Sangyu Lin, Legeng Wang, Shunli Harbin Inst Technol Ctr Ultraprecis Optoelect Instrument Engn Harbin 150080 Peoples R China Harbin Inst Technol Minist Ind & Informat Technol Key Lab Ultraprecis Intelligent Instrumentat Harbin 150080 Peoples R China

Recently, to easily extend the helical field-of-view (FOV), the segmented helical computed tomography (SHCT) method was proposed, as well as the corresponding generalized backprojection filtration (G-BPF) type algorithm. Similar to the geometric relationship between helical and circular CT, SHCT just becomes full-scan multiple source-translation CT (F-mSTCT) when the pitch is zero and the number of scan cycles is one. The strategy of G-BPF follows the idea of the generalized Feldkamp approximate cone-beam algorithm for helical CT, i.e., using the F-mSTCT cone-beam BPF algorithm to approximately perform reconstruction for SHCT. The image quality is limited by the pitch size, which implies that satisfactory quality could only be obtained under the conditions of small pitches. To extend the analytical reconstruction for SHCT, an effective single-slice rebinning (SSRB) method for SHCT is investigated here. Transforming the SHCT cone-beam reconstruction into the virtual F-mSTCT fan-beam stack reconstruction task with low computational complexity, and then some techniques are developed to address the challenges involved. By using the basic BPF reconstruction with derivating along the detector (D-BPF), our experiments demonstrate that SSRB has fewer interlayer artifacts, higher z-resolution, more uniform in-plane resolution, and higher reconstruction efficiency compared to G-BPF. SSRB could promote the effective application of deep learning in SHCT reconstruction.

关键词： Computed tomography Image processing Image quality Medical image processing Positron emission tomography reconstruction algorithms

来源：评论

学校读者我要写书评

暂无评论

A Task-based comparison of two reconstruction algorithms for digital breast tomosynthesis

A Task-based comparison of two reconstruction algorithms for...

引用

Medical Imaging - Physics of Medical Imaging

作者： Mahadevan, Ravi Ikejimba, Lynda C. Lin, Yuan Samei, Ehsan Lo, Joseph Y. Duke Univ Med Ctr Dept Radiol Carl E Ravin Adv Imaging Labs Durham NC 27710 USA

ISBN: (纸本)9780819498267

Digital breast tomosynthesis (DBT) generates 3-D reconstructions of the breast by taking X-Ray projections at various angles around the breast. DBT improves cancer detection as it minimizes tissue overlap that is present in traditional 2-D mammography. In this work, two methods of reconstruction, filtered backprojection (FBP) and the Newton-Raphson iterative reconstruction were used to create 3-D reconstructions from phantom images acquired on a breast tomosynthesis system. The task based image analysis method was used to compare the performance of each reconstruction technique. The task simulated a 10mm lesion within the breast containing iodine concentrations between 0.0mg/ml and 8.6mg/ml. The TTF was calculated using the reconstruction of an edge phantom, and the NPS was measured with a structured breast phantom (CIRS 020) over different exposure levels. The detectability index d' was calculated to assess image quality of the reconstructed phantom images. Image quality was assessed for both conventional, single energy and dual energy subtracted reconstructions. Dose allocation between the high and low energy scans was also examined. Over the full range of dose allocations, the iterative reconstruction yielded a higher detectability index than the FBP for single energy reconstructions. For dual energy subtraction, detectability index was maximized when most of the dose was allocated to the high energy image. With that dose allocation, the performance trend for reconstruction algorithms reversed;FBP performed better than the corresponding iterative reconstruction. However, FBP performance varied very erratically with changing dose allocation. Therefore, iterative reconstruction is preferred for both imaging modalities despite underperforming dual energy FBP, as it provides stable results.

关键词： Dual energy imaging Iodine reconstruction algorithms Breast Digital breast tomosynthesis Image quality 3D image reconstruction Tissues Image filtering Physics

来源：评论

学校读者我要写书评

暂无评论

Learned reconstruction Methods With Convergence Guarantees: A survey of concepts and applications

引用

IEEE SIGNAL PROCESSING MAGAZINE 2023年第1期40卷 164-182页

作者： Mukherjee, Subhadip Hauptmann, Andreas Oktem, Ozan Pereyra, Marcelo Schonlieb, Carola-Bibiane Univ Bath Dept Comp Sci Machine Learning & Artificial Intelligence Bath BA2 7PB England Univ Oulu Computat Math Res Unit Math Sci Oulu 90014 Finland UCL Dept Comp Sci London WC1E 6BT England Uppsala Univ Dept Informat Technol Computat Sci S-75237 Uppsala Sweden KTH Royal Inst Technol Dept Math Numer Anal S-11428 Stockholm Sweden Heriot Watt Univ Maxwell Inst Math Sci Edinburgh EH14 4AS Scotland Heriot Watt Univ Sch Math & Comp Sci Edinburgh EH14 4AS Scotland Univ Cambridge Appl Math Cambridge CB3 0WA England Cambridge Image Anal Grp Cambridge England EPSRC Cambridge Math Informat Healthcare Hub Cambridge England

In recent years, deep learning has achieved remarkable empirical success for image reconstruction. This has catalyzed an ongoing quest for the precise characterization of the correctness and reliability of data-driven methods in critical use cases, for instance, in medical imaging. Notwithstanding the excellent performance and efficacy of deep learning-based methods, concerns have been raised regarding the approaches' stability, or lack thereof, with serious practical implications. Significant advances have been made in recent years to unravel the inner workings of data-driven image recovery methods, challenging their widely perceived black-box nature. In this article, we specify relevant notions of convergence for data-driven image reconstruction, which forms the basis of a survey of learned methods with mathematically rigorous reconstruction guarantees. An example that is highlighted is the role of input-convex neural networks (ICNNs), offering the possibility to combine the power of deep learning with classical convex regularization theory for devising methods that are provably convergent. This survey article is aimed at both methodological researchers seeking to advance the frontiers of our understanding of data-driven image reconstruction methods as well as practitioners by providing an accessible description of useful convergence concepts and by placing some of the existing empirical practices on a solid mathematical foundation.

关键词： Deep learning Learning systems Neural networks Closed box reconstruction algorithms Image reconstruction Reliability

来源：评论

学校读者我要写书评

暂无评论

Laser diode photoacoustic point source detection: machine learning-based denoising and reconstruction

引用

OPTICS EXPRESS 2023年第9期31卷 13895-13910页

作者： Vousten, Vincent Moradi, Hamid Wu, Zijiang Boctor, Emad M. Salcudean, Septimiu E. Univ British Columbia Dept Elect & Comp Engn Vancouver BC Canada Eindhoven Univ Technol Dept Biomed Engn Eindhoven Netherlands Johns Hopkins Univ Whiting Sch Engn Baltimore MD USA

A new development in photoacoustic (PA) imaging has been the use of compact, portable and low-cost laser diodes (LDs), but LD-based PA imaging suffers from low signal intensity recorded by the conventional transducers. A common method to improve signal strength is temporal averaging, which reduces frame rate and increases laser exposure to patients. To tackle this problem, we propose a deep learning method that will denoise point source PA radio-frequency (RF) data before beamforming with a very few frames, even one. We also present a deep learning method to automatically reconstruct point sources from noisy pre-beamformed data. Finally, we employ a strategy of combined denoising and reconstruction, which can supplement the reconstruction algorithm for very low signal-to-noise ratio inputs.

关键词： Diode lasers High power lasers Image reconstruction Medical imaging reconstruction algorithms Tissue characterization

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：