检索结果-内蒙古大学图书馆

15th International conference on image Analysis and Recognition (ICIAR)

作者： Leko, Gabor Balazs, Peter Varga, Laszlo G. Univ Szeged Dept Image Proc & Comp Graph Arpad Ter 2 H-6720 Szeged Hungary

ISBN: (纸本)9783319930008;9783319929996

Binary tomography focuses on the problem of reconstructing homogeneous objects from a small number of their projections. In many applications, incomplete projection data holds insufficient information for the correct reconstruction of the original object. In this paper, we provide an optimization based method to select the "most informative" projection set, using information of global uncertainty. Beside the projection data we assume no further knowledge of the image to be reconstructed. Still, we achieve approximately as accurate reconstruction results, as it is possible to gain with a former method that uses blueprint images to find the optimal set of projections. We give experimental results for validating our approach on artificial images of various structures.

关键词： Binary tomography reconstruction Uncertainty Projection selection Optimization

来源：评论

学校读者我要写书评

暂无评论

Radio Interferometric image reconstruction Algorithm Based on Primal Dual

Radio Interferometric Image Reconstruction Algorithm Based o...

引用

10th International conference on Communication Software and Networks (ICCSN)

作者： Lao, Bao-qiang An, Tao Chinese Acad Sci Shanghai Astron Observ Nandan Rd 80 Shanghai 200030 Peoples R China

ISBN: (纸本)9781538672242

The last-standing ill-posed inverse problem of radio interferometric imaging is analyzed. A new convex optimization algorithm, Primal Dual, is applied to radio interferometric imaging to recover the emission structure from the incomplete sampling. The convex optimization problem is defined as the primal problem and its dual problem is calculated. According to the characteristics of these two problems, the final solution of the primal problem is solved and the image of radio sources are reconstructed by iteratively alternating between solving the primal problem and the dual problem by using moreau decomposition, forward-backward method and the proximity operator. The algorithm parameters are analyzed from the simulations based on experimental data. The algorithm is validated and the parameters are optimized. The comparison between the images inferred from the compressed sensing and classical CLEAN algorithms shows that the signal to noise ratio and the dynamic range in the reconstructed images from compressed sensing are significantly higher than the CLEAN images, and the sidelobe levels are much lower in the former based on the real data. Besides the obvious efficacy of the Primal Dual algorithm in reconstructing extended source images, the major attraction is that it is simple to parallelize to support large data sets.

关键词： astronomy interferometric image reconstruction primal dual

来源：评论

学校读者我要写书评

暂无评论

Identify Hierarchical Structures from Task-Based fMRI data via Hybrid Spatiotemporal Neural Architecture Search Net 1

引用

10th International Workshop on Machine Learning in Medical Imaging (MLMI) / 22nd International conference on Medical image Computing and Computer-Assisted Intervention (MICCAI)

作者： Zhang, Wei Zhao, Lin Li, Qing Zhao, Shijie Dong, Qinglin Jiang, Xi Zhang, Tuo Liu, Tianming Univ Georgia Dept Comp Sci Athens GA 30605 USA Beijing Normal Univ Coll Informat Sci & Technol Beijing 100875 Peoples R China Northwestern Polytech Univ Dept Automat Xian 710072 Peoples R China Univ Elect Sci & Technol China Sch Life Sci & Technol MOE Key Lab Neuroinformat Chengdu Peoples R China

