Denoising of 3D magnetic resonance images by using higher-order singular value decomposition

Improving Xenon-129 lung ventilation image SNR with deep-learning based image reconstruction

PURPOSE

To evaluate the feasibility and utility of a deep learning (DL)-based reconstruction for improving the SNR of hyperpolarized 129Xe lung ventilation MRI.

METHODS

129Xe lung ventilation MRI data acquired from patients with asthma and/or chronic obstructive pulmonary disease (COPD) were retrospectively reconstructed with a commercial DL reconstruction pipeline at five different denoising levels. Quantitative imaging metrics of lung ventilation including ventilation defect percentage (VDP) and ventilation heterogeneity index (VHI) were compared between each set of DL-reconstructed images and alternative denoising strategies including: filtering, total variation denoising and higher-order singular value decomposition. Structural similarity between the denoised and original images was assessed. In a prospective study, the feasibility of using SNR gains from DL reconstruction to allow natural-abundance xenon MRI was evaluated in healthy volunteers.

RESULTS

129Xe ventilation image SNR was improved with DL reconstruction when compared with conventionally reconstructed images. In patients with asthma and/or COPD, DL-reconstructed images exhibited a slight positive bias in ventilation defect percentage (1.3% at 75% denoising) and ventilation heterogeneity index (˜1.4) when compared with conventionally reconstructed images. Additionally, DL-reconstructed images preserved structural similarity more effectively than data denoised using alternative approaches. DL reconstruction greatly improved image SNR (greater than threefold), to a level that 129Xe ventilation imaging using natural-abundance xenon appears feasible.

CONCLUSION

DL-based image reconstruction significantly improves 129Xe ventilation image SNR, preserves structural similarity, and leads to a minor bias in ventilation metrics that can be attributed to differences in the image sharpness. This tool should help facilitate cost-effective 129Xe ventilation imaging with natural-abundance xenon in the future.

MRI at low field: A review of software solutions for improving SNR

Low magnetic field magnetic resonance imaging (MRI) (B 0 $$ {B}_0 $$  < 1 T) is regaining interest in the magnetic resonance (MR) community as a complementary, more flexible, and cost-effective approach to MRI diagnosis. Yet, the impaired signal-to-noise ratio (SNR) per square root of time, or SNR efficiency, leading in turn to prolonged acquisition times, still challenges its relevance at the clinical level. To address this, researchers investigate various hardware and software solutions to improve SNR efficiency at low field, including the leveraging of latest advances in computing hardware. However, there may not be a single recipe for improving SNR at low field, and it is key to embrace the challenges and limitations of each proposed solution. In other words, suitable solutions depend on the final objective or application envisioned for a low-field scanner and, more importantly, on the characteristics of a specific lowB 0 $$ {B}_0 $$ field. In this review, we aim to provide an overview on software solutions to improve SNR efficiency at low field. First, we cover techniques for efficient k-space sampling and reconstruction. Then, we present post-acquisition techniques that enhance MR images such as denoising and super-resolution. In addition, we summarize recently introduced electromagnetic interference cancellation approaches showing great promises when operating in shielding-free environments. Finally, we discuss the advantages and limitations of these approaches that could provide directions for future applications.

Tensor Methods in Biomedical Image Analysis

In the past decade, tensors have become increasingly attractive in different aspects of signal and image processing areas. The main reason is the inefficiency of matrices in representing and analyzing multimodal and multidimensional datasets. Matrices cannot preserve the multidimensional correlation of elements in higher-order datasets and this highly reduces the effectiveness of matrix-based approaches in analyzing multidimensional datasets. Besides this, tensor-based approaches have demonstrated promising performances. These together, encouraged researchers to move from matrices to tensors. Among different signal and image processing applications, analyzing biomedical signals and images is of particular importance. This is due to the need for extracting accurate information from biomedical datasets which directly affects patient's health. In addition, in many cases, several datasets have been recorded simultaneously from a patient. A common example is recording electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) of a patient with schizophrenia. In such a situation, tensors seem to be among the most effective methods for the simultaneous exploitation of two (or more) datasets. Therefore, several tensor-based methods have been developed for analyzing biomedical datasets. Considering this reality, in this paper, we aim to have a comprehensive review on tensor-based methods in biomedical image analysis. The presented study and classification between different methods and applications can show the importance of tensors in biomedical image enhancement and open new ways for future studies.

Hyperpolarized 13 C metabolic imaging of the human abdomen with spatiotemporal denoising

PURPOSE

Improving the quality and maintaining the fidelity of large coverage abdominal hyperpolarized (HP) 13 C MRI studies with a patch based global-local higher-order singular value decomposition (GL-HOVSD) spatiotemporal denoising approach.

METHODS

Denoising performance was first evaluated using the simulated [1-13 C]pyruvate dynamics at different noise levels to determine optimal kglobal and klocal parameters. The GL-HOSVD spatiotemporal denoising method with the optimized parameters was then applied to two HP [1-13 C]pyruvate EPI abdominal human cohorts (n = 7 healthy volunteers and n = 8 pancreatic cancer patients).

RESULTS

The parameterization of kglobal  = 0.2 and klocal  = 0.9 denoises abdominal HP data while retaining image fidelity when evaluated by RMSE. The kPX (conversion rate of pyruvate-to-metabolite, X = lactate or alanine) difference was shown to be <20% with respect to ground-truth metabolic conversion rates when there is adequate SNR (SNRAUC  > 5) for downstream metabolites. In both human cohorts, there was a greater than nine-fold gain in peak [1-13 C]pyruvate, [1-13 C]lactate, and [1-13 C]alanine apparent SNRAUC . The improvement in metabolite SNR enabled a more robust quantification of kPL and kPA . After denoising, we observed a 2.1 ± 0.4 and 4.8 ± 2.5-fold increase in the number of voxels reliably fit across abdominal FOVs for kPL and kPA quantification maps.

