Denoising Diffusion MRI via Graph Total Variance in Spatioangular Domain.
Ontology highlight
ABSTRACT:
SUBMITTER: Wu H
PROVIDER: S-EPMC8670899 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Diffusion magnetic resonance imaging (DMRI) suffers from lower signal-to-noise-ratio (SNR) due to MR signal attenuation associated with the motion of water molecules. To improve SNR, the non-local means (NLM) algorithm has demonstrated state-of-the-art performance in noise reduction. However, existing NLM algorithms do not take into account explicitly the fact that DMRI signal can vary significantly with local fiber orientations. Applying NLM naïvely can hence blur subtle structures and aggravate partial volume effects. To overcome this limitation, we improve NLM by performing neighborhood matching in non-flat domains and removing noise with information from both x -space (spatial domain) and q -space (wavevector domain). Specifically, we first encode the q -space sampling domain using a graph. We then perform graph framelet transforms to extract robust rotation-invariant features for each sampling point in x-q space. The resulting features are employed for robust neighborhood matching to locate recurrent information. Finally, we remove noise via an NLM framework. To adapt to the various types of noise in multi-coil MR imaging, we transform the signal before denoising so that it is Gaussian-distributed, allowing noise removal to be carried out in an unbiased manner. Our method is able to more effectively locate recurrent information in white matter structures with different orientations, avoiding the blurring effects caused by naïvely applying NLM. Experiments on synthetic, repetitively-acquired, and infant DMRI data demonstrate that our method is able to preserve subtle structures while effectively removing noise.
| S-EPMC8325050 | biostudies-literature
Project description:Total variation (TV) based models are very popular in image denoising but suffer from some drawbacks. For example, local TV methods often cannot preserve edges and textures well when they face excessive smoothing. Non-local TV methods constitute an alternative, but their computational cost is huge. To overcome these issues, we propose an image denoising method named non-local patch graph total variation (NPGTV). Its main originality stands for the graph total variation method, which combines the total variation with graph signal processing. Schematically, we first construct a K-nearest graph from the original image using a non-local patch-based method. Then the model is solved with the Douglas-Rachford Splitting algorithm. By doing so, the image details can be well preserved while being denoised. Experiments conducted on several standard natural images illustrate the effectiveness of our method when compared to some other state-of-the-art denoising methods like classical total variation, non-local means filter (NLM), non-local graph based transform (NLGBT), adaptive graph-based total variation (AGTV).
| S-EPMC6907757 | biostudies-literature
Project description:Missing data is a common problem in longitudinal studies due to subject dropouts and failed scans. We present a graph-based convolutional neural network to predict missing diffusion MRI data. In particular, we consider the relationships between sampling points in the spatial domain and the diffusion wave-vector domain to construct a graph. We then use a graph convolutional network to learn the non-linear mapping from available data to missing data. Our method harnesses a multi-scale residual architecture with adversarial learning for prediction with greater accuracy and perceptual quality. Experimental results show that our method is accurate and robust in the longitudinal prediction of infant brain diffusion MRI data.
