330 Hits in 2.6 sec

Learning Splines for Sparse Tomographic Reconstruction [chapter]

Elham Sakhaee, Alireza Entezari
2014 Lecture Notes in Computer Science  
We present a spline-based sparse tomographic reconstruction algorithm where content-adaptive patch sparsity is integrated into the reconstruction process.  ...  The experiments show that enforcing patch-based sparsity, in terms of a learned dictionary, on higher order spline representations, outperforms existing methods that utilize pixelbasis for image representation  ...  Fig. 6 . 6 Enforcing adaptive sparsity with spline learning, (d), outperforms sparse wavelet tomographic reconstruction, (c), in a few-view setup.  ... 
doi:10.1007/978-3-319-14249-4_1 fatcat:mjvb3qodm5e3hbwgyplrek4a7i

Sparse image representation for jet neutron and gamma tomography

T. Craciunescu, V. Kiptily, A. Murari, I. Tiseanu, V. Zoita
2013 Fusion engineering and design  
The JET gamma/neutron profile monitor plasma coverage of the emissive region enables tomographic reconstruction.  ...  A new reconstruction method, based on the sparse representation of the reconstructed image in an over-complete dictionary, has been developed and applied to JET neutron/gamma tomography.  ...  Figure 2 : 2 The dictionary D learned from 50 tomographic reconstructions obtained using the ML method. This dictionary was used as an initial guess for solving Eq.4.  ... 
doi:10.1016/j.fusengdes.2013.03.024 fatcat:o5mnjtzmwvabhc7tdj3h54ne3y

CoronARe: A Coronary Artery Reconstruction Challenge [chapter]

Serkan Çimen, Mathias Unberath, Alejandro Frangi, Andreas Maier
2017 Lecture Notes in Computer Science  
CoronARe ranks state-of-the-art methods in symbolic and tomographic coronary artery reconstruction from interventional C-arm rotational angiography.  ...  Acknowledgement The authors would like to thank Zach Mullen, Kitware, for his support in hosting this challenge.  ...  Submission formats for tomographic and symbolic reconstructions are held as simple as possible. For tomographic data we rely on the previously established CAVAREV format.  ... 
doi:10.1007/978-3-319-67564-0_10 fatcat:nze5kbdasvc2xmucyft4apmski

An over-complete dictionary based regularized reconstruction of a field of ensemble average propagators

Wenxing Ye, Baba C. Vemuri, Alireza Entezari
2012 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI)  
We present a dictionary learning framework for achieving a smooth EAP reconstruction across the field wherein, the dictionary atoms are learned from the data via an initial regression using adaptive spline  ...  The formulation involves a two stage optimization where the first stage involves optimizing for a sparse dictionary using a K-SVD based updating and the second stage involves a quadratic cost function  ...  The problem of searching for the proper kernel function as well as the sparse weighting coefficients can be solved by a dictionary learning paradigm.  ... 
doi:10.1109/isbi.2012.6235711 pmid:23227275 pmcid:PMC3515658 dblp:conf/isbi/YeVE12 fatcat:jx2m3ulevvhsvc63z76f6ralbe

Evaluation of interpolation methods for surface-based motion compensated tomographic reconstruction for cardiac angiographic C-arm data

Kerstin Müller, Chris Schwemmer, Joachim Hornegger, Yefeng Zheng, Yang Wang, Günter Lauritsch, Christopher Rohkohl, Andreas K. Maier, Carl Schultz, Rebecca Fahrig
2013 Medical Physics (Lancaster)  
In general, the framework of motion estimation using a surface model and motion interpolation to a dense MVF provides the ability for tomographic reconstruction using a motion compensation technique.  ...  Conclusions: In this work, the influence of different motion interpolation methods on left ventricle motion compensated tomographic reconstructions was investigated.  ...  The interpolation is used to compute a dense motion vector field from a sparse one for the purpose of motion compensation in left ventricle tomographic reconstruction.  ... 
doi:10.1118/1.4789593 pmid:23464287 pmcid:PMC3598768 fatcat:iwydjw2ufnhlvfiifpgijwjb2y

