Sparse representation-based MRI super-resolution reconstruction
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
TL;DR: A multi-scale SR network with dual attention is built to achieve the recovered results with more powerful feature expression and the generalized neural model exploits the data to enable the network in learning to enrich features of sparse data, which dramatically reduces the sampling time and increases measurement efficiency.
8 citations
TL;DR: In this article , a broadband model-based OAM (MB-OAM) framework was proposed to exploit scanning symmetries for an enhanced performance by capitalizing on the large detection bandwidth of a spherical polyvinylidene difluoride film while accurately accounting for its spatial impulse response.
Abstract: Optoacoustic mesoscopy (OAM) retrieves anatomical and functional contrast in vivo at depths not resolvable with optical microscopy. Recent progress on reconstruction algorithms have further advanced its imaging performance to provide high lateral resolution ultimately limited by acoustic diffraction. In this work, a new broadband model-based OAM (MB-OAM) framework efficiently exploiting scanning symmetries for an enhanced performance is presented. By capitalizing on the large detection bandwidth of a spherical polyvinylidene difluoride film while accurately accounting for its spatial impulse response, the new approach significantly outperforms standard OAM implementations in terms of contrast and resolution, as validated by functional in vivo experiments in mice and human volunteers. Furthermore, L1-norm regularization enables resolving structures separated by less than the theoretical diffraction-limited resolution. This unique label-free angiographic performance demonstrates the general applicability of MB-OAM as a super-resolution deep-tissue imaging method capable of breaking through the limits imposed by acoustic diffraction.
8 citations
13 Oct 2019
TL;DR: This work proposes the first framework for predicting high-resolution (HR) brain networks from low-dimensional (LR)brain networks by hierarchically aligning and embedding LR neighborhood centered at the testing sample, along with its corresponding HR neighborhood.
Abstract: Several works have been dedicated to image super-resolution (i.e., synthesizing high-resolution data from low-resolution data). However, existing works only operate on images (e.g., predicting 7T-like magnetic resonance image (MRI) from 3T MRI) whereas brain connectivity network super-resolution remains unexplored. To fill this gap, we propose the first framework for predicting high-resolution (HR) brain networks from low-dimensional (LR) brain networks by hierarchically aligning and embedding LR neighborhood centered at the testing sample, along with its corresponding HR neighborhood. The proposed hierarchical embedding better preserves higher-order structural neighborhood of subjects within each domain. Recently, a seminal work was introduced for brain network prediction at a single resolution (or scale), where domain alignment was achieved using canonical correlation analysis followed by manifold learning to identify the most similar neighbors to the testing subject (i.e., testing neighborhood) in the source domain that can best predict the missing target network. Here, we inductively extend this idea by hierarchically learning the embedding and alignment of embedding of LR and HR neighborhoods. Our proposed framework achieved the best results in comparison with baseline methods.
8 citations
TL;DR: Results show that the authors' reconstructions have advantages over rigid and conventional non-rigid registration-based super-resolution, in terms of the root-mean-square error and structure similarity, and improve the precision of brain automatic segmentation.
Abstract: Most of the recent leading multiple magnetic resonance imaging (MRI) super-resolution techniques for brain are limited to rigid motion. In this study, the authors aim to develop a super-resolution technique with diffeomorphism mainly for longitudinal brain MRI data. For the images from different time slots, unpredicted deformation may occur. In previous studies, sole rigid registration or traditional non-rigid registration has been frequently used to achieve multi-plane super-resolution. However, non-rigid motion of two brains from different time slots is difficult to model, since brain contains a wealth of complex structure such as the cerebral cortex. In order to address such problem, rigid and large diffeomorphic registration has been embedded into their super-resolution framework. In addition, many previous researchers use L 2 norm to achieve super-resolution framework. In this work, L 1 norm minimisation and regularisation based on a bilateral prior are adopted. These operations ensure its robustness to the assumed model of data and noise. Their approach is evaluated using Alzheimer datasets from seven different resolutions. Results show that their reconstructions have advantages over rigid and conventional non-rigid registration-based super-resolution, in terms of the root-mean-square error and structure similarity. Furthermore, their reconstruction results improve the precision of brain automatic segmentation.