| S-EPMC6935161 | biostudies-literature
Project description:BackgroundAutomated segmentation of spinal magnetic resonance imaging (MRI) plays a vital role both scientifically and clinically. However, accurately delineating posterior spine structures is challenging.MethodsThis retrospective study, approved by the ethical committee, involved translating T1-weighted and T2-weighted images into computed tomography (CT) images in a total of 263 pairs of CT/MR series. Landmark-based registration was performed to align image pairs. We compared two-dimensional (2D) paired - Pix2Pix, denoising diffusion implicit models (DDIM) image mode, DDIM noise mode - and unpaired (SynDiff, contrastive unpaired translation) image-to-image translation using "peak signal-to-noise ratio" as quality measure. A publicly available segmentation network segmented the synthesized CT datasets, and Dice similarity coefficients (DSC) were evaluated on in-house test sets and the "MRSpineSeg Challenge" volumes. The 2D findings were extended to three-dimensional (3D) Pix2Pix and DDIM.Results2D paired methods and SynDiff exhibited similar translation performance and DCS on paired data. DDIM image mode achieved the highest image quality. SynDiff, Pix2Pix, and DDIM image mode demonstrated similar DSC (0.77). For craniocaudal axis rotations, at least two landmarks per vertebra were required for registration. The 3D translation outperformed the 2D approach, resulting in improved DSC (0.80) and anatomically accurate segmentations with higher spatial resolution than that of the original MRI series.ConclusionsTwo landmarks per vertebra registration enabled paired image-to-image translation from MRI to CT and outperformed all unpaired approaches. The 3D techniques provided anatomically correct segmentations, avoiding underprediction of small structures like the spinous process.Relevance statementThis study addresses the unresolved issue of translating spinal MRI to CT, making CT-based tools usable for MRI data. It generates whole spine segmentation, previously unavailable in MRI, a prerequisite for biomechanical modeling and feature extraction for clinical applications.Key points• Unpaired image translation lacks in converting spine MRI to CT effectively. • Paired translation needs registration with two landmarks per vertebra at least. • Paired image-to-image enables segmentation transfer to other domains. • 3D translation enables super resolution from MRI to CT. • 3D translation prevents underprediction of small structures.
| S-EPMC10643734 | biostudies-literature
Project description:BackgroundMulti-b-valued/multi-shell diffusion provides potentially valuable metrics in breast MRI but suffers from low signal-to-noise ratio and has potentially long scan times.PurposeTo investigate the effects of model-based denoising with no loss of spatial resolution on multi-shell breast diffusion MRI; to determine the effects of downsampling on multi-shell diffusion; and to quantify these effects in multi-b-valued (three directions per b-value) acquisitions.Study typeProspective ("fully-sampled" multi-shell) and retrospective longitudinal (multi-b).SubjectsOne normal subject (multi-shell) and 10 breast cancer subjects imaging at four timepoints (multi-b).Field strength/sequence3T multi-shell acquisition and 1.5T multi-b acquisition.AssessmentThe "fully-sampled" multi-shell acquisition was retrospectively downsampled to determine the bias and error from downsampling. Mean, axial/parallel, radial diffusivity, and fractional anisotropy (FA) were analyzed. Denoising was applied retrospectively to the multi-b-valued breast cancer subject dataset and assessed subjectively for image noise level and tumor conspicuity.Statistical testsParametric paired t-test (P < 0.05 considered statistically significant) on mean and coefficient of variation of each metric-the apparent diffusion coefficient (ADC) from all b-values, fast ADC, slow ADC, and perfusion fraction. Paired and two-sample t-tests for each metric comparing normal and tumor tissue.ResultsIn the multi-shell data, denoising effectively suppressed FA (-45% to -78%), with small biases in mean diffusivity (-5% in normal, +23% in tumor, and -4% in vascular compartments). In the multi-b data, denoising resulted in small biases to the ADC metrics in tumor and normal contralateral tissue (by -3% to +11%), but greatly reduced the coefficient of variation for every metric (by -1% to -24%). Denoising improved differentiation of tumor and normal tissue regions in most metrics and timepoints; subjectively, image noise level and tumor conspicuity were improved in the fast ADC maps.Data conclusionModel-based denoising effectively suppressed erroneously high FA and improved the accuracy of diffusivity metrics.Evidence level3 TECHNICAL EFFICACY STAGE: 1.