CONCLUSION

Spatiotemporal denoising greatly improves visualization of low SNR metabolites particularly [1-13 C]alanine and quantification of [1-13 C]pyruvate metabolism in large FOV HP 13 C MRI studies of the human abdomen.

Boosting quantification accuracy of chemical exchange saturation transfer MRI with a spatial-spectral redundancy-based denoising method

Chemical exchange saturation transfer (CEST) is a versatile technique that enables noninvasive detections of endogenous metabolites present in low concentrations in living tissue. However, CEST imaging suffers from an inherently low signal-to-noise ratio (SNR) due to the decreased water signal caused by the transfer of saturated spins. This limitation challenges the accuracy and reliability of quantification in CEST imaging. In this study, a novel spatial-spectral denoising method, called BOOST (suBspace denoising with nOnlocal lOw-rank constraint and Spectral local-smooThness regularization), was proposed to enhance the SNR of CEST images and boost quantification accuracy. More precisely, our method initially decomposes the noisy CEST images into a low-dimensional subspace by leveraging the global spectral low-rank prior. Subsequently, a spatial nonlocal self-similarity prior is applied to the subspace-based images. Simultaneously, the spectral local-smoothness property of Z-spectra is incorporated by imposing a weighted spectral total variation constraint. The efficiency and robustness of BOOST were validated in various scenarios, including numerical simulations and preclinical and clinical conditions, spanning magnetic field strengths from 3.0 to 11.7 T. The results demonstrated that BOOST outperforms state-of-the-art algorithms in terms of noise elimination. As a cost-effective and widely available post-processing method, BOOST can be easily integrated into existing CEST protocols, consequently promoting accuracy and reliability in detecting subtle CEST effects.

A user independent denoising method for x-nuclei MRI and MRS

PURPOSE

X-nuclei (also called non-proton MRI) MRI and spectroscopy are limited by the intrinsic low SNR as compared to conventional proton imaging. Clinical translation of x-nuclei examination warrants the need of a robust and versatile tool improving image quality for diagnostic use. In this work, we compare a novel denoising method with fewer inputs to the current state-of-the-art denoising method.

METHODS

Denoising approaches were compared on human acquisitions of sodium (23 Na) brain, deuterium (2 H) brain, carbon (13 C) heart and brain, and simulated dynamic hyperpolarized 13 C brain scans, with and without additional noise. The current state-of-the-art denoising method Global-local higher order singular value decomposition (GL-HOSVD) was compared to the few-input method tensor Marchenko-Pastur principal component analysis (tMPPCA). Noise-removal was quantified by residual distributions, and statistical analyses evaluated the differences in mean-square-error and Bland-Altman analysis to quantify agreement between original and denoised results of noise-added data.

RESULTS

GL-HOSVD and tMPPCA showed similar performance for the variety of x-nuclei data analyzed in this work, with tMPPCA removing ˜5% more noise on average over GL-HOSVD. The mean ratio between noise-added and denoising reproducibility coefficients of the Bland-Altman analysis when compared to the original are also similar for the two methods with 3.09 ± 1.03 and 2.83 ± 0.79 for GL-HOSVD and tMPPCA, respectively.

CONCLUSION

The strength of tMPPCA lies in the few-input approach, which generalizes well to different data sources. This makes the use of tMPPCA denoising a robust and versatile tool in x-nuclei imaging improvements and the preferred denoising method.

Noise Reduction Using Singular Value Decomposition with Jensen–Shannon Divergence for Coronary Computed Tomography Angiography

Coronary computed tomography angiography (CCTA) is widely used due to its improvements in computed tomography (CT) diagnostic performance. Unlike other CT examinations, CCTA requires shorter rotation times of the X-ray tube, improving the temporal resolution and facilitating the imaging of the beating heart in a stationary state. However, reconstructed CT images, including those of the coronary arteries, contain insufficient X-ray photons and considerable noise. In this study, we introduce an image-processing technique for noise reduction using singular value decomposition (SVD) for CCTA images. The threshold of SVD was determined on the basis of minimization of Jensen–Shannon (JS) divergence. Experiments were performed with various numerical phantoms and varying levels of noise to reduce noise in clinical CCTA images using the determined threshold value. The numerical phantoms produced 10% higher-quality images than the conventional noise reduction method when compared on a quantitative SSIM basis. The threshold value determined by minimizing the JS–divergence was found to be useful for efficient noise reduction in actual clinical images, depending on the level of noise.

Tensor denoising of multidimensional MRI data

PURPOSE

To develop a denoising strategy leveraging redundancy in high-dimensional data.

THEORY AND METHODS

The SNR fundamentally limits the information accessible by MRI. This limitation has been addressed by a host of denoising techniques, recently including the so-called MPPCA: principal component analysis of the signal followed by automated rank estimation, exploiting the Marchenko-Pastur distribution of noise singular values. Operating on matrices comprised of data patches, this popular approach objectively identifies noise components and, ideally, allows noise to be removed without introducing artifacts such as image blurring, or nonlocal averaging. The MPPCA rank estimation, however, relies on a large number of noise singular values relative to the number of signal components to avoid such ill effects. This condition is unlikely to be met when data patches and therefore matrices are small, for example due to spatially varying noise. Here, we introduce tensor MPPCA (tMPPCA) for the purpose of denoising multidimensional data, such as from multicontrast acquisitions. Rather than combining dimensions in matrices, tMPPCA uses each dimension of the multidimensional data's inherent tensor-structure to better characterize noise, and to recursively estimate signal components.

RESULTS

Relative to matrix-based MPPCA, tMPPCA requires no additional assumptions, and comparing the two in a numerical phantom and a multi-TE diffusion MRI data set, tMPPCA dramatically improves denoising performance. This is particularly true for small data patches, suggesting that tMPPCA can be especially beneficial in such cases.

