scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Sparse representation-based MRI super-resolution reconstruction

01 Jan 2014-Measurement (Elsevier)-Vol. 47, pp 946-953
TL;DR: A novel dictionary training method for sparse reconstruction for enhancing the similarity of sparse representations between the low resolution and high resolution MRI block pairs through simultaneous training two dictionaries.
About: This article is published in Measurement.The article was published on 2014-01-01. It has received 73 citations till now. The article focuses on the topics: Real-time MRI & Sparse approximation.
Citations
More filters
Journal ArticleDOI
Linwei Yue1, Huanfeng Shen1, Jie Li1, Qiangqiang Yuan1, Hongyan Zhang1, Liangpei Zhang1 
TL;DR: This paper aims to provide a review of SR from the perspective of techniques and applications, and especially the main contributions in recent years, and discusses the current obstacles for future research.

378 citations

Journal ArticleDOI
17 Jun 2014
TL;DR: The working principles, applications, merits, and demerits of these methods has been discussed in detail along with their other technical issues followed by present status and future trends.
Abstract: Under the alternating electrical excitation, biological tissues produce a complex electrical impedance which depends on tissue composition, structures, health status, and applied signal frequency, and hence the bioelectrical impedance methods can be utilized for noninvasive tissue characterization. As the impedance responses of these tissue parameters vary with frequencies of the applied signal, the impedance analysis conducted over a wide frequency band provides more information about the tissue interiors which help us to better understand the biological tissues anatomy, physiology, and pathology. Over past few decades, a number of impedance based noninvasive tissue characterization techniques such as bioelectrical impedance analysis (BIA), electrical impedance spectroscopy (EIS), electrical impedance plethysmography (IPG), impedance cardiography (ICG), and electrical impedance tomography (EIT) have been proposed and a lot of research works have been conducted on these methods for noninvasive tissue characterization and disease diagnosis. In this paper BIA, EIS, IPG, ICG, and EIT techniques and their applications in different fields have been reviewed and technical perspective of these impedance methods has been presented. The working principles, applications, merits, and demerits of these methods has been discussed in detail along with their other technical issues followed by present status and future trends.

281 citations

Journal ArticleDOI
TL;DR: To develop a super‐resolution technique using convolutional neural networks for generating thin‐slice knee MR images from thicker input slices, and compare this method with alternative through‐plane interpolation methods.
Abstract: PURPOSE To develop a super-resolution technique using convolutional neural networks for generating thin-slice knee MR images from thicker input slices, and compare this method with alternative through-plane interpolation methods. METHODS We implemented a 3D convolutional neural network entitled DeepResolve to learn residual-based transformations between high-resolution thin-slice images and lower-resolution thick-slice images at the same center locations. DeepResolve was trained using 124 double echo in steady-state (DESS) data sets with 0.7-mm slice thickness and tested on 17 patients. Ground-truth images were compared with DeepResolve, clinically used tricubic interpolation, and Fourier interpolation methods, along with state-of-the-art single-image sparse-coding super-resolution. Comparisons were performed using structural similarity, peak SNR, and RMS error image quality metrics for a multitude of thin-slice downsampling factors. Two musculoskeletal radiologists ranked the 3 data sets and reviewed the diagnostic quality of the DeepResolve, tricubic interpolation, and ground-truth images for sharpness, contrast, artifacts, SNR, and overall diagnostic quality. Mann-Whitney U tests evaluated differences among the quantitative image metrics, reader scores, and rankings. Cohen's Kappa (κ) evaluated interreader reliability. RESULTS DeepResolve had significantly better structural similarity, peak SNR, and RMS error than tricubic interpolation, Fourier interpolation, and sparse-coding super-resolution for all downsampling factors (p < .05, except 4 × and 8 × sparse-coding super-resolution downsampling factors). In the reader study, DeepResolve significantly outperformed (p < .01) tricubic interpolation in all image quality categories and overall image ranking. Both readers had substantial scoring agreement (κ = 0.73). CONCLUSION DeepResolve was capable of resolving high-resolution thin-slice knee MRI from lower-resolution thicker slices, achieving superior quantitative and qualitative diagnostic performance to both conventionally used and state-of-the-art methods.

243 citations


Cites methods from "Sparse representation-based MRI sup..."

  • ...We quantitatively compare the various resolution-enhancement methods using image quality metrics and qualitatively compare the methods through a reader study to evaluate the diagnostic potential of DeepResolve....

    [...]

  • ...An L2 loss function was chosen for DeepResolve....

    [...]

  • ...Such methods could also be especially useful for newer implementations of DESS that enable simultaneous T2 relaxometry, morphometry, and semiquantitative radiological assessment.47 The thicker slices could be used for generating high-SNR for quantitative T2 measurements, whereas the thin slices could be used for accurate morphometry and semi-quantitative whole-joint assessment.48 Bilateral knee imaging methods that acquire several hundred slices could also benefit from DeepResolve.49 The training data for DeepResolve consisted of 34% of patients with a KL OA grade of 2 and 59% of patients of grade 3....

    [...]