ISBN: (数字)9783030322489

ISBN: (纸本)9783030322489;9783030322472

The hierarchical organization of brain function has been an established concept in the neuroscience field. Recently, these hierarchical organizations have been extensively investigated in terms of how such hierarchical functional networks are constructed in the human brain via a variety of deep learning models. However, a key problem of how to determine the optimal neural architecture (NA), e.g., hyper parameters, of deep model has not been solved yet. To address this question, in this work, a novel Hybrid Spatiotemporal Neural Architecture Search Net (HS-NASNet) is proposed by jointly using Evolutionary Optimizer, Deep Belief Networks (DBN) and Deep LASSO to reasonably determine the NA, thus revealing the latent hierarchical spatiotemporal features based on the Human Connectome Project (HCP) 900 fMRI datasets. Briefly, this HS-NASNet can automatically search the global optimal NA of DBN given the search space, and then the optimized DBN can extract the weights between two adjacent layers of the optimal NA, which are then treated as the hierarchical temporal dictionaries for Deep LASSO to identify the corresponding hierarchical spatial maps. Our results demonstrate that the optimized deep model can achieve accurate fMRI signal reconstruction and identify spatiotemporal functional networks exhibiting multiscale properties that can be well characterized and interpreted based on current neuroscience knowledge.

关键词： Hierarchical organization Neural architecture search Evolutionary optimization Deep Belief Network Task-based fMRI LASSO

来源：评论

学校读者我要写书评

暂无评论

The LOOT model for primary vertex finding in the BES-iii inner tracking detector

引用

AIP conference Proceedings 2021年第1期2377卷

作者： Ekaterina Rezvaya Pavel Goncharov Egor Schavelev Igor Denisenko Gennady Ososkov Aleksey Zhemchugov 1Dubna State University 19 Universitetskaya 141980 Dubna Moscow region Russia 2Saint Petersburg State University 7/9 Universitetskaya Emb. 199034 Saint Petersburg Russia 3Joint Institute for Nuclear Research 6 Joliot-Curie 141980 Dubna Moscow region Russia

The track recognition process (tracking) plays a key role in the event reconstruction in high energy physics. Our study is devoted to tracking for the proposed inner detector of the BES-iii experiment, which has only three cylindrical GEM stations. This means, if a particle is registered only at two out of three stations, then its track in the magnetic field cannot be restored without additional information. Such information can be the coordinates of the primary event vertex, from which all tracks exit. Knowing the location of the primary vertex would also help to improve the precision in determining the particle momentum. Besides, it leads to the significant reduction of the algorithmic complexity during the track-candidate search – from O(n2) to O(n), and can improve the overall track reconstruction efficiency. It should also be noted that tracking is especially complicated for strip GEM detectors due to their design specifics, which leads to the appearance of two orders of magnitude more fake hits in addition to useful ones. To solve the problem of vertex finding for the inner detector of the BES-iii experiment, we chose a deep convolutional neural network model Look Once On Tracks (LOOT), which processes the whole event at once, as an image, and after proper training can predict the coordinates of the primary vertex location. In this work, the preliminary results of primary vertex prediction on the BES-iii simulated data using the LOOT model are presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint reconstruction and material classification in spectral CT 3

Joint reconstruction and material classification in spectral...

引用

conference on Anomaly Detection and Imaging with X-Rays (ADIX) iii

作者： Babaheidarian, Parisa Castanon, David A. Boston Univ Elect & Comp Engn Boston MA 02215 USA

ISBN: (数字)9781510617766

ISBN: (纸本)9781510617766

Detecting the presence of hazardous materials in luggage is an important problem in aviation security. The current generation of inspection systems is based on X-ray computed tomography, followed by recognition systems to identify potential prohibited materials. As such, the image formation algorithms are designed independently of the recognition algorithms. In this paper, we present a new class of algorithms for processing the X-ray data by simultaneously forming images from the collected X-ray observations and identifying the underlying materials in the images. These algorithms exploit information about the possible materials in the image to modify the image reconstruction techniques, as well as material identification. We evaluate our joint algorithm on simulated phantoms using multi-spectral computed tomography, and compare our reconstruction and classification results with alternative state of the art approaches. Our experiments indicate that there are significant improvements in recognition performance possible through our joint approach.

关键词： computed tomography multi-spectral tomography inverse problems image formation luggage inspection threat detection

来源：评论

学校读者我要写书评

暂无评论

An Efficient Computer Aided Detection for 3D Neurostructural reconstruction of Magnetic Resonance images 9

An Efficient Computer Aided Detection for 3D Neurostructural...

