51,779 Hits in 3.2 sec

Deep Learning Based Detection and Correction of Cardiac MR Motion Artefacts During Reconstruction for High-Quality Segmentation [article]

Ilkay Oksuz, James R. Clough, Bram Ruijsink, Esther Puyol Anton, Aurelien Bustin, Gastao Cruz, Claudia Prieto, Andrew P. King, Julia A. Schnabel
2020 arXiv   pre-print
The method is based on our recently developed joint artefact detection and reconstruction method, which reconstructs high quality MR images from k-space using a joint loss function and essentially converts  ...  Using a test set of 500 2D+time cine MR acquisitions from the UK Biobank data set, we achieve demonstrably good image quality and high segmentation accuracy in the presence of synthetic motion artefacts  ...  Our novel idea of detecting and correcting artefacts from k-space for high segmentation accuracy has been shown to improve both reconstructed image quality and segmentation quality.  ... 
arXiv:1910.05370v4 fatcat:bq6pftuktvhufnycpepolrz2u4

Memory Efficient Model Based Deep Learning Reconstructions for High Spatial Resolution 3D Non-Cartesian Acquisitions [article]

Zachary Miller, Ali Pirasteh, Kevin M. Johnson
2022 arXiv   pre-print
Significance: Block-wise learning allows for MBDL to be applied to high spatial resolution, 3D non-Cartesian datasets with improved image quality and significant reductions in reconstruction time relative  ...  The goal of this work is to develop and apply a memory efficient method called block-wise learning that combines gradient checkpointing with patch-wise training to allow for fast and high-quality 3D non-Cartesian  ...  Such algorithms have been successful in achieving high quality images primarily for 2D Cartesian reconstruction (Hammernik et al., 2018; Aggarwal, Mani and Jacob, 2019) .  ... 
arXiv:2204.13862v2 fatcat:widvl3uknjcvdfuc76iwaa2ai4

Reconstruction for Diverging-Wave Imaging Using Deep Convolutional Neural Networks [article]

Jingfeng Lu, Fabien Millioz, Damien Garcia, Sebastien Salles, Wanyu Liu, Denis Friboulet
2020 arXiv   pre-print
To deal with this limitation, we propose a convolutional neural networks (CNN) architecture for high-quality reconstruction of DW ultrasound images using a small number of transmissions.  ...  A mapping between low-quality images and corresponding high-quality compounded reconstruction was learned by training the network using in vitro and in vivo samples.  ...  ., images). In this paper, we introduce a novel CNN architecture for high-quality reconstruction for DW imaging using a small number of DW transmissions.  ... 
arXiv:1911.03416v3 fatcat:nuu6czc7grgrfnzb57i3uwplku

Context-Sensitive Super-Resolution for Fast Fetal Magnetic Resonance Imaging [chapter]

Steven McDonagh, Benjamin Hou, Amir Alansary, Ozan Oktay, Konstantinos Kamnitsas, Mary Rutherford, Jo V. Hajnal, Bernhard Kainz
2017 Lecture Notes in Computer Science  
3D Magnetic Resonance Imaging (MRI) is often a trade-off between fast but low-resolution image acquisition and highly detailed but slow image acquisition.  ...  the generation of high resolution images with sharp edges and fine scale detail.  ...  image acquisition.  ... 
doi:10.1007/978-3-319-67564-0_12 fatcat:rxm4bt7nqfav5nnynpmme2utji

23 Na MRI in ischemic stroke: Acquisition time reduction using postprocessing with convolutional neural networks

Anne Adlung, Nadia K. Paschke, Alena‐Kathrin Golla, Dominik Bauer, Sherif A. Mohamed, Melina Samartzi, Marc Fatar, Eva Neumaier‐Probst, Frank G. Zöllner, Lothar R. Schad
2021 NMR in Biomedicine  
Long acquisition times are one of the most challenging aspects for its clinical establishment. K-space undersampling is an approach for acquisition time reduction, but generates noise and artifacts.  ...  The reconstructions were performed with full dataset (FI) and with a simulated dataset an image that was acquired in 2.5 min (RI).  ...  ACKNOWLEDGEMENTS The authors would like to thank Victor Saase for participating in the subjective image quality rating. Shradha Jain, Dr Michaela A.U.  ... 
doi:10.1002/nbm.4474 pmid:33480128 fatcat:a24y7jg6kbah3bqj2moifqgksq