Cubic-Spline Interpolation for Sparse-View CT Image Reconstruction With Filtered Backprojection in Dynamic Myocardial Perfusion Imaging

2019 Tomography  
We interpolated the sparse-view (quarter) projections to a full-view setting using a cubic-spline interpolation method before applying FBP to reconstruct the DCE heart images (synthesized full-view).  ...  This method may facilitate the application of sparse-view dynamic acquisition for ultralow-dose quantitative computed tomography (CT) myocardial perfusion (MP) imaging.  ...  The cubic-spline view interpolation method allows the standard FBP algorithm to be used for sparse-view image reconstruction without the need of implementing iterative reconstruction algorithms such as  ... 
doi:10.18383/j.tom.2019.00013 pmid:31572791 pmcid:PMC6752292 fatcat:3ijqaul2svbfbaagjbbclijbce

Limited Tomography Reconstruction via Tight Frame and Sinogram Extrapolation [article]

Jae Kyu Choi, Bin Dong, Xiaoqun Zhang
2016 arXiv   pre-print
X-ray computed tomography (CT) is one of widely used diagnostic tools for medical and dental tomographic imaging of the human body.  ...  In this paper, we consider two dimensional CT reconstruction using the horizontally truncated projections.  ...  R Λ P u = f 0 . (10) When W is a B-spline framelet, then by [5] , (10) can be viewed as a finite difference approximation of sparse model based approach (7) with HOT k (u) for some k ∈ N.  ... 
arXiv:1602.07049v1 fatcat:tzkmsb6chfdv3hlgvh2qhsx654

Framelet pooling aided deep learning network: the method to process high dimensional medical data

Chang Min Hyun, Kang Cheol Kim, Hyun Cheol Cho, Jae Kyu Choi, Jin Keun Seo
2020 Machine Learning: Science and Technology  
The purpose of this paper is to introduce a framelet-pooling aided deep learning method for mitigating computational bundles caused by large dimensionality.  ...  learning tasks.  ...  Figure 8 . 8 Qualitative comparison of the proposed method for sparse-view CT reconstruction problem.  ... 
doi:10.1088/2632-2153/ab592b fatcat:mep6loatdfbdxldpwaonjz2lhe

Deep Microlocal Reconstruction for Limited-Angle Tomography [article]

Héctor Andrade-Loarca, Gitta Kutyniok, Ozan Öktem, Philipp Petersen
2021 arXiv   pre-print
We present a deep learning-based algorithm to jointly solve a reconstruction problem and a wavefront set extraction problem in tomographic imaging.  ...  We find strong numerical evidence for the effectiveness of this approach.  ...  Learned Primal-Dual network in (2.5) for tomographic reconstruction that was first introduced in [2] .  ... 
arXiv:2108.05732v1 fatcat:273mpr5zpzhnnibqhkks4vylqe

Compressed sensing for STEM tomography

Laurène Donati, Masih Nilchian, Sylvain Trépout, Cédric Messaoudi, Sergio Marco, Michael Unser
2017 Ultramicroscopy  
We then propose a regularized tomographic reconstruction framework to recover volumes from RB-STEM measurements.  ...  This application of compressed sensing principles to STEM paves the way for a practical implementation of RB-STEM and opens new perspectives for high-quality reconstructions in STEM tomography. (L.  ...  Acknowledgments The authors acknowledge the PICT-IBiSA for providing access to their chemical imaging equipment. The work of L. Donati and M.  ... 
doi:10.1016/j.ultramic.2017.04.003 pmid:28411510 fatcat:3fsyvuecnnh27h32vlfjs3q63e