CONCLUSIONS

The MPPCA denoising technique can be extended to high-dimensional data with improved performance for smaller patch sizes.

Denoise ultra-low-field 3D magnetic resonance images using a joint signal-image domain filter

Ultra-low-field magnetic resonance imaging (MRI) could suffer from heavy uncorrelated noise, and its removal could be a critical post-processing task. As a primary source of interference, Gaussian noise could corrupt the sampled MR signal (k-space data), especially at lower B₀ field strength. For this reason, we consider both signal and image domains by proposing a new joint filter characterized by a Kalman filter with linear prediction and a nonlocal mean filter with higher-order singular value decomposition (HOSVD) for denoising 3D MR data. The Kalman filter first attenuates the noise in k-space, and then its reconstruction images are used to guide HOSVD denoising process with exploring self-similarity among 3D structures. The clearer prefiltered images could also generate improved HOSVD learned bases used to transform the noise corrupted patch groups in the original MR data. The flexibility of proposed method is also demonstrated by integrating other k-space filters into the algorithm scheme. Experimental data includes simulated MR images with the varying noise level and real MR images obtained from our 50 mT MRI scanner. The results reveal that our method has a better noise-removal ability and introduces lesser unexpected artifacts than other related MRI denoising approaches.

Spatiotemporal organisation of protein processing in the kidney

The kidney regulates plasma protein levels by eliminating them from the circulation. Proteins filtered by glomeruli are endocytosed and degraded in the proximal tubule and defects in this process result in tubular proteinuria, an important clinical biomarker. However, the spatiotemporal organization of renal protein metabolism in vivo was previously unclear. Here, using functional probes and intravital microscopy, we track the fate of filtered proteins in real time in living mice, and map specialized processing to tubular structures with singular value decomposition analysis and three-dimensional electron microscopy. We reveal that degradation of proteins requires sequential, coordinated activity of distinct tubular sub-segments, each adapted to specific tasks. Moreover, we leverage this approach to pinpoint the nature of endo-lysosomal disorders in disease models, and show that compensatory uptake in later regions of the proximal tubule limits urinary protein loss. This means that measurement of proteinuria likely underestimates severity of endocytotic defects in patients.

Polesel et al. visualize plasma protein filtration, uptake and metabolism in the kidneys of living mice in real-time. They reveal coordinated activity of different specialized tubular segments, with major compensatory adaptations occurring in disease states.

Accelerated MRI Reconstruction With Separable and Enhanced Low-Rank Hankel Regularization

Magnetic resonance imaging serves as an essential tool for clinical diagnosis, however, suffers from a long acquisition time. Sparse sampling effectively saves this time but images need to be faithfully reconstructed from undersampled data. Among the existing reconstruction methods, the structured low-rank methods have advantages in robustness to the sampling patterns and lower error. However, the structured low-rank methods use the 2D or higher dimension k-space data to build a huge block Hankel matrix, leading to considerable time and memory consumption. To reduce the size of the Hankel matrix, we proposed to separably construct multiple small Hankel matrices from rows and columns of the k-space and then constrain the low-rankness on these small matrices. This separable model can significantly reduce the computational time but ignores the correlation existed in inter- and intra-row or column, resulting in increased reconstruction error. To improve the reconstructed image without obviously increasing the computation, we further introduced the self-consistency of k-space and virtual coil prior. Besides, the proposed separable model can be extended into other imaging scenarios which hold exponential characteristics in the parameter dimension. The in vivo experimental results demonstrated that the proposed method permits the lowest reconstruction error with a fast reconstruction. The proposed approach requires only 4% of the state-of-the-art STDLR-SPIRiT runtime for parallel imaging reconstruction, and achieves the fastest computational speed in parameter imaging reconstruction.

Assessment of higher-order singular value decomposition denoising methods on dynamic hyperpolarized [1-13C]pyruvate MRI data from patients with glioma

BACKGROUND

Real-time metabolic conversion of intravenously-injected hyperpolarized [1-13C]pyruvate to [1-13C]lactate and [13C]bicarbonate in the brain can be measured using dynamic hyperpolarized carbon-13 (HP-13C) MRI. However, voxel-wise evaluation of metabolism in patients with glioma is challenged by the limited signal-to-noise ratio (SNR) of downstream 13C metabolites, especially within lesions. The purpose of this study was to evaluate the ability of higher-order singular value decomposition (HOSVD) denoising methods to enhance dynamic HP [1-13C]pyruvate MRI data acquired from patients with glioma.

METHODS

Dynamic HP-13C MRI were acquired from 14 patients with glioma. The effects of two HOSVD denoising techniques, tensor rank truncation-image enhancement (TRI) and global-local HOSVD (GL-HOSVD), on the SNR and kinetic modeling were analyzed in [1-13C]lactate data with simulated noise that matched the levels of [13C]bicarbonate signals. Both methods were then evaluated in patient data based on their ability to improve [1-13C]pyruvate, [1-13C]lactate and [13C]bicarbonate SNR. The effects of denoising on voxel-wise kinetic modeling of kPL and kPB was also evaluated. The number of voxels with reliable kinetic modeling of pyruvate-to-lactate (kPL) and pyruvate-to-bicarbonate (kPB) conversion rates within regions of interest (ROIs) before and after denoising was then compared.

RESULTS

Both denoising methods improved metabolite SNR and regional signal coverage. In patient data, the average increase in peak dynamic metabolite SNR was 2-fold using TRI and 4-5 folds using GL-HOSVD denoising compared to acquired data. Denoising reduced kPL modeling errors from a native average of 23% to 16% (TRI) and 15% (GL-HOSVD); and kPB error from 42% to 34% (TRI) and 37% (GL-HOSVD) (values were averaged voxelwise over all datasets). In contrast-enhancing lesions, the average number of voxels demonstrating within-tolerance kPL modeling error relative to the total voxels increased from 48% in the original data to 84% (TRI) and 90% (GL-HOSVD), while the number of voxels showing within-tolerance kPB modeling error increased from 0% to 15% (TRI) and 8% (GL-HOSVD).

