Multi-input Cardiac Image Super-Resolution Using Convolutional Neural Networks
Lecture notes in computer sciencePublished 1 January 2016Open access
Ozan Oktay, Wenjia Bai, Matthew Lee, Ricardo Guerrero, Konstantinos Kamnitsas, José Caballero
Citations219
SJR quartileQ2
SJR score0.35
SNIP0.55
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Experimental results show that the CNN model outperforms state-of-the-art SR methods in terms of image quality while being computationally efficient and that image segmentation and motion tracking benefits more from SR-CNN when it is used as an initial upscaling method than conventional interpolation methods for the subsequent analysis.
Abstract
10.1007/978-3-319-46726-9_29
Keywords
Computer ScienceMedicine
arXiv (Cornell University)Very Deep Convolutional Networks for Large-Scale Image Recognition
75,540 Citations2014Karen Simonyan, Andrew Zisserman
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings of the IEEEGradient-based learning applied to document recognition
58,219 Citations1998Yann LeCun, Léon Bottou +2 more
This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.
IEEE Transactions on Image ProcessingImage quality assessment: from error visibility to structural similarity
56,043 Citations2004Zhou Wang, Alan C. Bovik +2 more
A structural similarity index is developed and its promise is demonstrated through a set of intuitive examples, as well as comparison to both subjective ratings and state-of-the-art objective methods on a database of images compressed with JPEG and JPEG2000.
IEEE Transactions on Pattern Analysis and Machine IntelligenceImage Super-Resolution Using Deep Convolutional Networks
9,852 Citations2015Chao Dong, Chen Change Loy +2 more
This work proposes a deep learning method for single image super-resolution (SR) that directly learns an end-to-end mapping between the low/high-resolution images, represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one.
IEEE Transactions on Medical ImagingNonrigid registration using free-form deformations: application to breast MR images
5,226 Citations1999Daniel Rueckert, Luke Sonoda +4 more
The results clearly indicate that the proposed nonrigid registration algorithm is much better able to recover the motion and deformation of the breast than rigid or affine registration algorithms.
Multi-view Convolutional Neural Networks for 3D Shape Recognition
3,348 Citations2015Hang Su, Subhransu Maji +2 more
This work presents a standard CNN architecture trained to recognize the shapes' rendered views independently of each other, and shows that a 3D shape can be recognized even from a single view at an accuracy far higher than using state-of-the-art3D shape descriptors.
Series in machine perception and artificial intelligenceSIGNATURE VERIFICATION USING A “SIAMESE” TIME DELAY NEURAL NETWORK
2,202 Citations1994Jane Bromley, JAMES W. BENTZ +6 more
Compression Artifacts Reduction by a Deep Convolutional Network
917 Citations2015Chao Dong, Yubin Deng +2 more
A compact and efficient network for seamless attenuation of different compression artifacts is formulated and it is demonstrated that a deeper model can be effectively trained with the features learned in a shallow network.
The Computer JournalSuper-Resolution in Medical Imaging
552 Citations2008Hayit Greenspan
Research on super-resolution research in key medical imaging modalities, including MRI, fMRI and PET, has started to emerge in recent years and is reviewed herein.
Medical Image AnalysisNon-local MRI upsampling
270 Citations2010José V. Manjón, Pierrick Coupé +4 more
A new upsampling method is proposed to recover some of this high frequency information by using a data-adaptive patch-based reconstruction in combination with a subsampling coherence constraint to outperform classical interpolation methods in terms of quantitative measures and visual observation.
Lecture notes in computer scienceCardiac Image Super-Resolution with Global Correspondence Using Multi-Atlas PatchMatch
244 Citations2013Wenzhe Shi, José Caballero +8 more
A novel algorithm for the estimation of high-resolution cardiac MR images from single short-axis cardiac MR image stacks using an innovative super-resolution model which does not require explicit motion estimation and can be used for the reproducible estimation of 3D cardiac functional indices.
IEEE Transactions on Medical ImagingA Probabilistic Patch-Based Label Fusion Model for Multi-Atlas Segmentation With Registration Refinement: Application to Cardiac MR Images
211 Citations2013Wenjia Bai, Wenzhe Shi +6 more
A multi-atlas method that formulates a patch-based label fusion model in a Bayesian framework for cardiac magnetic resonance (MR) image segmentation and improves image registration accuracy by utilizing label information, which leads to improvement of segmentation accuracy.
Medical Image AnalysisSingle-image super-resolution of brain MR images using overcomplete dictionaries
171 Citations2012Andrea Rueda, Norberto Malpica +1 more
A sparse-based super-resolution method, adapted for easily including prior knowledge, which couples up high and low frequency information so that a high-resolution version of a low-resolution brain MR image is generated, shown to outperform a recent state-of-the-art algorithm.
Lecture notes in computer scienceImage Quality Transfer via Random Forest Regression: Applications in Diffusion MRI
105 Citations2014Daniel C. Alexander, Darko Zikic +3 more
This paper proposes a framework for solving the problem of image quality transfer using random forest regression to relate patches in the low-quality data set to voxel values in the high quality data set and demonstrates efficacy on a standard data set.
Super-resolution reconstruction of cardiac MRI using coupled dictionary learning
47 Citations2014Kanwal K. Bhatia, Anthony N. Price +3 more
This paper explores the use of example-based super-resolution, to enable high fidelity patch-based reconstruction, using training data that does not need to be accurately aligned with the target data.
Lecture notes in computer scienceCorrection of Movement Artifacts from 4-D Cardiac Short- and Long-Axis MR Data
40 Citations2004Jyrki Lötjönen, Mika Pollari +2 more
An algorithm was developed to correct movement artifacts simultaneously from short- and long-axis MR cine series and it was found that the algorithm reduced significantly movement artifacts.
Lecture notes in computer scienceMotion-Corrected, Super-Resolution Reconstruction for High-Resolution 3D Cardiac Cine MRI
36 Citations2015Freddy Odille, Aurélien Bustin +3 more
Image sharpness, as assessed by intensity profiles and by objective metrics based on the structure tensor, was improved with both SR techniques and the Beltrami constraint provided efficient denoising without altering the effective resolution.
Lecture notes in computer scienceSuper-Resolution Reconstruction Using Cross-Scale Self-similarity in Multi-slice MRI
35 Citations2013Esben Plenge, Dirk H. J. Poot +2 more
A novel approach to SRR in MRI is presented, which exploits the high-resolution content usually available in the 2D slices of MRI slice stacks to reconstruct isotropic high- resolution 3D images and outperforms state-of-the-art MRI super-resolution methods.
arXiv (Cornell University)Is L2 a Good Loss Function for Neural Networks for Image Processing
35 Citations2015Hang Zhao, Orazio Gallo +2 more
The performance of several losses are studied, including perceptually-motivated losses, and a novel, differentiable error function is proposed, showing that the quality of the results improves significantly with better loss functions, even for the same network architecture.