A Deep Learning-based Integrated Framework for Quality-aware Undersampled Cine Cardiac MRI Reconstruction and Analysis [article]

Inês P. Machado, Esther Puyol-Antón, Kerstin Hammernik, Gastão Cruz, Devran Ugurlu, Ihsane Olakorede, Ilkay Oksuz, Bram Ruijsink, Miguel Castelo-Branco, Alistair A. Young, Claudia Prieto, Julia A. Schnabel (+1 others)
2022 arXiv   pre-print
The framework enables active acquisition of radial k-space data, in which acquisition can be stopped as soon as acquired data are sufficient to produce high quality reconstructions and segmentations.  ...  In this paper, we present a fully-automated, quality-controlled integrated framework for reconstruction, segmentation and downstream analysis of undersampled cine CMR data.  ...  Traditionally, cine CMR acquisition, reconstruction and analysis have been considered as independent steps, despite the obvious inter-dependence between high-quality image reconstruction and high accuracy  ... 
arXiv:2205.01673v1 fatcat:erl7jduhyfelpddyzla7zyf4gq

High-resolution Petrous Bone Imaging Using Multi-slice Computerized Tomography

R. Klingebiel, H.-C. Bauknecht, P. Rog
2001 Acta Oto-Laryngologica  
We de ned a data acquisition protocol for high-resolution (HR) temporal bone imaging using MSCT and assessed its impact on data acquisition and post-processing (PP).  ...  The parameters image quality and diagnostic value of MSCT data were assessed for the cross-sectional source images as well as for 2-dimensional (2D) reformations and 3-dimensional (3D) reconstructions  ...  This is especially important for petrous bone imaging as it is very dif cult to assess the complex internal architecture without using reformatted and:or reconstructed images (2, 6) .  ... 
doi:10.1080/00016480118263 pmid:11583399 fatcat:f2rwczm2zjhtngczvfue5mkd4q

Context-based image acquisition from memory in digital systems

Jianxiong Liu, Christos Bouganis, Peter Y. K. Cheung
2016 Journal of Real-Time Image Processing  
that efficiently trades image quality for reduced cost of the image acquisition process.  ...  The sampled pixels are used to reconstruct an approximation to the ground truth, which is stored in a high-performance image buffer for further processing.  ...  This trade-off between image quality and various costs of image acquisition is the key idea of the proposed CbIA framework that provides an alternative approach of designing hardware architectures for  ... 
doi:10.1007/s11554-016-0591-1 fatcat:rtu2eh5cdjaklm5uvaz54c5hpq

Compressed hyperspectral sensing

Grigorios Tsagkatakis, Panagiotis Tsakalides, Ralf Widenhorn, Antoine Dupret
2015 Image Sensors and Imaging Systems 2015  
integration periods, without the need for successive frame acquisition.  ...  A key shortcoming shared by all current methods lies in the high scanning repetition rates required for generating the complete 3D hyperspectral datacube.  ...  In this work, we proposed a novel HSI architecture that can achieve high quality reconstruction of the hypercube Ipx, λq from a limited number of frames, without resorting to moving parts, by exploiting  ... 
doi:10.1117/12.2083282 fatcat:udl2aqlxnbavfju6sf4ukua7ne

From Compressed-Sensing to Artificial Intelligence-Based Cardiac MRI Reconstruction

Aurélien Bustin, Niccolo Fuin, René M. Botnar, Claudia Prieto
2020 Frontiers in Cardiovascular Medicine  
However, CMR suffers from long acquisition times due to the need of obtaining images with high temporal and spatial resolution, different contrasts, and/or whole-heart coverage.  ...  In this article, we provide an overview of the recent developments in the area of artificial intelligence for CMR image reconstruction.  ...  for DL reconstruction, and high-quality MR images are obtained as an output in an end-to-end fashion.  ... 
doi:10.3389/fcvm.2020.00017 pmid:32158767 pmcid:PMC7051921 fatcat:xbge626jhzeulfjlssdlqnalze

