Dataset Information

A New Sparse Representation Framework for Reconstruction of an Isotropic High Spatial Resolution MR Volume From Orthogonal Anisotropic Resolution Scans.

ABSTRACT: In magnetic resonance (MR), hardware limitations, scan time constraints, and patient movement often result in the acquisition of anisotropic 3-D MR images with limited spatial resolution in the out-of-plane views. Our goal is to construct an isotropic high-resolution (HR) 3-D MR image through upsampling and fusion of orthogonal anisotropic input scans. We propose a multiframe super-resolution (SR) reconstruction technique based on sparse representation of MR images. Our proposed algorithm exploits the correspondence between the HR slices and the low-resolution (LR) sections of the orthogonal input scans as well as the self-similarity of each input scan to train pairs of overcomplete dictionaries that are used in a sparse-land local model to upsample the input scans. The upsampled images are then combined using wavelet fusion and error backprojection to reconstruct an image. Features are learned from the data and no extra training set is needed. Qualitative and quantitative analyses were conducted to evaluate the proposed algorithm using simulated and clinical MR scans. Experimental results show that the proposed algorithm achieves promising results in terms of peak signal-to-noise ratio, structural similarity image index, intensity profiles, and visualization of small structures obscured in the LR imaging process due to partial volume effects. Our novel SR algorithm outperforms the nonlocal means (NLM) method using self-similarity, NLM method using self-similarity and image prior, self-training dictionary learning-based SR method, averaging of upsampled scans, and the wavelet fusion method. Our SR algorithm can reduce through-plane partial volume artifact by combining multiple orthogonal MR scans, and thus can potentially improve medical image analysis, research, and clinical diagnosis.

SUBMITTER: Jia Y

PROVIDER: S-EPMC5534179 | biostudies-literature | 2017 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A New Sparse Representation Framework for Reconstruction of an Isotropic High Spatial Resolution MR Volume From Orthogonal Anisotropic Resolution Scans.

Jia Yuanyuan Y Gholipour Ali A He Zhongshi Z Warfield Simon K SK

IEEE transactions on medical imaging 20170123 5

In magnetic resonance (MR), hardware limitations, scan time constraints, and patient movement often result in the acquisition of anisotropic 3-D MR images with limited spatial resolution in the out-of-plane views. Our goal is to construct an isotropic high-resolution (HR) 3-D MR image through upsampling and fusion of orthogonal anisotropic input scans. We propose a multiframe super-resolution (SR) reconstruction technique based on sparse representation of MR images. Our proposed algorithm exploi ...[more]

PMID: 28129152

Similar Datasets

Project description:PurposeTo evaluate the use of low-dimensional-structure self-learning and thresholding (LOST) compressed sensing acquisition and reconstruction in the assessment of left atrial (LA) and left ventricular (LV) scar by using late gadolinium enhancement (LGE) magnetic resonance (MR) imaging with isotropic spatial resolution.Materials and methodsThe study was approved by the local institutional review board and was compliant with HIPAA. All subjects provided written informed consent. Twenty-eight patients (eight women; mean age, 58.0 years ± 10.1) with a history of atrial fibrillation were recruited for the LA LGE study, and 14 patients (five women; mean age, 54.2 years ± 18.6) were recruited for assessment of LV myocardial infarction. With use of a pseudorandom k-space undersampling pattern, threefold accelerated three-dimensional (3D) LGE data were acquired with isotropic spatial resolution and reconstructed off-line by using LOST. For comparison, subjects were also imaged by using standard 3D LGE protocols with nonisotropic spatial resolution. Images were compared qualitatively by three cardiologists with regard to diagnostic value, presence of enhancement, and image quality. The signed rank test and Wilcoxon unpaired two-sample test were used to test the hypothesis that there would be no significant difference in image quality ratings with different resolutions.ResultsInterpretable images were obtained in 26 of the 28 patients (93%) in the LA LGE study. LGE was seen in 17 of 30 cases (57%) with nonisotropic resolution and in 18 cases (60%) with isotropic resolution. Diagnostic quality scores of isotropic images were significantly higher than those of nonisotropic images with coronal views (median, 3 vs 2, respectively [25th and 75th percentiles: 3, 3 vs 2, 3]; P < .001) and sagittal views (median, 3 vs 2 [25th and 75th percentiles: 3, 4 vs 2, 3]; P < .001) but lower with axial views (median, 4 vs 3 [25th and 75th percentiles: 3, 4 vs 3, 3]; P < .001). For the LV LGE study, all patients had interpretable images. LGE was seen in six of 14 patients (43%), with 100% agreement between both data sets. Diagnostic quality scores of high-isotropic-resolution LV images were higher than those of nonisotropic images with short-axis views (median, 4 vs 3 [25th and 75th percentiles: 3, 4 vs 2, 3]; P = .014) and two-chamber views (median, 4 vs 3 [25th and 75th percentiles: 3, 4 vs 2, 3]; P = .001).ConclusionAn accelerated LGE acquisition with LOST enables imaging with high isotropic spatial resolution for improved assessment of LV, LA, and pulmonary vein scar.

Project description:Most existing algorithms for automatic 3D morphometry of human brain MRI scans are designed for data with near-isotropic voxels at approximately 1 mm resolution, and frequently have contrast constraints as well-typically requiring T1-weighted images (e.g., MP-RAGE scans). This limitation prevents the analysis of millions of MRI scans acquired with large inter-slice spacing in clinical settings every year. In turn, the inability to quantitatively analyze these scans hinders the adoption of quantitative neuro imaging in healthcare, and also precludes research studies that could attain huge sample sizes and hence greatly improve our understanding of the human brain. Recent advances in convolutional neural networks (CNNs) are producing outstanding results in super-resolution and contrast synthesis of MRI. However, these approaches are very sensitive to the specific combination of contrast, resolution and orientation of the input images, and thus do not generalize to diverse clinical acquisition protocols - even within sites. In this article, we present SynthSR, a method to train a CNN that receives one or more scans with spaced slices, acquired with different contrast, resolution and orientation, and produces an isotropic scan of canonical contrast (typically a 1 mm MP-RAGE). The presented method does not require any preprocessing, beyond rigid coregistration of the input scans. Crucially, SynthSR trains on synthetic input images generated from 3D segmentations, and can thus be used to train CNNs for any combination of contrasts, resolutions and orientations without high-resolution real images of the input contrasts. We test the images generated with SynthSR in an array of common downstream analyses, and show that they can be reliably used for subcortical segmentation and volumetry, image registration (e.g., for tensor-based morphometry), and, if some image quality requirements are met, even cortical thickness morphometry. The source code is publicly available at https://github.com/BBillot/SynthSR.

Dataset Information

A New Sparse Representation Framework for Reconstruction of an Isotropic High Spatial Resolution MR Volume From Orthogonal Anisotropic Resolution Scans.

Publications

A New Sparse Representation Framework for Reconstruction of an Isotropic High Spatial Resolution MR Volume From Orthogonal Anisotropic Resolution Scans.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets