Filters








673 Hits in 5.6 sec

Regularized Compression of MRI Data: Modular Optimization of Joint Reconstruction and Coding [article]

Veronica Corona, Yehuda Dar, Guy Williams, Carola-Bibiane Schönlieb
2020 arXiv   pre-print
In this work we propose a framework for joint optimization of the MRI reconstruction and lossy compression, producing compressed representations of medical images that achieve improved trade-offs between  ...  Our experiments show that our regularization-based approach for joint MRI reconstruction and compression often achieves significant PSNR gains between 4 to 9 dB at high bit-rates compared to non-regularized  ...  CONCLUSION In this paper we proposed a new modular optimization method for joint reconstruction and lossy compression of MRI data.  ... 
arXiv:2010.04065v2 fatcat:tq4y6ve525bohna74hwirbo6ei

Bi-Linear Modeling of Data Manifolds for Dynamic-MRI Recovery [article]

Gaurav N. Shetty, Konstantinos Slavakis, Abhishek Bose, Ukash Nakarmi, Gesualdo Scutari, Leslie Ying
2019 arXiv   pre-print
Extensive numerical results on simulated as well as real cardiac-cine and perfusion MRI data illustrate noteworthy improvements of the advocated machine-learning framework over state-of-the-art reconstruction  ...  Recovery of the high-fidelity MRI data is realized by solving a non-convex minimization task for the linear decompression operator and those affine combinations of landmark points which locally approximate  ...  Optimized and time-efficient C/C++ versions of the developed MATLAB code for BiLMDM are not considered in this work.  ... 
arXiv:1812.10617v2 fatcat:mxyrh6adrjfvlpayh3hvyvn2tu

Image reconstruction by domain-transform manifold learning

Bo Zhu, Jeremiah Z. Liu, Stephen F. Cauley, Bruce R. Rosen, Matthew S. Rosen
2018 Nature  
strategy, and often requires expert parameter tuning to optimize reconstruction performance.  ...  Image reconstruction plays a critical role in the implementation of all contemporary imaging modalities across the physical and life sciences including optical, MRI, CT, PET, and radio astronomy.  ...  convolutional domain and the sparse representations through a joint optimization (see Supplementary Methods for details).  ... 
doi:10.1038/nature25988 pmid:29565357 fatcat:g54lhh77w5f37op5kbwhljkshi

High-dimensionality undersampled patch-based reconstruction (HD-PROST) for accelerated multi-contrast MRI

Aurélien Bustin, Gastão Lima da Cruz, Olivier Jaubert, Karina Lopez, René M. Botnar, Claudia Prieto
2019 Magnetic Resonance in Medicine  
To develop a new high-dimensionality undersampled patch-based reconstruction (HD-PROST) for highly accelerated 2D and 3D multi-contrast MRI.  ...  The regularization parameter , which balances the contribution of the prior term (obtained at the end of optimization 2) and the data fidelity term, was set to 5e −3 .  ...  | Optimization 1: joint MR reconstruction update The first sub-problem is a joint multi-contrast MR reconstruction that incorporates the denoised tensor  (obtained at the end of optimization 2) as  ... 
doi:10.1002/mrm.27694 pmid:30834594 pmcid:PMC6646908 fatcat:dknap4ijdrfzdilzdwiu7qrjp4

Dynamic Proximal Unrolling Network for Compressive Imaging [article]

Yixiao Yang, Ran Tao, Kaixuan Wei, Ying Fu
2021 arXiv   pre-print
Specifically, DPUNet can exploit both the embedded observation model via gradient descent and imposed image priors by learned dynamic proximal operators, achieving joint reconstruction.  ...  Experimental results demonstrate that the proposed DPUNet can effectively handle multiple compressive imaging modalities under varying sampling ratios and noise levels via only one trained model, and outperform  ...  Given the modular nature of the proximal optimization framework, the overall iterative procedure can be truncated and unrolled into a trainable reconstruction network by replacing all instances of the  ... 
arXiv:2107.11007v2 fatcat:kejgz4xl2zcfvdzbywjhiyriy4

Proceedings of 3rd IEEE International Conference on Image Processing

1996 Proceedings of 3rd IEEE International Conference on Image Processing ICIP-96  
Tubaro 18A5: Stereo coding and application-oriented coding Joint estimation and optimum encoding of depth field for 3-D object-based video coding A. Aydin Alatan, L.  ...  Macq Irregular image sub-sampling and reconstruction by adaptive sampling Subband VPIC with classified joint vector quantization A hybrid object-based video compression technique DCT of spatially adaptive  ... 
doi:10.1109/icip.1996.559416 fatcat:jb4cdydgf5edtdljfuzj423ozu

International Conference on Image Processing

1996 Proceedings of 3rd IEEE International Conference on Image Processing  
Macq Irregular image sub-sampling and reconstruction by adaptive sampling Subband VPIC with classified joint vector quantization A hybrid object-based video compression technique DCT of spatially adaptive  ...  binary position coding Fast Wavelet transform for color image compression Direct processing of EZW compressed image data Enhanced zerotree wavelet transform image coding exploiting similarities  ... 
doi:10.1109/icip.1996.560353 fatcat:le3ysy6wxrfr7nq56ueropy7tu

