Filters








405 Hits in 5.6 sec

Patch based super-resolution of MR spectroscopic images

S. Jain, D. M. Sima, F. Sanaei Nezhad, S. Williams, S. Van Huffel, F. Maes, D. Smeets
2016 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)  
The proposed method is based on a non-local patch-based strategy that uses a high resolution T1-weighted image to regularise the super-resolution process.  ...  In this paper, a new single-image super-resolution method is presented to increase the spatial resolution of metabolite maps computed from magnetic resonance spectroscopic imaging.  ...  To the best of our knowledge, a patch-based super-resolution technique has never been applied before for up-sampling MRSI-based metabolic images.  ... 
doi:10.1109/isbi.2016.7493305 dblp:conf/isbi/JainSNWHMS16 fatcat:dulmsqpymvbr7g5lqhi6dxqq7q

Patch-Based Super-Resolution of MR Spectroscopic Images: Application to Multiple Sclerosis

Saurabh Jain, Diana M. Sima, Faezeh Sanaei Nezhad, Gilbert Hangel, Wolfgang Bogner, Stephen Williams, Sabine Van Huffel, Frederik Maes, Dirk Smeets
2017 Frontiers in Neuroscience  
Methods: In this paper, a patch-based super-resolution method is presented to increase the spatial resolution of metabolite maps computed from MRSI.  ...  The proposed method uses high resolution anatomical MR images (T1-weighted and Fluid-attenuated inversion recovery) to regularize the super-resolution process.  ...  AUTHOR CONTRIBUTIONS SJ, DMS, SV, FM, DS contributed to the design and analysis of the work; FS, GH, WB, SW contributed to the data acquisition; SJ and DMS wrote the paper; all authors revised the manuscript  ... 
doi:10.3389/fnins.2017.00013 pmid:28197066 pmcid:PMC5281632 fatcat:5rmb44mvz5anbefttmvp6mm3h4

Super Resolution Convolutional Neural Networks for Increasing Spatial Resolution of $$^{1}$$ H Magnetic Resonance Spectroscopic Imaging [chapter]

Sevim Cengiz, Maria del C. Valdes-Hernandez, Esin Ozturk-Isik
2017 Communications in Computer and Information Science  
Advanced post-processsing algorithms, like convolutional neural networks (CNN) might help with generation of super resolution MR spectroscopic images.  ...  FLAIR, T1 weighted and T2 weighted MR images were used in training the SRCNN scheme. The spatial resolution of MRSI images were increased by using the model trained with the anatomical MR images.  ...  Future studies will be conducted to investigate the use of other deep learning methods, like fast SRCNN (FSR-CNN) and patch-based super-resolution, to increase the spatial resolution of MR spectroscopic  ... 
doi:10.1007/978-3-319-60964-5_56 fatcat:x2ssncjjhbahdcurqmhfi63iqm

Workshop on reconstruction schemes for magnetic resonance data: summary of findings and recommendations

Esin Ozturk-Isik, Ian Marshall, Patryk Filipiak, Arnold J. V. Benjamin, Valia Guerra Ones, Rafael Ortiz Ramón, Maria del C. Valdés Hernández
2017 Royal Society Open Science  
image patches whereas Y l is the space of low-resolution observations of patches in X h .  ...  Recent advances in super-resolution MR may offer the possibility of improving the resolution of MR images and was mentioned as an avenue worth exploring.  ...  All authors listed approved the present version of the article and agreed to be accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the  ... 
doi:10.1098/rsos.160731 pmid:28386427 pmcid:PMC5367301 fatcat:54xhzt743zd53kbhqlvbqfesfu

Super-Resolution Hyperpolarized 13C Imaging of Human Brain Using Patch-Based Algorithm

2020 Tomography  
In this study, a patch-based algorithm (PA) is proposed to enhance spatial resolution of hyperpolarized 13C human brain images by exploiting compartmental information from the corresponding high-resolution  ...  Spatial resolution of metabolic imaging with hyperpolarized 13C-labeled substrates is limited owing to the multidimensional nature of spectroscopic imaging and the transient characteristics of dissolution  ...  ACKNOWLEDGMENTS We appreciate the clinical research team and the supporting staffs of the Advanced Imaging Research Center at UT Southwestern for imaging the volunteers-Craig R.  ... 
doi:10.18383/j.tom.2020.00037 pmid:33364424 pmcid:PMC7744189 fatcat:t2c6nfnsgfcbrcmjv4ipk4ydey