Joint multi-contrast Variational Network reconstruction (jVN) with application to rapid 2D and 3D imaging [article]

Daniel Polak, Stephen Cauley, Berkin Bilgic, Enhao Gong, Peter Bachert, Elfar Adalsteinsson, Kawin Setsompop
2019 arXiv   pre-print
Complementary k-space sampling across imaging contrasts and Bunch-Phase/Wave-Encoding were used for data acquisition to improve the reconstruction at high accelerations.  ...  Purpose: To improve the image quality of highly accelerated multi-channel MRI data by learning a joint variational network that reconstructs multiple clinical contrasts jointly.  ...  We empirically observed that this improved the image quality for all evaluated reconstructions.  ... 
arXiv:1910.03273v1 fatcat:es3naqkmy5bcncjkxcp2v4z3wm

APIR-Net: Autocalibrated Parallel Imaging Reconstruction using a Neural Network [article]

Chaoping Zhang, Florian Dubost, Marleen de Bruijne, Stefan Klein, Dirk H.J. Poot
2019 arXiv   pre-print
The experiments indicate that APIR-Net provides a promising alternative to the conventional parallel imaging methods, and results in improved image quality especially for low SNR acquisitions.  ...  Deep learning has been successfully demonstrated in MRI reconstruction of accelerated acquisitions.  ...  To conclude, APIR-Net provides a promising alternative to the conventional parallel imaging methods, and results in improved image quality especially for low SNR acquisitions.  ... 
arXiv:1909.09006v1 fatcat:luaglwjtszdrhj25zg4n22wg6q

A Multimodal Deep Network for the Reconstruction of T2W MR Images [article]

Antonio Falvo, Danilo Comminiello, Simone Scardapane, Michele Scarpiniti, Aurelio Uncini
2020 arXiv   pre-print
In this paper, we present a deep learning method that is able to reconstruct subsampled MR images obtained by reducing the k-space data, while maintaining a high image quality that can be used to observe  ...  Results prove the effectiveness of the proposed method in reconstructing subsampled MR images while saving execution time.  ...  By using the proposed architecture, high image quality is achieved, thus enabling the recognition of brain injuries caused by the disease.  ... 
arXiv:1908.03009v2 fatcat:5a2cccj2r5ak3br2bt5brc4cya

Reconstruction in deep learning of highly under-sampled T2-weighted image with T1-weighted image

Lei Xiang, Weitang Chang, Yong Chen, Weili Lin, Qian Wang, Dinggang Shen
2018 Proceedings of the International Society for Magnetic Resonance in Medicine ... Scientific Meeting and Exhibition. International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition  
Discuss and Conclusion In this work, we propose a U-net architecture for reconstruction of high-quality T2WI with prior information of T1WI.  ...  Our results demonstrate that the proposed method could achieve 8 or higher acceleration rate while keeping high image quality of the reconstructed T2WI.  ... 
pmid:30956568 pmcid:PMC6448782 fatcat:ec5aiagdebakpotbremt2fy3ua

Applications of Deep Learning to Neuro-Imaging Techniques

Guangming Zhu, Bin Jiang, Liz Tong, Yuan Xie, Greg Zaharchuk, Max Wintermark
2019 Frontiers in Neurology  
/harmonizing images, improving image quality, lowering radiation and contrast dose, and shortening the duration of imaging studies.  ...  There are many other innovative applications of AI in various technical aspects of medical imaging, particularly applied to the acquisition of images, ranging from removing image artifacts, normalizing  ...  This approach produced high quality ASL images by denoising images without estimating its noise level.  ... 
doi:10.3389/fneur.2019.00869 pmid:31474928 pmcid:PMC6702308 fatcat:yki64mb57jhafduasd3hohfkgi
« Previous Showing results 1 — 15 out of 51,779 results