CONCLUSION

Post-processing denoising methods significantly improved the SNR of dynamic HP-13C imaging data, resulting in a greater number of voxels satisfying minimum SNR criteria and maximum kinetic modeling errors in tumor lesions. This enhancement can aid in the voxel-wise analysis of HP-13C data and thereby improve monitoring of metabolic changes in patients with glioma following treatment.

Nonconvex Nonlocal Tucker Decomposition for 3D Medical Image Super-Resolution

Limited by hardware conditions, imaging devices, transmission efficiency, and other factors, high-resolution (HR) images cannot be obtained directly in clinical settings. It is expected to obtain HR images from low-resolution (LR) images for more detailed information. In this article, we propose a novel super-resolution model for single 3D medical images. In our model, nonlocal low-rank tensor Tucker decomposition is applied to exploit the nonlocal self-similarity prior knowledge of data. Different from the existing methods that use a convex optimization for tensor Tucker decomposition, we use a tensor folded-concave penalty to approximate a nonlocal low-rank tensor. Weighted 3D total variation (TV) is used to maintain the local smoothness across different dimensions. Extensive experiments show that our method outperforms some state-of-the-art (SOTA) methods on different kinds of medical images, including MRI data of the brain and prostate and CT data of the abdominal and dental.

Multiparametric Functional MRI of the Kidney: Current State and Future Trends with Deep Learning Approaches

BACKGROUND

 Until today, assessment of renal function has remained a challenge for modern medicine. In many cases, kidney diseases accompanied by a decrease in renal function remain undetected and unsolved, since neither laboratory tests nor imaging diagnostics provide adequate information on kidney status. In recent years, developments in the field of functional magnetic resonance imaging with application to abdominal organs have opened new possibilities combining anatomic imaging with multiparametric functional information. The multiparametric approach enables the measurement of perfusion, diffusion, oxygenation, and tissue characterization in one examination, thus providing more comprehensive insight into pathophysiological processes of diseases as well as effects of therapeutic interventions. However, application of multiparametric fMRI in the kidneys is still restricted mainly to research areas and transfer to the clinical routine is still outstanding. One of the major challenges is the lack of a standardized protocol for acquisition and postprocessing including efficient strategies for data analysis. This article provides an overview of the most common fMRI techniques with application to the kidney together with new approaches regarding data analysis with deep learning.

METHODS

 This article implies a selective literature review using the literature database PubMed in May 2021 supplemented by our own experiences in this field.

RESULTS AND CONCLUSION

 Functional multiparametric MRI is a promising technique for assessing renal function in a more comprehensive approach by combining multiple parameters such as perfusion, diffusion, and BOLD imaging. New approaches with the application of deep learning techniques could substantially contribute to overcoming the challenge of handling the quantity of data and developing more efficient data postprocessing and analysis protocols. Thus, it can be hoped that multiparametric fMRI protocols can be sufficiently optimized to be used for routine renal examination and to assist clinicians in the diagnostics, monitoring, and treatment of kidney diseases in the future.

KEY POINTS

  · Multiparametric fMRI is a technique performed without the use of radiation, contrast media, and invasive methods.. · Multiparametric fMRI provides more comprehensive insight into pathophysiological processes of kidney diseases by combining functional and structural parameters.. · For broader acceptance of fMRI biomarkers, there is a need for standardization of acquisition, postprocessing, and analysis protocols as well as more prospective studies.. · Deep learning techniques could significantly contribute to an optimization of data acquisition and the postprocessing and interpretation of larger quantities of data..

CITATION FORMAT

· Zhang C, Schwartz M, Küstner T et al. Multiparametric Functional MRI of the Kidney: Current State and Future Trends with Deep Learning Approaches. Fortschr Röntgenstr 2022; DOI: 10.1055/a-1775-8633.

Photoacoustic computed tomography of mechanical HIFU-induced vascular injury

Mechanical high-intensity focused ultrasound (HIFU) has been used for cancer treatment and drug delivery. Existing monitoring methods for mechanical HIFU therapies such as MRI and ultrasound imaging often suffer from high cost, poor spatial-temporal resolution, and/or low sensitivity to tissue's hemodynamic changes. Evaluating vascular injury during mechanical HIFU treatment, therefore, remains challenging. Photoacoustic computed tomography (PACT) is a promising tool to meet this need. Intrinsically sensitive to optical absorption, PACT provides high-resolution imaging of blood vessels using hemoglobin as the endogenous contrast. In this study, we have developed an integrated HIFU-PACT system for detecting vascular rupture in mechanical HIFU treatment. We have demonstrated singular value decomposition for enhancing hemorrhage detection. We have validated the HIFU-PACT performance on phantoms and in vivo animal tumor models. We expect that PACT-HIFU will find practical applications in oncology research using small animal models.

[A diffusion-weighted image denoising algorithm using HOSVD combined with Rician noise corrected model]

OBJECTIVE

To propose a novel diffusion-weighted (DW) image denoising algorithm based on HOSVD to improve the signal-to-noise ratio (SNR) of DW images and the accuracy of subsequent quantization parameters.

METHODS

This HOSVDbased denoising method incorporated the sparse constraint and noise-correction model. The signal expectations with Rician noise were integrated into the traditional HOSVD denoising framework for direct denoising of the DW images with Rician noise. HOSVD denoising was performed directly on each local DW image block to avoid the stripe artifacts. We compared the proposed method with 4 image denoising algorithms (LR + Edge, GL-HOSVD, BM3D and NLM) to verify the effect of the proposed method.

