Cardiac Image Super-Resolution with Global Correspondence Using Multi-Atlas PatchMatch
Lecture notes in computer sciencePublished 1 January 2013Open access
Wenzhe Shi, José Caballero, Christian Ledig, Xiahai Zhuang, Wenjia Bai, Kanwal K. Bhatia
Citations244
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
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.
Abstract
The accurate measurement of 3D cardiac function is an important task in the analysis of cardiac magnetic resonance (MR) images. However, short-axis image acquisitions with thick slices are commonly used in clinical practice due to constraints of acquisition time, signal-to-noise ratio and patient compliance. In this situation, the estimation of a high-resolution image can provide an approximation of the underlaying 3D measurements. In this paper, we develop a novel algorithm for the estimation of high-resolution cardiac MR images from single short-axis cardiac MR image stacks. First, we propose to use a novel approximate global search approach to find patch correspondence between the short-axis MR image and a set of atlases. Then, we propose an innovative super-resolution model which does not require explicit motion estimation. Finally, we build an expectation-maximization framework to optimize the model. We validate the proposed approach using images from 19 subjects with 200 atlases and show that the proposed algorithm significantly outperforms conventional interpolation such as linear or B-spline interpolation. In addition, we show that the super-resolved images can be used for the reproducible estimation of 3D cardiac functional indices.
Keywords
Computer ScienceEngineering
International Journal of Computer VisionRobust Real-Time Face Detection
14,193 Citations2004Paul Viola, Michael Jones
A new image representation called the “Integral Image” is introduced which allows the features used by the detector to be computed very quickly and a method for combining classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising face-like regions.
IEEE Transactions on Pattern Analysis and Machine IntelligenceMedical image analysis: progress over two decades and the challenges ahead
4,160 Citations2000James S. Duncan, Nicholas Ayache
A look at progress in the field over the last 20 years is looked at and some of the challenges that remain for the years to come are suggested.
IEEE Computer Graphics and ApplicationsExample-based super-resolution
2,509 Citations2002William T. Freeman, Thouis R. Jones +1 more
This work built on another training-based super- resolution algorithm and developed a faster and simpler algorithm for one-pass super-resolution that requires only a nearest-neighbor search in the training set for a vector derived from each patch of local image data.
IEEE Transactions on Pattern Analysis and Machine IntelligenceLimits on super-resolution and how to break them
1,210 Citations2002Simon Baker, Takeo Kanade
Limits on super-resolution and how to break them
1,183 Citations2002Simon Baker, Takeo Kanade
An algorithm is proposed that learns recognition-based priors for specific classes of scenes, the use of which gives far better super-resolution results for both faces and text.
Lecture notes in computer scienceClassCut for Unsupervised Class Segmentation
995 Citations2010Bogdan Alexe, Thomas Deselaers +1 more
A novel method for unsupervised class segmentation on a set of images that alternates between segmenting object instances and learning a class model based on a segmentation energy defined over all images at the same time, which can be optimized efficiently by techniques used before in interactive segmentation.
IEEE Transactions on Signal ProcessingB-spline signal processing. I. Theory
915 Citations1993Michaël Unser, Akram Aldroubi +1 more
The use of continuous B-spline representations for signal processing applications such as interpolation, differentiation, filtering, noise reduction, and data compressions, and the extension of such operators for higher-dimensional signals such as digital images is considered.
NeuroImagePatch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation
688 Citations2010Pierrick Coupé, José V. Manjón +4 more
Inspired by recent work in image denoising, the proposed nonlocal patch-based label fusion produces accurate and robust segmentation in quantitative magnetic resonance analysis.
Magnetic Resonance in MedicineOn standardizing the MR image intensity scale
563 Citations1999L�szl� G. Ny�l, Jayaram K. Udupa
The method was tested quantitatively on 90 whole‐brain studies of multiple sclerosis patients for several protocols and qualitatively for several other protocols and body regions and showed that the standardized image intensities have statistically significantly more consistent range and meaning than the originals.