Deep Learning in Mining Biological Data

Mufti Mahmud, M. Shamim Kaiser, T. Martin McGinnity, Amir Hussain
2021 Cognitive Computation  
Mining such enormous amount of data for pattern recognition is a big challenge and requires sophisticated data-intensive machine learning techniques.  ...  To investigate how DL—especially its different architectures—has contributed and been utilized in the mining of biological data pertaining to those three types, a meta-analysis has been performed and the  ...  Acknowledgements The authors would like to thank the members of the acslab (http://www.acsla b.info/) for valuable discussions. Author Contributions  ... 
doi:10.1007/s12559-020-09773-x pmid:33425045 pmcid:PMC7783296 fatcat:n4nk7gakfbb4fbhdi5pqeojwjm

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
Li, L., +, Joint Coding of Local and Global Deep Features in Videos for Visual Search. Learned Fast HEVC Intra Coding.  ...  ., +, TIP 2020 9292-9304 Joint Coding of Local and Global Deep Features in Videos for Visual Search. Ding, L., +, TIP 2020 3734-3749 Learned Fast HEVC Intra Coding.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Small Sample Learning in Big Data Era [article]

Jun Shu, Zongben Xu, Deyu Meng
2018 arXiv   pre-print
This category mainly focuses on learning with insufficient samples, and can also be called small data learning in some literatures.  ...  More extensive surveys on both categories of SSL techniques are introduced and some neuroscience evidences are provided to clarify the rationality of the entire SSL regime, and the relationship with human  ...  priors, outperforming the state-of-the-art results for a wide variety of imaging problems, such as denoising, deblurring, and compressed sensing magnetic resonance imaging(MRI).  ... 
arXiv:1808.04572v3 fatcat:lqqzzrmgfnfb3izctvdzgopuny

Development of Real-Time Magnetic Resonance Imaging of Mouse Hearts at 9.4 Tesla— Simulations and First Application

Tobias Wech, Nicole Seiberlich, Andreas Schindele, Vicente Grau, Leonie Diffley, Michael L. Gyngell, Alfio Borzi, Herbert Kostler, Jurgen E. Schneider
2016 IEEE Transactions on Medical Imaging  
Simulations on an in silico phantom were performed to determine the achievable acceleration factor and to optimize regularization parameters.  ...  The technique combines a highly undersampled radial gradient echo acquisition with an image reconstruction utilizing both parallel imaging and compressed sensing.  ...  Optimizing the regularization of FISTA-TV The choice of the two regularization parameters α and μ within the optimization problem [3] has significant impact on the reconstruction performance of FISTA-TV  ... 
doi:10.1109/tmi.2015.2501832 pmid:26595913 pmcid:PMC4948122 fatcat:xbput2hwhvhtde3uwdfdi3w4zy

Table of contents

2020 IEEE Transactions on Image Processing  
Zeng 9654 Lossless Coding of Images and Video Graph-Based Compensated Wavelet Lifting for Scalable Lossless Coding of Dynamic Medical Data ................... ..........................................  ...  Ortega 9330 Rate Distortion Optimization: A Joint Framework and Algorithms for Random Access Hierarchical Video Coding ................................................................. X. Wang, E.-h.  ...  Lin, and Zhang, Y. Tian, K. Wang, W. Zhang, and F.-  ... 
doi:10.1109/tip.2019.2940373 fatcat:i7hktzn4wrfz5dhq7hj75u6esa

A Multi-GPU Programming Library for Real-Time Applications [chapter]

Sebastian Schaetz, Martin Uecker
2012 Lecture Notes in Computer Science  
We achieve a speed-up of about 1.7 using 2 GPUs and reach a final speed-up of 2.1 with 4 GPUs.  ...  Such systems combine disproportionate floating point performance with high data locality and are thus well suited to implement real-time algorithms.  ...  This version however is not taken into account in this comparison because of MGPUunrelated code optimization.  ... 
doi:10.1007/978-3-642-33078-0_9 fatcat:kcur6mssxbg2pjmttin3d3kkaq

Connectivity Inference from Neural Recording Data: Challenges, Mathematical Bases and Research Directions [article]

Ildefons Magrans de Abril, Junichiro Yoshimoto, Kenji Doya
2017 arXiv   pre-print
This article presents a review of computational methods for connectivity inference from neural activity data derived from multi-electrode recordings or fluorescence imaging.  ...  We first identify biophysical and technical challenges in connectivity inference along the data processing pipeline.  ...  and internal funding from the Okinawa Institute of Science and Technology Graduate University.  ... 
arXiv:1708.01888v2 fatcat:fezbmzuzenac7mqcnqhq5sveye

Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction

Matthew J. Muckley, Bruno Riemenschneider, Alireza Radmanesh, Sunwoo Kim, Geunu Jeong, Jingyu Ko, Yohan Jun, Hyungseob Shin, Dosik Hwang, Mahmoud Mostapha, Simon Arberet, Dominik Nickel (+11 others)
2021 IEEE Transactions on Medical Imaging  
Lastly, we identify common failure modes across the submissions, highlighting areas of need for future research in the MRI reconstruction community.  ...  Accelerating MRI scans is one of the principal outstanding problems in the MRI research community.  ...  We give special thanks to Philips North America and their clinical partner sites for the data they contributed for use as part of the Transfer track.  ... 
doi:10.1109/tmi.2021.3075856 fatcat:sfwfufzrw5eb7gm63oy5lkmt3u
« Previous Showing results 1 — 15 out of 673 results