RESULTS

The experimental results showed that the proposed method effectively reduced the noise of DW images while preserving the image details and edge structure information. The proposed algorithm was significantly better than LR +Edge, BM3D and NLM in terms of quantitative metrics of PSNR, SSIM and FA-RMSE and in visual evaluation of denoising images and FA images. GL-HOSVD obtained good denoising results but introduced stripe artifacts at a high noise level during the denoising process. In contrast, the proposed method achieved good denoising results without causing stripe artifacts.

CONCLUSION

This HOSVD-based denoising method allows direct processing of DW images with Rician noise without introducing artifacts and can provide accurate quantitative parameters for diagnostic purposes.

Denoising of hyperpolarized 13 C MR images of the human brain using patch-based higher-order singular value decomposition

PURPOSE

To improve hyperpolarized ¹³ C (HP-¹³ C) MRI by image denoising with a new approach, patch-based higher-order singular value decomposition (HOSVD).

METHODS

The benefit of using a patch-based HOSVD method to denoise dynamic HP-¹³ C MR imaging data was investigated. Image quality and the accuracy of quantitative analyses following denoising were evaluated first using simulated data of [1-¹³ C]pyruvate and its metabolic product, [1-¹³ C]lactate, and compared the results to a global HOSVD method. The patch-based HOSVD method was then applied to healthy volunteer HP [1-¹³ C]pyruvate EPI studies. Voxel-wise kinetic modeling was performed on both non-denoised and denoised data to compare the number of voxels quantifiable based on SNR criteria and fitting error.

RESULTS

Simulation results demonstrated an 8-fold increase in the calculated SNR of [1-¹³ C]pyruvate and [1-¹³ C]lactate with the patch-based HOSVD denoising. The voxel-wise quantification of k_PL (pyruvate-to-lactate conversion rate) showed a 9-fold decrease in standard errors for the fitted k_PL after denoising. The patch-based denoising performed superior to the global denoising in recovering k_PL information. In volunteer data sets, [1-¹³ C]lactate and [¹³ C]bicarbonate signals became distinguishable from noise across captured time points with over a 5-fold apparent SNR gain. This resulted in >3-fold increase in the number of voxels quantifiable for mapping k_PB (pyruvate-to-bicarbonate conversion rate) and whole brain coverage for mapping k_PL .

CONCLUSIONS

Sensitivity enhancement provided by this denoising significantly improved quantification of metabolite dynamics and could benefit future studies by improving image quality, enabling higher spatial resolution, and facilitating the extraction of metabolic information for clinical research.

Denoising of magnetic resonance images using discriminative learning-based deep convolutional neural network

BACKGROUND

The noise in magnetic resonance (MR) images causes severe issues for medical diagnosis purposes.

OBJECTIVE

In this paper, we propose a discriminative learning based convolutional neural network denoiser to denoise the MR image data contaminated with noise.

METHODS

The proposed method incorporates the use of depthwise separable convolution along with local response normalization with modified hyperparameters and internal skip connections to denoise the contaminated MR images. Moreover, the addition of parametric RELU instead of normal conventional RELU in our proposed architecture gives more stable and fine results. The denoised images were further segmented to test the appropriateness of the results. The network is trained on one dataset and tested on other dataset produces remarkably good results.

RESULTS

Our proposed network was used to denoise the images of different noise levels, and it yields better performance as compared with various networks. The SSIM and PSNR showed an average improvement of (7.2 ± 0.002) % and (8.5 ± 0.25) % respectively when tested on different datasets without retaining the network. An improvement of 5% and 6% was achieved in the values of mean intersection over union (mIoU) and BF score when the denoised images were segmented for testing the relevancy in biomedical imaging applications. The statistical test suggests that the obtained results are statistically significant as p< 0.05.

CONCLUSION

The denoised images obtained are more clinically suitable for medical image diagnosis purposes, as depicted by the evaluation parameters. Further, external clinical validation was performed by an experienced radiologist for testing the validation of the resulting images.

Denoising of 3D Brain MR Images with Parallel Residual Learning of Convolutional Neural Network Using Global and Local Feature Extraction

Magnetic resonance (MR) images often suffer from random noise pollution during image acquisition and transmission, which impairs disease diagnosis by doctors or automated systems. In recent years, many noise removal algorithms with impressive performances have been proposed. In this work, inspired by the idea of deep learning, we propose a denoising method named 3D-Parallel-RicianNet, which will combine global and local information to remove noise in MR images. Specifically, we introduce a powerful dilated convolution residual (DCR) module to expand the receptive field of the network and to avoid the loss of global features. Then, to extract more local information and reduce the computational complexity, we design the depthwise separable convolution residual (DSCR) module to learn the channel and position information in the image, which not only reduces parameters dramatically but also improves the local denoising performance. In addition, a parallel network is constructed by fusing the features extracted from each DCR module and DSCR module to improve the efficiency and reduce the complexity for training a denoising model. Finally, a reconstruction (REC) module aims to construct the clean image through the obtained noise deviation and the given noisy image. Due to the lack of ground-truth images in the real MR dataset, the performance of the proposed model was tested qualitatively and quantitatively on one simulated T1-weighted MR image dataset and then expanded to four real datasets. The experimental results show that the proposed 3D-Parallel-RicianNet network achieves performance superior to that of several state-of-the-art methods in terms of the peak signal-to-noise ratio, structural similarity index, and entropy metric. In particular, our method demonstrates powerful abilities in both noise suppression and structure preservation.

