检索结果-内蒙古大学图书馆

25th Biennial International conference on Information Processing in Medical Imaging (IPMI)

作者： Schlemper, Jo Caballero, Jose Hajnal, Joseph v. Price, Anthony Rueckert, Daniel Imperial Coll London London England Kings Coll London London England

ISBN: (纸本)9783319590509;9783319590493

The acquisition of Magnetic Resonance Imaging (MRI) is inherently slow. Inspired by recent advances in deep learning, we propose a framework for reconstructing MR images from undersampled data using a deep cascade of convolutional neural networks to accelerate the data acquisition process. We show that for Cartesian undersampling of 2D cardiac MR images, the proposed method outperforms the state-of-the-art compressed sensing approaches, such as dictionary learning-based MRI (DLMRI) reconstruction, in terms of reconstruction error, perceptual quality and reconstruction speed for both 3-fold and 6-fold undersampling. Compared to DLMRI, the error produced by the method proposed is approximately twice as small, allowing to preserve anatomical structures more faithfully. Using our method, each image can be reconstructed in 23 ms, which is fast enough to enable real-time applications.

关键词： Deep learning Convolutional neural network Magnetic Resonance Imaging image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Model-Based image Signal Processors via Learnable Dictionaries 36

Model-Based Image Signal Processors via Learnable Dictionari...

引用

36th AAAI conference on Artificial Intelligence / 34th conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence

作者： Conde, Marcos v. McDonagh, Steven Maggioni, Matteo Leonardis, Ales Perez-Pellitero, Eduardo Huawei Noahs Ark Lab Montreal PQ Canada Univ Wurzburg Inst Comp Sci Comp Vis Lab Wurzburg Germany

ISBN: (纸本)9781577358763

Digital cameras transform sensor RAW readings into RGB images by means of their image Signal Processor (ISP). Computational photography tasks such as image denoising and colour constancy are commonly performed in the RAW domain, in part due to the inherent hardware design, but also due to the appealing simplicity of noise statistics that result from the direct sensor readings. Despite this, the availability of RAW images is limited in comparison with the abundance and diversity of available RGB data. Recent approaches have attempted to bridge this gap by estimating the RGB to RAW mapping: handcrafted model-based methods that are interpretable and controllable usually require manual parameter fine-tuning, while end-to-end learnable neural networks require large amounts of training data, at times with complex training procedures, and generally lack interpretability and parametric control. Towards addressing these existing limitations, we present a novel hybrid model-based and data-driven ISP that builds on canonical ISP operations and is both learnable and interpretable. Our proposed invertible model, capable of bidirectional mapping between RAW and RGB domains, employs end-to-end learning of rich parameter representations, i.e. dictionaries, that are free from direct parametric supervision and additionally enable simple and plausible data augmentation. We evidence the value of our data generation process by extensive experiments under both RAW image reconstruction and RAW image denoising tasks, obtaining state-of-the-art performance in both. Additionally, we show that our ISP can learn meaningful mappings from few data samples, and that denoising models trained with our dictionary-based data augmentation are competitive despite having only few or zero ground-truth labels.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

A Model for Representing the Color and Depth Metric Characteristics of Objects in an image

A Model for Representing the Color and Depth Metric Characte...

引用

conference on Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO)

作者： Gadasin, D., v Shvedov, A., v Kuzin, I. A. Moscow Tech Univ Commun & Informat Moscow Russia

ISBN: (纸本)9781665415491

In general, a person receives information from the surrounding world with the help of the senses, processes it through the brain, using the knowledge gained earlier, and then transmits and accepts it, again using the senses. In other words, these information processes (receiving, processing, transmitting information), a person implements in a sign-signal form. The considered information processes are closely interrelated. For example, the processing and transmission of information is impossible without its storage, and to save the processed information, it must be transmitted. In this paper, the possibility of storing in the form of a single data structure not only information about the color of each pixel corresponding to the object of the scene fixed on it, but also the depth of its position is considered. A model is constructed for storing rangefinder information for each point of the three-dimensional scene in the image. An image generation algorithm is proposed for this model.

关键词： Three-dimensional reconstruction computer vision depth map data representation model scene reconstruction two-dimensional images three-dimensional images

来源：评论

学校读者我要写书评

暂无评论

Incorporation of Axial System Response in Iterative reconstruction from Axially Compressed data of a Cylindrical Scanner using On-the-Fly Computing

Incorporation of Axial System Response in Iterative Reconstr...