  • ...In addition to the TCI image inputs to DeepResolve, we also generated FI images from the simulated thick-slice images.37,38 For comparing against a state-of-the-art single MR image superresolution method, we generated ScSR images for the same 3443 3443 160 imaging volume as DeepResolve.22 The ScSR method creates sparse residual images using a 2D patch-based dictionary approach that iteratively tries to enhance low-resolution features based on image pairs of low resolution and high resolution (detailed description in Supporting Information)....

    [...]

  • ...For comparing against a state-of-the-art single MR image superresolution method, we generated ScSR images for the same 3443 3443 160 imaging volume as DeepResolve.(22) The ScSR method creates sparse residual images using a 2D patch-based dictionary approach that iteratively tries to enhance low-resolution features based on image pairs of low resolution and high resolution (detailed description in Supporting Information)....

    [...]

Journal ArticleDOI
TL;DR: A graph-based redundant wavelet transform is introduced to sparsely represent magnetic resonance images in iterative image reconstructions and outperforms several state-of-the-art reconstruction methods in removing artifacts and achieves fewer reconstruction errors on the tested datasets.

150 citations


Cites background from "Sparse representation-based MRI sup..."

  • ...In general, three requirements exist in a successful CS application: sparse representation (Wang et al., 2014; Zhang et al., 2012), incoherent undersampling artifacts (Greiser and von Kienlin, 2003; Tsai and Nishimura, 2000), and an effective nonlinear reconstruction algorithm (Aelterman et al.,…...

    [...]

Journal ArticleDOI
TL;DR: Experimental results show that the proposed deep convolutional neural network model outperforms state-of-the-art MRI super-resolution methods in terms of visual quality and objective quality criteria such as peak signal-to-noise ratio and structural similarity.

96 citations

References
More filters
Journal ArticleDOI
TL;DR: A missing image data reconstruction method based on an adaptive inverse projection via sparse representation using low-dimensional subspaces that approximate target textures including missing areas to solve the problem of not being able to directly estimate missing intensities.
Abstract: In this paper, a missing image data reconstruction method based on an adaptive inverse projection via sparse representation is proposed. The proposed method utilizes sparse representation for obtaining low-dimensional subspaces that approximate target textures including missing areas. Then, by using the obtained low-dimensional subspaces, inverse projection for reconstructing missing areas can be derived to solve the problem of not being able to directly estimate missing intensities. Furthermore, in this approach, the proposed method monitors errors caused by the derived inverse projection, and the low-dimensional subspaces optimal for target textures are adaptively selected. Therefore, we can apply adaptive inverse projection via sparse representation to target missing textures, i.e., their adaptive reconstruction becomes feasible. The proposed method also introduces some schemes for color processing into the calculation of subspaces on the basis of sparse representation and attempts to avoid spurious color caused in the reconstruction results. Consequently, successful reconstruction of missing areas by the proposed method can be expected. Experimental results show impressive improvement of our reconstruction method over previously reported reconstruction methods.

22 citations

01 Jan 2011
TL;DR: The ultrasound screening of placenta in the initial stages of gestation helps to identify the complication induced by GDM on the placental development which accounts for the fetal growth.
Abstract: Medical diagnosis is the major challenge faced by the medical experts. Highly specialized tools are necessary to assist the experts in diagnosing the diseases. Gestational Diabetes Mellitus is a condition in pregnant women which increases the blood sugar levels. It complicates the pregnancy by affecting the placental growth. The ultrasound screening of placenta in the initial stages of gestation helps to identify the complication induced by GDM on the placental development which accounts for the fetal growth. This work focus on the classification of ultrasound placenta images into normal and abnormal images based on statistical measurements. The ultrasound images are usually low in resolution which may lead to loss of characteristic features of the ultrasound images. The placenta images obtained in an ultrasound examination is stereo mapped to reconstruct the placenta structure from the ultrasound images. The dimensionality reduction is done on stereo mapped placenta images using wavelet decomposition. The ultrasound placenta image is segmented using watershed approach to obtain the statistical measurements of the stereo mapped placenta images. Using the statistical measurements, the ultrasound placenta images are then classified as normal and abnormal using Back Propagation neural networks.

16 citations

Journal ArticleDOI
C.Y. Peng1, J.W. Li1
TL;DR: It is shown that the l 1 -norm minimisation problem can be reduced from a large and dense linear system to a small and sparse one and proposed is a fast sparse representation model (FSRM) that exploits the property.
Abstract: To solve the l1-norm minimisation problem, many algorithms, such as the l1-Magic solver, utilise the conjugate gradient (CG) method to speed up implementation. Since the dictionary employed by CG is often dense in ‘large-scale’ mode, the time complexities of these algorithms remain significantly high. As signals can be modelled by a small set of atoms in a dictionary, proposed is a fast sparse representation model (FSRM) that exploits the property and it is shown that the l1-norm minimisation problem can be reduced from a large and dense linear system to a small and sparse one. Experimental results with image recognition demonstrate that the FSRM is able to achieve double-digit gain in speed with comparable accuracy compared with the l1-Magic solver.

10 citations