A Modified Higher-Order Singular Value Decomposition Framework With Adaptive Multilinear Tensor Rank Approximation for Three-Dimensional Magnetic Resonance Rician Noise Removal

The magnetic resonance (MR) images are acknowledged to be inevitably corrupted by Rician distributed noise, which adversely affected the image quality for diagnosis purpose. However, the traditional denoising methods may recover the images from corruptions with severe loss of detailed structure and edge information, which would affect the lesion detections and diagnostic decision making. In this study, we challenged improving the Rician noise removal from three-dimensional (3D) MR volumetric data through a modified higher-order singular value decomposition (MHOSVD) method. The proposed framework of MHOSVD involved a parameterized logarithmic nonconvex penalty function for low-rank tensor approximation (LRTA) algorithm optimization to suppress the image noise in MR dataset. Reference cubes were extracted from the noisy image volume, and block matching was performed according to nonlocal similarity for a fourth-order tensor construction. Then the LRTA problem was implemented by tensor factorization approaches, and the ranks of unfolding matrices along different modes of the tensor were estimated utilizing an adaptive nonconvex low-rank method. The denoised MR images were finally restored through aggregating all recovered cubes. We investigated the proposed algorithm MHOSVD on both the synthetic and real clinic 3D MR images for Rician noise removal, and relative results demonstrated that the MHOSVD can recover images with fine structures and detailed edge preservation with heavy noise even as high as 15% of the maximum intensity. The experimental results were also compared along with several classical denoising methods; the MHOSVD exhibited a sufficient improvement in noise-removal performance at various noise conditions in terms of different measurement indices such as peak signal-to-noise ratio and structural similarity index metrics. Based upon the comparison, the proposed MHOSVD has proved a relative state-of-the-art performance with excellent detailed structure reservation.

3D MR image denoising using a modified adaptive high order singular value decomposition method. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2020;2020:1580-1583. [PMID: 33018295 DOI: 10.1109/embc44109.2020.9175418] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

Magnetic resonance (MR) images are generally degraded by random noise governed by Rician distributions. In this study, we developed a modified adaptive high order singular value decomposition (HOSVD) method, taking consideration of the nonlocal self-similarity and weighted Schatten p-norm. We extracted 3D cubes from noise images and classified the similar cubes by the Euclidean distance between cubes to construction a fourth-order tensor. Each rank of unfolding matrices was adaptively determined by weighted Schatten p-norm regularization. The latent noise-free 3D MR images can be obtained by an adaptive HOSVD. Denoising experiments were tested on both synthetic and clinical 3D MR images, and the results showed the proposed method outperformed several existing methods for Rician noise removal in 3D MR images.

MRI denoising using progressively distribution-based neural network

Magnetic Resonance (MR) images often suffer from noise pollution during image acquisition and transmission, which limits the accuracy of quantitative measurements from the data. Noise in magnitude MR images is usually governed by Rician distribution, due to the existence of uncorrelated Gaussian noise with zero-mean and equal variance in both the real and imaginary parts of the complex K-space data. Different from the existing MRI denoising methods that utilizing the spatial neighbor information around the pixels or patches, this work turns to capture the pixel-level distribution information by means of supervised network learning. A progressive network learning strategy is proposed via fitting the distribution of pixel-level and feature-level intensities. The proposed network consists of two residual blocks, one is used for fitting pixel domain without batch normalization layer and another one is applied for matching feature domain with batch normalization layer. Experimental results under synthetic, complex-valued and clinical MR brain images demonstrate great potential of the proposed network with substantially improved quantitative measures and visual inspections.

Non-Local SVD Denoising of MRI Based on Sparse Representations

Magnetic Resonance (MR) Imaging is a diagnostic technique that produces noisy images, which must be filtered before processing to prevent diagnostic errors. However, filtering the noise while keeping fine details is a difficult task. This paper presents a method, based on sparse representations and singular value decomposition (SVD), for non-locally denoising MR images. The proposed method prevents blurring, artifacts, and residual noise. Our method is composed of three stages. The first stage divides the image into sub-volumes, to obtain its sparse representation, by using the KSVD algorithm. Then, the global influence of the dictionary atoms is computed to upgrade the dictionary and obtain a better reconstruction of the sub-volumes. In the second stage, based on the sparse representation, the noise-free sub-volume is estimated using a non-local approach and SVD. The noise-free voxel is reconstructed by aggregating the overlapped voxels according to the rarity of the sub-volumes it belongs, which is computed from the global influence of the atoms. The third stage repeats the process using a different sub-volume size for producing a new filtered image, which is averaged with the previously filtered images. The results provided show that our method outperforms several state-of-the-art methods in both simulated and real data.

Demonstration of Human Fetal Bone Morphology with MR Imaging: A Preliminary Study

Purpose:

CT is a useful modality for the evaluation of fetal skeletal dysplasia but radiation exposure is unavoidable. The purpose of this study is to compare the usefulness of MRI and CT for evaluating the fetal skeletal shape.

Methods:

This study was approved by our Institutional Review Board. Fetal specimens (n = 14) were scanned on a 3T MRI scanner using our newly-developed sequence. It is based on T2*-weighted imaging (TR, 12 ms; TE for opposed-phase imaging, 6.1 ms, for in-phase imaging, 7.3 ms; flip angle, 40°). The specimens were also scanned on a 320 detector-row CT scanner. Four radiologists visually graded and compared the visibility of the bone shape of eight regions on MRI- and CT-scans using a 5-point grading system.

Results:

The diagnostic ability of MRI with respect to the 5th metacarpals, femur, fibula, and pelvis was superior to CT (all, P < 0.050); there was no significant difference in the evaluation results of observers with respect to the cervical and lumbar spine, and the 5th metatarsal (0.058 ≤ P ≤ 1.000). However, the diagnostic ability of MRI was significantly inferior to CT for the assessment of the bone shape of the thoracic spine (observers A and C: P = 0.002, observers B and D: P = 0.001).

Conclusion:

The MRI method we developed represents a potential alternative to CT imaging for the evaluation of the fetal bone structure.