| S-EPMC8406040 | biostudies-literature
Project description:Over the past several years, significant efforts have been made to improve the spatial resolution of diffusion-weighted imaging (DWI), aiming at better detecting subtle lesions and more reliably resolving white-matter fiber tracts. A major concern with high-resolution DWI is the limited signal-to-noise ratio (SNR), which may significantly offset the advantages of high spatial resolution. Although the SNR of DWI data can be improved by denoising in post-processing, existing denoising procedures may potentially reduce the anatomic resolvability of high-resolution imaging data. Additionally, non-Gaussian noise induced signal bias in low-SNR DWI data may not always be corrected with existing denoising approaches. Here we report an improved denoising procedure, termed diffusion-matched principal component analysis (DM-PCA), which comprises 1) identifying a group of (not necessarily neighboring) voxels that demonstrate very similar magnitude signal variation patterns along the diffusion dimension, 2) correcting low-frequency phase variations in complex-valued DWI data, 3) performing PCA along the diffusion dimension for real- and imaginary-components (in two separate channels) of phase-corrected DWI voxels with matched diffusion properties, 4) suppressing the noisy PCA components in real- and imaginary-components, separately, of phase-corrected DWI data, and 5) combining real- and imaginary-components of denoised DWI data. Our data show that the new two-channel (i.e., for real- and imaginary-components) DM-PCA denoising procedure performs reliably without noticeably compromising anatomic resolvability. Non-Gaussian noise induced signal bias could also be reduced with the new denoising method. The DM-PCA based denoising procedure should prove highly valuable for high-resolution DWI studies in research and clinical uses.
| S-EPMC5918820 | biostudies-literature
Project description:PurposeTo introduce, develop, and evaluate a novel denoising technique for diffusion MRI that leverages nonlinear redundancy in the data to boost the SNR while preserving signal information.MethodsWe exploit nonlinear redundancy of the dMRI data by means of kernel principal component analysis (KPCA), a nonlinear generalization of PCA to reproducing kernel Hilbert spaces. By mapping the signal to a high-dimensional space, a higher level of redundant information is exploited, thereby enabling better denoising than linear PCA. We implement KPCA with a Gaussian kernel, with parameters automatically selected from knowledge of the noise statistics, and validate it on realistic Monte Carlo simulations as well as with in vivo human brain submillimeter and low-resolution dMRI data. We also demonstrate KPCA denoising on multi-coil dMRI data.ResultsSNR improvements up to 2.7 × were obtained in real in vivo datasets denoised with KPCA, in comparison to SNR gains of up to 1.8 × using a linear PCA denoising technique called Marchenko-Pastur PCA (MPPCA). Compared to gold-standard dataset references created from averaged data, we showed that lower normalized root mean squared error was achieved with KPCA compared to MPPCA. Statistical analysis of residuals shows that anatomical information is preserved and only noise is removed. Improvements in the estimation of diffusion model parameters such as fractional anisotropy, mean diffusivity, and fiber orientation distribution functions were also demonstrated.ConclusionNonlinear redundancy of the dMRI signal can be exploited with KPCA, which allows superior noise reduction/SNR improvements than the MPPCA method, without loss of signal information.
| S-EPMC8497014 | biostudies-literature
Project description:PurposeTo investigate the feasibility of accelerating prostate diffusion-weighted imaging (DWI) by reducing the number of acquired averages and denoising the resulting image using a proposed guided denoising convolutional neural network (DnCNN).Materials and methodsRaw data from the prostate DWI scans were retrospectively gathered between July 2018 and July 2019 from six single-vendor MRI scanners. There were 103 datasets used for training (median age, 64 years; interquartile range [IQR], 11), 15 for validation (median age, 68 years; IQR, 12), and 37 for testing (median age, 64 years; IQR, 12). High b-value diffusion-weighted (hb DW) data were reconstructed into noisy images using two averages and reference images using all 16 averages. A conventional DnCNN was modified into a guided DnCNN, which uses the low b-value DW image as a guidance input. Quantitative and qualitative reader evaluations were performed on the denoised hb DW images. A cumulative link mixed regression model was used to compare the readers' scores. The agreement between the apparent diffusion coefficient (ADC) maps (denoised vs reference) was analyzed using Bland-Altman analysis.ResultsCompared with the original DnCNN, the guided DnCNN produced denoised hb DW images with higher peak signal-to-noise ratio (32.79 ± 3.64 [standard deviation] vs 33.74 ± 3.64), higher structural similarity index (0.92 ± 0.05 vs 0.93 ± 0.04), and lower normalized mean square error (3.9% ± 10 vs 1.6% ± 1.5) (P < .001 for all). Compared with the reference images, the denoised images received higher image quality scores from the readers (P < .0001). The ADC values based on the denoised hb DW images were in good agreement with the reference ADC values (mean ADC difference ranged from -0.04 to 0.02 × 10-3 mm2/sec).ConclusionAccelerating prostate DWI by reducing the number of acquired averages and denoising the resulting image using the proposed guided DnCNN is technically feasible. Supplemental material is available for this article. © RSNA, 2020.