7 citations
Posted Content•
TL;DR: This paper presents a novel channel splitting and serial fusion network (CSSFN) for single MR image super-resolution that splits the hierarchical features into a series of subfeatures, which are then integrated together in a serial manner and can deal with the subfeatures on different channels discriminatively.
Abstract: Spatial resolution is a critical imaging parameter in magnetic resonance imaging (MRI). Acquiring high resolution MRI data usually takes long scanning time and would subject to motion artifacts due to hardware, physical, and physiological limitations. Single image super-resolution (SISR), especially that based on deep learning techniques, is an effective and promising alternative technique to improve the current spatial resolution of magnetic resonance (MR) images. However, the deeper network is more difficult to be effectively trained because the information is gradually weakened as the network deepens. This problem becomes more serious for medical images due to the degradation of training examples. In this paper, we present a novel channel splitting and serial fusion network (CSSFN) for single MR image super-resolution. Specifically, the proposed CSSFN network splits the hierarchical features into a series of subfeatures, which are then integrated together in a serial manner. Thus, the network becomes deeper and can deal with the subfeatures on different channels discriminatively. Besides, a dense global feature fusion (DGFF) is adopted to integrate the intermediate features, which further promotes the information flow in the network. Extensive experiments on several typical MR images show the superiority of our CSSFN model over other advanced SISR methods.
7 citations
Cites background or methods from "Sparse representation-based MRI sup..."
..., sparse representation [16], [18], example learning [45], [46], as well as compressive sensing [47] etc....
[...]
..., interpolation-based and edge-guided methods [4], [5], [6], [7], modeling and reconstruction based methods [8], [9], [14], [15], example learning based methods [10], [11], and dictionary learning and sparse representation methods [12], [13], [16], [18] etc....
[...]
References
More filters
TL;DR: A novel algorithm for adapting dictionaries in order to achieve sparse signal representations, the K-SVD algorithm, an iterative method that alternates between sparse coding of the examples based on the current dictionary and a process of updating the dictionary atoms to better fit the data.
Abstract: In recent years there has been a growing interest in the study of sparse representation of signals. Using an overcomplete dictionary that contains prototype signal-atoms, signals are described by sparse linear combinations of these atoms. Applications that use sparse representation are many and include compression, regularization in inverse problems, feature extraction, and more. Recent activity in this field has concentrated mainly on the study of pursuit algorithms that decompose signals with respect to a given dictionary. Designing dictionaries to better fit the above model can be done by either selecting one from a prespecified set of linear transforms or adapting the dictionary to a set of training signals. Both of these techniques have been considered, but this topic is largely still open. In this paper we propose a novel algorithm for adapting dictionaries in order to achieve sparse signal representations. Given a set of training signals, we seek the dictionary that leads to the best representation for each member in this set, under strict sparsity constraints. We present a new method-the K-SVD algorithm-generalizing the K-means clustering process. K-SVD is an iterative method that alternates between sparse coding of the examples based on the current dictionary and a process of updating the dictionary atoms to better fit the data. The update of the dictionary columns is combined with an update of the sparse representations, thereby accelerating convergence. The K-SVD algorithm is flexible and can work with any pursuit method (e.g., basis pursuit, FOCUSS, or matching pursuit). We analyze this algorithm and demonstrate its results both on synthetic tests and in applications on real image data
8,905 citations
TL;DR: This paper presents a new approach to single-image superresolution, based upon sparse signal representation, which generates high-resolution images that are competitive or even superior in quality to images produced by other similar SR methods.