Lecture notes in computer scienceThe Generalized PatchMatch Correspondence Algorithm
546 Citations2010Connelly Barnes, Eli Shechtman +2 more
This paper generalizes PatchMatch in three ways: to find k nearest neighbors, as opposed to just one, to search across scales and rotations, in addition to just translations, and to match using arbitrary descriptors and distances, not just sum-of-squared-differences on patch colors.
IEEE Transactions on Medical ImagingRobust Super-Resolution Volume Reconstruction From Slice Acquisitions: Application to Fetal Brain MRI
359 Citations2010Ali Gholipour, J A Estroff +1 more
A novel technique based on a slice acquisition model, which enables the reconstruction of a volumetric image from multiple-scan slice acquisitions and a robust M-estimation solution which minimizes a robust error norm function between the model-generated slices and the acquired slices are developed.
IEEE Transactions on Image ProcessingSuper-Resolution Without Explicit Subpixel Motion Estimation
304 Citations2009Hiroyuki Takeda, Peyman Milanfar +2 more
This paper introduces a novel framework for adaptive enhancement and spatiotemporal upscaling of videos containing complex activities without explicit need for accurate motion estimation based on multidimensional kernel regression, which significantly widens the applicability of super-resolution methods to a broad variety of video sequences containing complex motions.
Signal Image and Video ProcessingA survey on super-resolution imaging
283 Citations2011Jing Tian, Kai‐Kuang Ma
This paper provides a comprehensive review of SR image and video reconstruction methods developed in the literature and highlights the future research challenges.
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.
IEEE Transactions on Medical ImagingA Supervised Patch-Based Approach for Human Brain Labeling
269 Citations2011François Rousseau, Piotr A. Habas +1 more
Experiments on simulated and in vivo magnetic resonance images show that the proposed patch-based image labeling method relying on a label propagation framework is very successful in providing automated human brain labeling.
CirculationOperator-Independent Isotropic Three-Dimensional Magnetic Resonance Imaging for Morphology in Congenital Heart Disease
179 Citations2004Thomas Sangild Sørensen, Hermann Körperich +6 more
In adolescents and adults, isotropic 3D SSFP MRI allows reliable assessment of complex cardiac morphology and may substitute for conventional 2D MRI sequences to accelerate and simplify MR scanning in congenital heart disease.
Medical Image AnalysisA non-local approach for image super-resolution using intermodality priors☆
157 Citations2010François Rousseau
This paper proposes an approach for image super-resolution by using anatomical intermodality priors from a reference image, and introduces a new regularization approach that uses an example-based framework integrating non-local similarity constraints to handle in a better way repetitive structures and texture.
Magnetic Resonance in MedicineWhole‐heart cine MRI using real‐time respiratory self‐gating
134 Citations2007Sergio Uribe, Vivek Muthurangu +5 more
The respiratory self‐gating technique is shown to improve image quality in free‐breathing scanning and enables assessment of cardiac anatomy and function with minimum planning or patient cooperation.
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.
RadiologyAccelerated Two- and Three-dimensional Cine MR Imaging of the Heart by Using a 32-Channel Coil
17 Citations2009Amir H. Davarpanah, Yu-Po Chen +8 more
Accelerated real-time 2D and segmented 3D cine techniques are comparable to the standard clinical protocol in assessment of left ventricular global and regional parameters in substantially shorter image times.
A groupwise super-resolution approach: Application to brain MRI
12 Citations2010François Rousseau, K. Kim +1 more
This paper develops regularization term which is designed to take advantage of information redundancy in the set of images to reconstructing a high resolution isotropic image when presented with a set of low-resolution anisotropic images.
Improving image registration by correspondence interpolation
3 Citations2011Hildur Ólafsdóttir, Henrik Pedersen +3 more
The results show that the interpolator provides better gradient images and a more sharp cardiac atlas and provides better deformation fields on downsampled data, increasing the registration accuracy of original data to 5.8% on average with respect to a standard interpolator.