引用

9th Cairo International Biomedical Engineering conference (CIBEC)

作者： Mabrouk, Mai S. Marzouk, Samir Y. Afify, Heba M. Misr Univ Sci & Technol MUST Univ Dept Biomed Engn Cairo Egypt Arab Acad Sci & Technol Basic & Appl Sci Dept Cairo Egypt Modern Univ Technol & Informat MTI Univ Bioelect Engn Dept Cairo Egypt

ISBN: (纸本)9781538681541

The comprehensive framework for analyzing brain images performs by the integration between three dimensional (3D) reconstruction and neuroimaging approach to realize brain diseases progressions. Computer Aided Detection (CAD) technology has numerous achievements in brain tumor processing for improving the quality of brain visualization to support neuroradiologists without the need for surgical biopsy or resection. Despite the advance in the radiological diagnosis of neuroimaging data, magnetic resonance imaging (MRI) has some restrictions that related to human errors and incomplete interpretation of brain tumor regions. Also, MRI scan produces 2D images of the brain that was very difficult to handle different types of tumor. Therefore, many algorithms are used computer-based classification to accurately distinguish between tumor regions from the brain MR images that provided an early diagnosis of brain diseases. This study investigated the CAD system using 3D image reconstruction of MR brain and tumor structures efficiently under MATLAB platform to recognize the location, volume, and type of brain tumors. In addition, the proposed system applied the Fuzzy C-Means (FCM) algorithm as image segmentation and support vector machine (SVM) as image classification for tumor detection of MR brain images. Results confirmed that this 3D model depicted an advanced view for estimating of human brain diseases.

关键词： Computer-Aided Detection (CAD) Magnetic resonance imaging (MRI) 3D image reconstruction support vector machine (SVM) Fuzzy C-Means (FCM) algorithm

来源：评论

学校读者我要写书评

暂无评论

Retinal image Understanding Emerges from Self-Supervised Multimodal reconstruction 21st

Retinal Image Understanding Emerges from Self-Supervised Mul...

引用

21st International conference on Medical image Computing and Computer-Assisted Intervention (MICCAI) / 8th Eurographics Workshop on Visual Computing for Biology and Medicine (VCBM) / International Workshop on Computational Diffusion MRI (CDMRI)

作者： Hervella, Alvaro S. Rouco, Jose Novo, Jorge Ortega, Marcos Univ A Coruna CITIC Res Ctr Informat & Commun Technol La Coruna Spain Univ A Coruna Dept Comp Sci La Coruna Spain

ISBN: (纸本)9783030009281;9783030009274

The successful application of deep learning-based methodologies is conditioned by the availability of sufficient annotated data, which is usually critical in medical applications. This has motivated the proposal of several approaches aiming to complement the training with reconstruction tasks over unlabeled input data, complementary broad labels, augmented datasets or data from other domains. In this work, we explore the use of reconstruction tasks over multiple medical imaging modalities as a more informative self-supervised approach. Experiments are conducted on multimodal reconstruction of retinal angiography from retinography. The results demonstrate that the detection of relevant domain-specific patterns emerges from this self-supervised setting.

关键词： Self-supervised Multimodal Retinography Angiography

来源：评论

学校读者我要写书评

暂无评论

Integrating data and image Domain Deep Learning for Limited Angle Tomography using Consensus Equilibrium

Integrating Data and Image Domain Deep Learning for Limited ...

引用

International conference on Computer Vision Workshops (ICCV Workshops)