Fine-tuning deep learning model parameters for improved super-resolution of dynamic MRI with prior-knowledge [article]

Chompunuch Sarasaen, Soumick Chatterjee, Mario Breitkopf, Georg Rose, Andreas Nürnberger, Oliver Speck
2021 arXiv   pre-print
An U-Net based network with perceptual loss is trained on a benchmark dataset and fine-tuned using one subject-specific static high resolution MRI as prior knowledge to obtain high resolution dynamic images  ...  To overcome this spatio-temporal trade-off, this research presents a super-resolution (SR) MRI reconstruction with prior knowledge based fine-tuning to maximise spatial information while reducing the required  ...  Acknowledgements This work was conducted within the context of the International Graduate School MEMoRIAL at Otto von Guericke University (OVGU) Magdeburg, Germany, kindly supported by the European Structural  ... 
arXiv:2102.02711v3 fatcat:caq3etvnujdb7dqi5qbndyvdsi

Sparse Representation based Super-Resolution of MRI Images with Non-Local Total Variation Regularization

Bhabesh Deka, Helal Uddin Mullah, Sumit Datta, Vijaya Lakshmi, Rajarajeswari Ganesan
2020 SN Computer Science  
In this paper, we propose sparse representation over a learned overcomplete dictionary based single-image super-resolution (SISR) technique for DW and MRS images.  ...  These images are also acquired at a faster rate, but with low signal-to-noise ratio. This limitation can be overcome by applying image super-resolution techniques.  ...  These limits can be overcome by image super-resolution (SR) [3] , which estimates a high-resolution (HR) from one or more available low-resolution (LR) image (s).  ... 
doi:10.1007/s42979-020-00269-x fatcat:b37lt7xionhdfcvrkdv32vmzam

7T-guided super-resolution of 3T MRI

Khosro Bahrami, Feng Shi, Islem Rekik, Yaozong Gao, Dinggang Shen
2017 Medical Physics (Lancaster)  
Conclusions-We propose a novel method for prediction of high-resolution 7T-like MR images from low-resolution 3T MR images.  ...  To this end, we propose a method to generate super-resolution 3T MRI that resembles 7T MRI, which is called as 7T-like MR image in this paper.  ...  Several works 24, 25, 26, 27, 28, 29, 30, 31 aimed to reconstruct super-resolution of natural images based on learning-based approaches.  ... 
doi:10.1002/mp.12132 pmid:28177548 pmcid:PMC5686784 fatcat:oemt6s6drzeiflut7lhekcrg7u

Deep Learning Super-resolution MR Spectroscopic Imaging of Brain Metabolism and Mutant IDH Glioma

Xianqi Li, Bernhard Strasser, Ulf Neuberger, Philipp Vollmuth, Martin Bendszus, Wolfgang Wick, Jorg Dietrich, Tracy T Batchelor, Daniel P Cahill, Ovidiu C Andronesi
2022 Neuro-Oncology Advances  
To further enhance structural details of metabolic maps we used prior information from high resolution anatomical MR imaging.  ...  The aim of this study was to achieve super-resolution MRSI using deep learning to image tumor metabolism in patients with mutant IDH glioma.  ...  This can be further improved by the aid of high-resolution anatomical MR images.  ... 
doi:10.1093/noajnl/vdac071 pmid:35911635 pmcid:PMC9332900 fatcat:z4dfgtcd7jdn7f7o3rg272eixe

High-resolution metabolic mapping of gliomas via patch-based super-resolution magnetic resonance spectroscopic imaging at 7T

Gilbert Hangel, Saurabh Jain, Elisabeth Springer, Eva Hečková, Bernhard Strasser, Michal Považan, Stephan Gruber, Georg Widhalm, Barbara Kiesel, Julia Furtner, Matthias Preusser, Thomas Roetzer (+4 others)
2019 NeuroImage  
PBSR-MRSI combines the benefits of ultra-high-field MR systems, cutting-edge MRSI, and advanced postprocessing to allow millimetric resolution molecular imaging of glioma tissue beyond standard methods  ...  An ideal example is the accurate imaging of glutamine, which is a prime target of modern therapeutic approaches, made possible due to the higher spectral resolution of 7 T systems.  ...  Patch-based super-resolution (PBSR) uses prior knowledge from MR imaging to further reduce partial volume errors, thereby recovering spatial details from lower-resolution imaging, such as MRSI (Jain et  ... 
doi:10.1016/j.neuroimage.2019.02.023 pmid:30772399 pmcid:PMC7220803 fatcat:yhyk6pc2vrcxzf3rmq3ahbmh4a