Abstract: This paper presents a new approach to single-image superresolution, based upon sparse signal representation. Research on image statistics suggests that image patches can be well-represented as a sparse linear combination of elements from an appropriately chosen over-complete dictionary. Inspired by this observation, we seek a sparse representation for each patch of the low-resolution input, and then use the coefficients of this representation to generate the high-resolution output. Theoretical results from compressed sensing suggest that under mild conditions, the sparse representation can be correctly recovered from the downsampled signals. By jointly training two dictionaries for the low- and high-resolution image patches, we can enforce the similarity of sparse representations between the low-resolution and high-resolution image patch pair with respect to their own dictionaries. Therefore, the sparse representation of a low-resolution image patch can be applied with the high-resolution image patch dictionary to generate a high-resolution image patch. The learned dictionary pair is a more compact representation of the patch pairs, compared to previous approaches, which simply sample a large amount of image patch pairs , reducing the computational cost substantially. The effectiveness of such a sparsity prior is demonstrated for both general image super-resolution (SR) and the special case of face hallucination. In both cases, our algorithm generates high-resolution images that are competitive or even superior in quality to images produced by other similar SR methods. In addition, the local sparse modeling of our approach is naturally robust to noise, and therefore the proposed algorithm can handle SR with noisy inputs in a more unified framework.
4,958 citations
24 Jun 2010
TL;DR: This paper deals with the single image scale-up problem using sparse-representation modeling, and assumes a local Sparse-Land model on image patches, serving as regularization, to recover an original image from its blurred and down-scaled noisy version.
Abstract: This paper deals with the single image scale-up problem using sparse-representation modeling. The goal is to recover an original image from its blurred and down-scaled noisy version. Since this problem is highly ill-posed, a prior is needed in order to regularize it. The literature offers various ways to address this problem, ranging from simple linear space-invariant interpolation schemes (e.g., bicubic interpolation), to spatially-adaptive and non-linear filters of various sorts. We embark from a recently-proposed successful algorithm by Yang et. al. [1,2], and similarly assume a local Sparse-Land model on image patches, serving as regularization. Several important modifications to the above-mentioned solution are introduced, and are shown to lead to improved results. These modifications include a major simplification of the overall process both in terms of the computational complexity and the algorithm architecture, using a different training approach for the dictionary-pair, and introducing the ability to operate without a training-set by boot-strapping the scale-up task from the given low-resolution image. We demonstrate the results on true images, showing both visual and PSNR improvements.
2,667 citations
19 Jul 2004
TL;DR: This paper proposes a novel method for solving single-image super-resolution problems, given a low-resolution image as input, and recovers its high-resolution counterpart using a set of training examples, inspired by recent manifold teaming methods.
Abstract: In this paper, we propose a novel method for solving single-image super-resolution problems. Given a low-resolution image as input, we recover its high-resolution counterpart using a set of training examples. While this formulation resembles other learning-based methods for super-resolution, our method has been inspired by recent manifold teaming methods, particularly locally linear embedding (LLE). Specifically, small image patches in the lowand high-resolution images form manifolds with similar local geometry in two distinct feature spaces. As in LLE, local geometry is characterized by how a feature vector corresponding to a patch can be reconstructed by its neighbors in the feature space. Besides using the training image pairs to estimate the high-resolution embedding, we also enforce local compatibility and smoothness constraints between patches in the target high-resolution image through overlapping. Experiments show that our method is very flexible and gives good empirical results.
1,951 citations
22 Apr 2010
TL;DR: This paper surveys the various options such training has to offer, up to the most recent contributions and structures of the MOD, the K-SVD, the Generalized PCA and others.
Abstract: Sparse and redundant representation modeling of data assumes an ability to describe signals as linear combinations of a few atoms from a pre-specified dictionary. As such, the choice of the dictionary that sparsifies the signals is crucial for the success of this model. In general, the choice of a proper dictionary can be done using one of two ways: i) building a sparsifying dictionary based on a mathematical model of the data, or ii) learning a dictionary to perform best on a training set. In this paper we describe the evolution of these two paradigms. As manifestations of the first approach, we cover topics such as wavelets, wavelet packets, contourlets, and curvelets, all aiming to exploit 1-D and 2-D mathematical models for constructing effective dictionaries for signals and images. Dictionary learning takes a different route, attaching the dictionary to a set of examples it is supposed to serve. From the seminal work of Field and Olshausen, through the MOD, the K-SVD, the Generalized PCA and others, this paper surveys the various options such training has to offer, up to the most recent contributions and structures.
1,345 citations