作者： Muhammad Usman Ghani W. Clem Karl Boston University

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Computed Tomography (CT) is a non-invasive imaging modality with applications ranging from healthcare to security. It reconstructs cross-sectional images of an object using a collection of projection data collected at different angles. Conventional methods, such as FBP, require that the projection data be uniformly acquired over the complete angular range. In some applications, it is not possible to acquire such data. Security is one such domain where non-rotational scanning configurations are being developed which violate the complete data assumption. Conventional methods produce images from such data that are filled with artifacts. The recent success of deep learning (DL) methods has inspired researchers to post-process these artifact laden images using deep neural networks (DNNs). This approach has seen limited success on real CT problems. Another approach has been to pre-process the incomplete data using DNNs aiming to avoid the creation of artifacts altogether. Due to imperfections in the learning process, this approach can still leave perceptible residual artifacts. In this work, we aim to combine the power of deep learning in both the data and image domains through a two-step process based on the consensus equilibrium (CE) framework. Specifically, we use conditional generative adversarial networks (cGANs) in both the data and the image domain for enhanced performance and efficient computation and combine them through a consensus process. We demonstrate the effectiveness of our approach on a real security CT dataset for a challenging 90 degree limited-angle problem. The same framework can be applied to other limited data problems arising in applications such as electron microscopy, non-destructive evaluation, and medical imaging.

关键词： Computed tomography image reconstruction Generators Machine learning data models

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks Conditioned on Brain Activity Reconstruct Seen images

Generative Adversarial Networks Conditioned on Brain Activit...

引用

IEEE International conference on Systems, Man, and Cybernetics (SMC)

作者： St-Yves, Ghislain Naselaris, Thomas Med Univ South Carolina Dept Neurosci 96 Jonathan Lucas St CSB 325c Charleston SC 29425 USA Med Univ South Carolina Dept Neurosci 96 Jonathan Lucas St CSB 325h Charleston SC 29425 USA

ISBN: (纸本)9781538666500

We consider the inference problem of reconstructing a visual stimulus from brain activity measurements (e.g. fMRI) that encode this stimulus. Recovering a complete image is complicated by the fact that neural representations are noisy, high-dimensional, and contain incomplete information about image details. Thus, reconstructions of complex images from brain activity require a strong prior. Here we propose to train generative adversarial networks (GANs) to learn a generative model of images that is conditioned on measurements of brain activity. We consider two challenges of this approach: First, given that GANs require far more data to train than is typically collected in an fMRI experiment, how do we obtain enough samples to train a GAN that is conditioned on brain activity? Secondly, how do we ensure that our generated samples are robust against noise present in fMRI data? Our strategy to surmount both of these problems centers around the creation of surrogate brain activity samples that are generated by an encoding model. We find that the generative model thus trained generalizes to real fMRI data measured during perception of images and is able to reconstruct the basic outline of the stimuli.

关键词： Gallium nitride image reconstruction Brain modeling Generative adversarial networks Encoding Training

来源：评论

学校读者我要写书评

暂无评论

Comparison of 3D Surgical Tool Segmentation Procedures with Robot Kinematics Prior

Comparison of 3D Surgical Tool Segmentation Procedures with ...

引用

25th IEEE/RSJ International conference on Intelligent Robots and Systems (IROS)

作者： Su, Yun-Hsuan Huang, Issac Huang, Kevin Hannaford, Blake Univ Washington Dept Elect Engn Paul Allen Ctr 185 Stevens WayRoom AE100RCampus Box 352500 Seattle WA 98195 USA Trinity Coll Dept Engn 300 Summit St Hartford CT 06106 USA

ISBN: (纸本)9781538680940

3D reconstruction and surgical tool segmentation are necessary for several advanced tasks in robot-assisted laparoscopic surgery. These tasks include vision-based force estimation, surgical guidance, and medical image registration where pre-operative data (CT or MRI scan image slices) are overlaid on patient anatomy in real-time during surgery [1] to name a few. In this work, two main strategies were considered: (1) initialize with surgical tool segmentation from 2D images, then proceed to local 3D reconstruction near the tool-tissue interaction region by projecting the segmented result into 3D space, and (2) initialize with 3D reconstruction of the entire surgical task space, followed by surgical tool segmentation from within the 3D reconstructed model. Both methods were implemented on the Raven II surgical robot system, and accuracy and time complexity for both methods were comparatively analyzed while considering various task parameters. Finally, based on the results of this work, guidelines for selecting reconstruction and segmentation strategies and procedure for particular situations are outlined in Section V.

关键词： Tools Three-dimensional displays Cameras image segmentation Robot vision systems Force image reconstruction

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：