Simultaneous Super-Resolution and Distortion Correction for Single-shot EPI DWI using Deep Learning [article]

Xinyu Ye, Peipei Wang, Sisi Li, Jieying Zhang, Yuan Lian, Yajing Zhang, Jie Lu, Hua Guo
2021 bioRxiv   pre-print
The results showed that the distortion-corrected high-resolution DWI images with restored anatomical details can be obtained from low-resolution SS-EPI images by taking the advantage of high-resolution  ...  Here we proposed a deep learning-based image-quality-transfer method with a novel loss function with improved network structure to simultaneously increase the resolution and correct distortions for SS-EPI  ...  Thus, the reconstruction of the super-resolution image can be viewed as a convolution process of low-resolution image patches.  ... 
doi:10.1101/2021.12.03.470880 fatcat:uvgcxcblgrcxbg2zoy5tuvpqa4

Flow-based Visual Quality Enhancer for Super-resolution Magnetic Resonance Spectroscopic Imaging [article]

Siyuan Dong, Gilbert Hangel, Eric Z. Chen, Shanhui Sun, Wolfgang Bogner, Georg Widhalm, Chenyu You, John A. Onofrey, Robin de Graaf, James S. Duncan
2022 arXiv   pre-print
Deep learning-based super-resolution methods provided promising results for improving the spatial resolution of MRSI, but the super-resolved images are often blurry compared to the experimentally-acquired  ...  Specifically, we propose a flow-based enhancer network to improve the visual quality of super-resolution MRSI.  ...  We first use a pretrained Multi-encoder UNet (MUNet) [9, 12, 13] as the SR Network to obtain a super-resolved image H from the low-resolution image L.  ... 
arXiv:2207.10181v1 fatcat:bszarb5r35dttlyuw4dvzewy4q

Applications of Deep Learning to Neuro-Imaging Techniques

Guangming Zhu, Bin Jiang, Liz Tong, Yuan Xie, Greg Zaharchuk, Max Wintermark
2019 Frontiers in Neurology  
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  ...  /harmonizing images, improving image quality, lowering radiation and contrast dose, and shortening the duration of imaging studies.  ...  (GAN-CIRCLE), for super-resolution MRI from low-resolution MRI.  ... 
doi:10.3389/fneur.2019.00869 pmid:31474928 pmcid:PMC6702308 fatcat:yki64mb57jhafduasd3hohfkgi

The 2018 correlative microscopy techniques roadmap

Toshio Ando, Satya Prathyusha Bhamidimarri, Niklas Brending, H Colin-York, Lucy Collinson, Niels De Jonge, P J de Pablo, Elke Debroye, Christian Eggeling, Christian Franck, Marco Fritzsche, Hans Gerritsen (+24 others)
2018 Journal of Physics D: Applied Physics  
A wide and diverse range of methodologies is now available, including electron microscopy, atomic force microscopy, magnetic resonance imaging, small-angle x-ray scattering and multiple super-resolution  ...  The latter can be achieved with fluorescence microscopy which, however, requires labelling and lacks spatial resolution.  ...  Acknowledgments Mr Donald Maillet for engineering expertise.  ... 
doi:10.1088/1361-6463/aad055 pmid:30799880 pmcid:PMC6372154 fatcat:sg76jitzs5es7ksufvc76kawdi

Accelerated MR spectroscopic imaging—a review of current and emerging techniques

Wolfgang Bogner, Ricardo Otazo, Anke Henning
2020 NMR in Biomedicine  
Over more than 30 years in vivo MR spectroscopic imaging (MRSI) has undergone an enormous evolution from theoretical concepts in the early 1980s to the robust imaging technique that it is today.  ...  In this way in vivo MRSI has considerably advanced in terms of spatial coverage, spatial resolution, acquisition speed, artifact suppression, number of detectable metabolites and quantification precision  ...  Moser, Lukas Hingerl and Gilbert Hangel for their support with the preparation of Figures 1, 4, 6 , and 8 as well as Zhi-Pei Liang and Fan Lam for providing Figure 15 . ORCID  ... 
doi:10.1002/nbm.4314 pmid:32399974 pmcid:PMC8244067 fatcat:kx2yyrjp7vbhvks5j723s5prre
« Previous Showing results 1 — 15 out of 405 results