引用

15th International Workshop on Room-Temperature Semiconductor X- and Gamma-Ray Detectors/ 2006 IEEE Nuclear Science Symposium

作者： Panin, v. Y. Kehren, F. Casey, M. E. Siemens Med Solut Mol Imaging Knoxville TN 37932 USA

ISBN: (纸本)9781424405619

The quality of images reconstructed by statistical iterative methods depends on an accurate model of the relationship between image space and projection space. Fast reconstruction is also an important aspect in the clinical environment. In previous work, we incorporated measured and modeled system response into iterative reconstruction. Since axial compression (span) was used in projection data, axial blurring was depth-dependent. We use pre-computed and stored axial components for a scanner without translation axial symmetry. For a scanner with translation symmetry, a fast line-of-response (LOR) line integral projector is available. In this case, axial blurring due to both geometrical and physics effects is implemented differently. Forward projection of axially blurred images is performed on-the-fly into LOR space, followed by axial compression of LOR data into scanner projection data formats. Our LOR projector is based on Joseph's method. The translation symmetry of the scanner is essential for its efficient and fast computing performance. LOR projection and span assembling are performed independently for each azimuthal angle and result in small additional memory allocation. Results show that an acceleration of the computing of the axial blurring is achievable without any component storage but with similar image quality.

关键词： data compression

来源：评论

学校读者我要写书评

暂无评论

GPU BASED ACCELERATION OF 3D USCT image reconstruction WITH EFFICIENT INTEGRATION INTO MATLAB

GPU BASED ACCELERATION OF 3D USCT IMAGE RECONSTRUCTION WITH ...

引用

conference on Medical Imaging - Ultrasonic Imaging, Tomography, and Therapy

作者： Kretzek, Ernst Zapf, Michael Birk, Matthias Gemmeke, Hartmut Ruiter, Nicole v. Karlsruhe Inst Technol Inst Data Proc & Elect D-76344 Eggenstein Leopoldshafen Germany

ISBN: (纸本)9780819494498

3D ultrasound computer tomography (3D USCT) promises reproducible high-resolution images for early detection of breast tumors. The synthetic aperture focusing technique (SAFT) used for image reconstruction is highly compute-intensive but suitable for an accelerated execution on GPUs. In this paper we investigate how a previous implementation of the SAFT algorithm in CUDA C can be further accelerated and integrated into the existing MATLAB signal and image processing chain for 3D USCT. The focus is on an efficient preprocessing and preparation of data blocks in MATLAB as well as an improved utilisation of special hardware like the texture fetching units on GPUs. For 64 slices with 1024x1024 pixels each the overall runtime of the reconstruction including data loading and preprocessing could be decreased from 35 hours with CPU to 2.4 hours with eight GPUs.

关键词： GPU MATLAB MEX Acceleration Texture memory

来源：评论

学校读者我要写书评

暂无评论

reconstruction from SAMPLES ON LINEAR AND EXPANDING SPIRAL SCANS.

RECONSTRUCTION FROM SAMPLES ON LINEAR AND EXPANDING SPIRAL S...

引用

ICASSP '88: 1988 International conference on Acoustics, Speech, and Signal Processing. v 1, Speech Processing;v 2, Multidimensional Signal Processing;v 3, Digital Signal Processing;v 4, vLSI Spectral Estimation;v 5, Audio & Electroacoustics

作者： Yudilevich, Eitan Stark, Henry Rensselaer Polytechnic Inst Troy NY USA Rensselaer Polytechnic Inst Troy NY USA

The problem of reconstructing a two-dimensional function from a set of spiral samples is addressed. A theorem is presented that allows exact interpolation from linear spiral samples to a Cartesian lattice. Nonlinear, expanding spirals are then dealt with;these spirals have a potential advantage in a situation for which the data collection time is limited. In general, there is no exact reconstruction procedure from nonlinear spiral samples. Two practical methods are presented to reconstruct an image from a set of linear spiral samples of its Fourier transform, and examples of reconstructions obtained through both methods are given.

关键词： image PROCESSING

来源：评论

学校读者我要写书评

暂无评论

Iterative processing of the noise coherence matrix to determine the acoustic properties of the water area

Iterative processing of the noise coherence matrix to determ...

引用

2023 International Congress on Ultrasonics, ICU Beijing 2023

作者： Dmitriev, K.v. Acoustics Department Moscow State University Leninskie gory 1 Moscow119992 Russia

An expression is given for the coherence matrix of the acoustic field produced by random sources in an inhomogeneous medium in the Born *** iterative algorithm is proposed to determine the wave number inside the inhomogeneity based on this *** reconstruction results are analyzed for the cases of precise input data, data with interference, and incomplete data. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Acoustic fields

来源：评论

学校读者我要写书评

暂无评论

Dynamic Magnetic Resonance image reconstruction Based on Rosette Sampling and Tensor Singular value Decomposition 5

Dynamic Magnetic Resonance Image Reconstruction Based on Ros...