| S-EPMC7529434 | biostudies-literature
Project description:MotivationSingle-cell RNA sequencing (scRNA-seq) is an increasingly popular technique for transcriptomic analysis of gene expression at the single-cell level. Cell-type clustering is the first crucial task in the analysis of scRNA-seq data that facilitates accurate identification of cell types and the study of the characteristics of their transcripts. Recently, several computational models based on a deep autoencoder and the ensemble clustering have been developed to analyze scRNA-seq data. However, current deep autoencoders are not sufficient to learn the latent representations of scRNA-seq data, and obtaining consensus partitions from these feature representations remains under-explored.ResultsTo address this challenge, we propose a single-cell deep clustering model via a dual denoising autoencoder with bipartite graph ensemble clustering called scBGEDA, to identify specific cell populations in single-cell transcriptome profiles. First, a single-cell dual denoising autoencoder network is proposed to project the data into a compressed low-dimensional space and that can learn feature representation via explicit modeling of synergistic optimization of the zero-inflated negative binomial reconstruction loss and denoising reconstruction loss. Then, a bipartite graph ensemble clustering algorithm is designed to exploit the relationships between cells and the learned latent embedded space by means of a graph-based consensus function. Multiple comparison experiments were conducted on 20 scRNA-seq datasets from different sequencing platforms using a variety of clustering metrics. The experimental results indicated that scBGEDA outperforms other state-of-the-art methods on these datasets, and also demonstrated its scalability to large-scale scRNA-seq datasets. Moreover, scBGEDA was able to identify cell-type specific marker genes and provide functional genomic analysis by quantifying the influence of genes on cell clusters, bringing new insights into identifying cell types and characterizing the scRNA-seq data from different perspectives.Availability and implementationThe source code of scBGEDA is available at https://github.com/wangyh082/scBGEDA. The software and the supporting data can be downloaded from https://figshare.com/articles/software/scBGEDA/19657911.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC9925104 | biostudies-literature
Project description:Microstructure imaging techniques based on tensor-valued diffusion encoding have gained popularity within the MRI research community. Unlike conventional diffusion encoding-applied along a single direction in each shot-tensor-valued encoding employs diffusion encoding along multiple directions within a single preparation of the signal. The benefit is that such encoding may probe tissue features that are not accessible by conventional encoding. For example, diffusional variance decomposition (DIVIDE) takes advantage of tensor-valued encoding to probe microscopic diffusion anisotropy independent of orientation coherence. The drawback is that tensor-valued encoding generally requires gradient waveforms that are more demanding on hardware; it has therefore been used primarily in MRI systems with relatively high performance. The purpose of this work was to explore tensor-valued diffusion encoding on clinical MRI systems with varying performance to test its technical feasibility within the context of DIVIDE. We performed whole-brain imaging with linear and spherical b-tensor encoding at field strengths between 1.5 and 7 T, and at maximal gradient amplitudes between 45 and 80 mT/m. Asymmetric gradient waveforms were optimized numerically to yield b-values up to 2 ms/?m2. Technical feasibility was assessed in terms of the repeatability, SNR, and quality of DIVIDE parameter maps. Variable system performance resulted in echo times between 83 to 115 ms and total acquisition times of 6 to 9 minutes when using 80 signal samples and resolution 2×2×4 mm3. As expected, the repeatability, signal-to-noise ratio and parameter map quality depended on hardware performance. We conclude that tensor-valued encoding is feasible for a wide range of MRI systems-even at 1.5 T with maximal gradient waveform amplitudes of 33 mT/m-and baseline experimental design and quality parameters for all included configurations. This demonstrates that tissue features, beyond those accessible by conventional diffusion encoding, can be explored on a wide range of MRI systems.
| S-EPMC6438503 | biostudies-literature