Front Matter: Volume 9413

2015 Medical Imaging 2015: Image Processing  
Base 36 numbering is employed for the last two digits and indicates the order of articles within the volume. Numbers start with 00,  ...  sparse tomographic reconstruction with Besov priors [9413-14] SESSION 4 COMPRESSED SENSING/SPARSE METHODS 9413 0G Rank-sparsity constrained atlas construction and phenotyping [9413-15] 9413 0H Compressed  ...  [9413-17] 9413 0J Alternating minimization algorithm with iteratively reweighted quadratic penalties for compressive transmission tomography [9413-18] SESSION 5 MACHINE LEARNING 9413 0K Revealing [9413  ... 
doi:10.1117/12.2194368 fatcat:lbd4hy3s2rbodfhutf34bmarhu

Studies on the sparsifying operator in compressive digital holography

Stijn Bettens, Hao Yan, David Blinder, Heidi Ottevaere, Colas Schretter, Peter Schelkens
2017 Optics Express  
sparse wavefields perfectly, and the robustness of the reconstructions to additive noise and sparsity defects.  ...  In particular, we recommend the CDF 9/7 and 17/11 wavelet transformations, as well as their reverse counterparts, because they yield sufficiently sparse representations for most accustomed wavefields in  ...  We learn from this observation that the selected metrics only predict the reconstruction error coarsely.  ... 
doi:10.1364/oe.25.018656 pmid:29041062 fatcat:nfm4pbioqjct5lqcfqxakn3qcu

Deep Learning-Based Reconstruction of Interventional Tools from Four X-Ray Projections for Tomographic Interventional Guidance [article]

Elias Eulig, Joscha Maier, Michael Knaup, N. Robert Bennett, Klaus Hörndler, Adam S. Wang, Marc Kachelrieß
2020 arXiv   pre-print
In this work we propose a deep learning-based pipeline for real-time tomographic (four-dimensional) interventional guidance at acceptable dose levels.  ...  Our pipeline is capable of reconstructing interventional tools from only four x-ray projections without the need for a patient prior with very high accuracy.  ...  Fig. 1 . 1 Illustration of a deep learning-based tomographic interventional guidance.  ... 
arXiv:2009.10993v1 fatcat:2rfbgjjbvfgwjap6lhty3pwlpu

A Bayesian fusion model for space-time reconstruction of finely resolved velocities in turbulent flows from low resolution measurements

Linh Van Nguyen, Jean-Philippe Laval, Pierre Chainais
2015 Journal of Statistical Mechanics: Theory and Experiment  
The study of turbulent flows calls for measurements with high resolution both in space and in time.  ...  The model is compared to other conventional methods such as Linear Stochastic Estimation and cubic spline interpolation.  ...  Sparse LTHS and HTLS measurements are subsampled from HTHS data to learn the fusion model. HTHS is used as the ground truth to estimate reconstruction errors.  ... 
doi:10.1088/1742-5468/2015/10/p10008 fatcat:jn4ilca6hzgsbcyb6xuamdps4e

Dictionary Learning on the Manifold of Square Root Densities and Application to Reconstruction of Diffusion Propagator Fields [chapter]

Jiaqi Sun, Yuchen Xie, Wenxing Ye, Jeffrey Ho, Alireza Entezari, Stephen J. Blackband, Baba C. Vemuri
2013 Lecture Notes in Computer Science  
In this paper, we present a novel dictionary learning framework for data lying on the manifold of square root densities and apply it to the reconstruction of diffusion propagator (DP) fields given a multi-shell  ...  Unlike most of the existing dictionary learning algorithms which rely on the assumption that the data points are vectors in some Euclidean space, our dictionary learning algorithm is designed to incorporate  ...  imaging (DSI) proposed in [12] and the tomographic reconstruction methods in [13] [14] [15] .  ... 
doi:10.1007/978-3-642-38868-2_52 pmid:24684004 pmcid:PMC4000552 fatcat:qhrrc6a5uzh3dcoqmsuq3ike5y
« Previous Showing results 1 — 15 out of 330 results