引用

5th International conference on Fuzzy Systems and data Mining (FSDM)

作者： Xu, Wen Yang, Xiaomei Deng, Jiaying Sichuan Univ Sch Elect & Elect Informat Engn Jinjiang Coll 1 Jinjiang Ave Pengshan Sichuan Peoples R China Sichuan Univ Sch Elect Engn & Informat 24 South Sect 1Yihuan Rd Chengdu Peoples R China

ISBN: (纸本)9781643680194;9781643680187

Rosette k-space trajectories are faster, more motion robust, for dynamic Magnetic Resonance Imaging data, in this work we have extended the concept of Rosette trajectories to time-dimensions, repeated sampling of k-space points leads to off-resonance behavior and cause destructive interference or loss of image intensity but with little blurring, off-resonance signal can be removed as background noise, to restore correlations between data, we regarded the sampling data as a tensor and introduced iterative reconstruction method derived from Total variation and tensor-Singular value Decomposition regularization terms for dynamic Magnetic Resonance Imaging reconstruction. The experimental results demonstrate that the proposed reconstruction model can effectively achieve better performance and satisfied quality for under sampled k-space data.

关键词： Rosette trajectory k-space Magnetic Resonance Imaging tensor Total variation tensor-Singular value Decomposition iterative reconstruction

来源：评论

学校读者我要写书评

暂无评论

Dual-modality endoscopic probe for tissue surface shape reconstruction and hyperspectral imaging enabled by deep neural networks

引用

MEDICAL image ANALYSIS 2018年 48卷 162-176页

作者： Lin, Jianyu Clancy, Neil T. Qi, Ji Hu, Yang Tatla, Taran Stoyanov, Danail Maier-Hein, Lena Elson, Daniel S. Imperial Coll London Hamlyn Ctr Robot Surg London England Imperial Coll London Dept Comp London England UCL Wellcome EPSRC Ctr Intervent & Surg Sci WEISS London England UCL Ctr Med Image Comp London England UCL Dept Comp Sci London England UCL Dept Surg & Canc London England Northwick Pk Hosp & Clin Res Ctr Dept Otolaryngol Harrow Middx England German Canc Res Ctr Div Med & Biol Informat Heidelberg Germany

Surgical guidance and decision making could be improved with accurate and real-time measurement of intra-operative data including shape and spectral information of the tissue surface. In this work, a dual modality endoscopic system has been proposed to enable tissue surface shape reconstruction and hyperspectral imaging (HSI). This system centers around a probe comprised of an incoherent fiber bundle, whose fiber arrangement is different at the two ends, and miniature imaging optics. For 3D reconstruction with structured light (SL), a light pattern formed of randomly distributed spots with different colors is projected onto the tissue surface, creating artificial texture. Pattern decoding with a Convolutional Neural Network (CNN) model and a customized feature descriptor enables real-time 3D surface reconstruction at approximately 12 frames per second (FPS). In HSI mode, spatially sparse hyperspectral signals from the tissue surface can be captured with a slit hyperspectral imager in a single snapshot. A CNN based super-resolution model, namely "super-spectral-resolution" network (SSRNet), has also been developed to estimate pixel-level dense hypercubes from the endoscope cameras standard RGB images and the sparse hyperspectral signals, at approximately 2 FPS. The probe, with a 2.1 mm diameter, enables the system to be used with endoscope working channels. Furthermore, since data acquisition in both modes can be accomplished in one snapshot, operation of this system in clinical applications is minimally affected by tissue surface movement and deformation. The whole apparatus has been validated on phantoms and tissue (ex vivo and in vivo), while initial measurements on patients during laryngeal surgery show its potential in real-world clinical applications. (C) 2018 Elsevier B.v. All rights reserved.

关键词： Intra-operative imaging 3D reconstruction Structured light Hyperspectral imaging Deep learning Super-spectral-resolution

来源：评论

学校读者我要写书评

暂无评论

3D Rheims reconstruction through ages: Robust and invariant postcard matching 12

3D Rheims reconstruction through ages: Robust and invariant ...

引用

27th image and vision Computing New Zealand conference, IvCNZ 2012

作者： Romaniuk, Barbara Younes, Lara Bittar, Éric Reims University CReSTIC-SIC Lab. Rue des Crayères 51687 Reims Cedex 2 France

ISBN: (纸本)9781450314732

We present the first step of the Rheims city (France) 3D reconstruction based on old postcards. Rheims endured drastic destruction during the First and then the Second World Wars. Old postcards, embodying the period from the beginning to the end of the 20th century, establish a testimony of the evolution in time and space of the most important places and monuments in the city. We aim to localize, render and visualize in 3D the buildings of this city, by using this sparse dataset and incomplete cadastral surveys. image matching is initially required for locating a building in the city space. In this paper we propose a performance comparison of state-of-the-art detector-descriptor couples. We focus on their robustness and their transformations invariance when low resolution data is subject to temporal and space modifications. © 2012 ACM.

关键词： image matching

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：