Denoising of MR images with Rician noise using a wider neural network and noise range division

Magnetic resonance (MR) images denoising is important in medical image analysis. Denoising methods based on deep learning have shown great promise and outperform all of the other conventional methods. However, deep-learning methods are limited by the number of training samples. In this article, using a small sample size, we applied a wider denoising neural network to MR images with Rician noise and trained several denoising models. The first model is specific to a certain noise, while the other applies to a wide range of noise levels. We considered the noise range as one interval, two sub-intervals, three sub-intervals, or even more sub-intervals to train the corresponding models. Experimental results demonstrate that for MR images, the proposed deep-learning models are efficient in terms of peak-signal-to-noise ratio, structure-similarity-index metrics and normalized mutual information. In addition, for blind noise, the effect of the three sub-intervals is better than that of the other sub-intervals.

Dynamic Imaging of Glucose and Lactate Metabolism by 13C-MRS without Hyperpolarization

Metabolic reprogramming is one of the defining features of cancer and abnormal metabolism is associated with many other pathologies. Molecular imaging techniques capable of detecting such changes have become essential for cancer diagnosis, treatment planning, and surveillance. In particular, ¹⁸F-FDG (fluorodeoxyglucose) PET has emerged as an essential imaging modality for cancer because of its unique ability to detect a disturbed molecular pathway through measurements of glucose uptake. However, FDG-PET has limitations that restrict its usefulness in certain situations and the information gained is limited to glucose uptake only.¹³C magnetic resonance spectroscopy theoretically has certain advantages over FDG-PET, but its inherent low sensitivity has restricted its use mostly to single voxel measurements unless dissolution dynamic nuclear polarization (dDNP) is used to increase the signal, which brings additional complications for clinical use. We show here a new method of imaging glucose metabolism in vivo by MRI chemical shift imaging (CSI) experiments that relies on a simple, but robust and efficient, post-processing procedure by the higher dimensional analog of singular value decomposition, tensor decomposition. Using this procedure, we achieve an order of magnitude increase in signal to noise in both dDNP and non-hyperpolarized non-localized experiments without sacrificing accuracy. In CSI experiments an approximately 30-fold increase was observed, enough that the glucose to lactate conversion indicative of the Warburg effect can be imaged without hyper-polarization with a time resolution of 12s and an overall spatial resolution that compares favorably to ¹⁸F-FDG PET.

An overview of deep learning in medical imaging focusing on MRI

What has happened in machine learning lately, and what does it mean for the future of medical image analysis? Machine learning has witnessed a tremendous amount of attention over the last few years. The current boom started around 2009 when so-called deep artificial neural networks began outperforming other established models on a number of important benchmarks. Deep neural networks are now the state-of-the-art machine learning models across a variety of areas, from image analysis to natural language processing, and widely deployed in academia and industry. These developments have a huge potential for medical imaging technology, medical data analysis, medical diagnostics and healthcare in general, slowly being realized. We provide a short overview of recent advances and some associated challenges in machine learning applied to medical image processing and image analysis. As this has become a very broad and fast expanding field we will not survey the entire landscape of applications, but put particular focus on deep learning in MRI. Our aim is threefold: (i) give a brief introduction to deep learning with pointers to core references; (ii) indicate how deep learning has been applied to the entire MRI processing chain, from acquisition to image retrieval, from segmentation to disease prediction; (iii) provide a starting point for people interested in experimenting and perhaps contributing to the field of deep learning for medical imaging by pointing out good educational resources, state-of-the-art open-source code, and interesting sources of data and problems related medical imaging.

Technical Note: Clustering-based motion compensation scheme for multishot diffusion tensor imaging

PURPOSE

To extend image reconstruction using image-space sampling function (IRIS) to address large-scale motion in multishot diffusion-weighted imaging (DWI).

METHODS

A clustered IRIS (CIRIS) algorithm that would extend IRIS was proposed to correct for large-scale motion. For DWI, CIRIS initially groups the shots into clusters without intracluster large-scale motion and reconstructs each cluster by using IRIS. Then, CIRIS registers these cluster images and combines the registered images by using a weighted average to correct for voxel mismatch caused by intercluster large-scale motion. For diffusion tensor imaging (DTI), CIRIS further reduces the effect of motion on diffusion directions by treating motion-induced direction changes as additional diffusion directions. CIRIS also introduces the detection and rejection of motion-corrupted data to avoid corresponding image degradation. The proposed method was evaluated by simulation and in vivo diffusion datasets.

RESULTS

Experiments demonstrated that CIRIS can reduce motion-induced blurring and artifacts in DWI and provide more accurate DTI estimations in the presence of large-scale motion, compared with IRIS.

CONCLUSION

The proposed method presents a novel approach to correct for large-scale in-plane motion for multishot DWI and is expected to benefit the practical application of high-resolution diffusion imaging.

Weighted Schatten p-norm minimization for 3D magnetic resonance images denoising

Magnetic resonance (MR) imaging plays an important role in clinical diagnosis and scientific research. A clean MR image can better provide patient's information to doctors or researchers for further treatment. However, in real life, MR images are inevitably corrupted by annoying Rician noise in the process of imaging. Aiming at the Rician noise of 3D MR images, a framework is proposed to suppress noise by low-rank matrix approximation (LRMA) with weighted Schatten p-norm minimization regularization (WSNMD-3D). The proposed method not only considers the importance of different rank components, but can also approximate the true rank of the latent low-rank matrix. This approach first groups similar non-local cubic patches extracted from the noisy 3D MR image into a matrix whose columns are vectorized patches. The above matrix can be modeled as a low-rank matrix approximate model. Then weighted Schatten p-norm minimization (WSNM) is applied to the model, which shrinks different rank components with different treatments. Finally, the denoised 3D MR image is acquired by aggregating all denoised patches with weighted averaging. Experimental results on synthetic and real 3D MR data show that the proposed method obtains better results than state-of-the-art methods, both visually and quantitatively.

Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network

PURPOSE

To test if the proposed deep learning based denoising method denoising convolutional neural networks (DnCNN) with residual learning and multi-channel strategy can denoise three dimensional MR images with Rician noise robustly.

MATERIALS AND METHODS

Multi-channel DnCNN (MCDnCNN) method with two training strategies was developed to denoise MR images with and without a specific noise level, respectively. To evaluate our method, three datasets from two public data sources of IXI dataset and Brainweb, including T1 weighted MR images acquired at 1.5 and 3 T as well as MR images simulated with a widely used MR simulator, were randomly selected and artificially added with different noise levels ranging from 1 to 15%. For comparison, four other state-of-the-art denoising methods were also tested using these datasets.

RESULTS

In terms of the highest peak-signal-to-noise-ratio and global of structure similarity index, our proposed MCDnCNN model for a specific noise level showed the most robust denoising performance in all three datasets. Next to that, our general noise-applicable model also performed better than the rest four methods in two datasets. Furthermore, our training model showed good general applicability.

CONCLUSION

Our proposed MCDnCNN model has been demonstrated to robustly denoise three dimensional MR images with Rician noise.

A New 4-D Nonlocal Transform-Domain Filter for 3-D Magnetic Resonance Images Denoising

The simultaneous removal of noise and preservation of the integrity of 3-D magnetic resonance (MR) images is a difficult and important task. In this paper, we consider characterizing MR images with 3-D operators, and present a novel 4-D transform-domain method termed 'modified nonlocal tensor-SVD (MNL-tSVD)' for MR image denoising. The proposed method is based on the grouping, hard-thresholding and aggregation paradigms, and can be viewed as a generalized nonlocal extension of tensor-SVD (t-SVD). By keeping MR images in its natural three-dimensional form, and collaboratively filtering similar patches, MNL-tSVD utilizes both the self-similarity property and 3-D structure of MR images to preserve more actual details and minimize the introduction of new artifacts. We show the adaptability of MNL-tSVD by incorporating it into a two-stage denoising strategy with a few adjustments. In addition, analysis of the relationship between MNL-tSVD and current the state-of-the-art 4-D transforms is given. Experimental comparisons over simulated and real brain data sets at different Rician noise levels show that MNL-tSVD can produce competitive performance compared with related approaches.

Denoise diffusion-weighted images using higher-order singular value decomposition

Noise usually affects the reliability of quantitative analysis in diffusion-weighted (DW) magnetic resonance imaging (MRI), especially at high b-values and/or high spatial resolution. Higher-order singular value decomposition (HOSVD) has recently emerged as a simple, effective, and adaptive transform to exploit sparseness within multidimensional data. In particular, the patch-based HOSVD denoising has demonstrated superb performance when applied to T1-, T2-, and proton density-weighted MRI data. In this study, we aim to investigate the feasibility of denoising DW data using the HOSVD transform. With the low signal-to-noise ratio in typical DW data, the patch-based HOSVD denoising suffers from stripe artifacts in homogeneous regions because of the HOSVD bases learned from the noisy patches. To address this problem, we propose a novel denoising method. It first introduces a global HOSVD-based denoising as a prefiltering stage to guide the subsequent patch-based HOSVD denoising stage. The HOSVD bases from the patch groups in prefiltered images are then used to transform the noisy patch groups in original DW data. Experiments were performed using simulated and in vivo DW data. Results show that the proposed method significantly reduces stripe artifacts compared with conventional patch-based HOSVD denoising methods, and outperforms two state-of-the-art denoising methods in terms of denoising quality and diffusion parameters estimation.

Diffusion-Weighted Images Superresolution Using High-Order SVD

The spatial resolution of diffusion-weighted imaging (DWI) is limited by several physical and clinical considerations, such as practical scanning times. Interpolation methods, which are widely used to enhance resolution, often result in blurred edges. Advanced superresolution scanning acquires images with specific protocols and long acquisition times. In this paper, we propose a novel single image superresolution (SR) method which introduces high-order SVD (HOSVD) to regularize the patch-based SR framework on DWI datasets. The proposed method was implemented on an adaptive basis which ensured a more accurate reconstruction of high-resolution DWI datasets. Meanwhile, the intrinsic dimensional decreasing property of HOSVD is also beneficial for reducing the computational burden. Experimental results from both synthetic and real DWI datasets demonstrate that the proposed method enhances the details in reconstructed high-resolution DWI datasets and outperforms conventional techniques such as interpolation methods and nonlocal upsampling.

Postreconstruction filtering of 3D PET images by using weighted higher-order singular value decomposition

Background

Positron emission tomography (PET) always suffers from high levels of noise due to the constraints of the injected dose and acquisition time, especially in the studies of dynamic PET imaging. To improve the quality of PET image, several approaches have been introduced to suppress noise. However, traditional filters often blur the image edges, or erase small detail, or rely on multiple parameters. In order to solve such problems, nonlocal denoising methods have been adapted to denoise PET images.

Methods

In this paper, we propose to use the weighted higher-order singular value decomposition for PET image denoising. We first modeled the noise in the PET image as Poisson distribution. Then, we transformed the noise to an additive Gaussian noise by use of the anscombe root transformation. Finally, we denoised the transformed image using the proposed higher-order singular value decomposition (HOSVD)-based algorithms. The denoised results were compared with results from some general filters by performing physical phantom and mice studies.

Results

Compared to other commonly used filters, HOSVD-based denoising algorithms can preserve boundaries and quantitative accuracy better. The spatial resolution and the low activity features in PET image also can be preserved by use of HOSVD-based methods. Comparing with the standard HOSVD-based algorithm, the proposed weighted HOSVD algorithm can suppress the stair-step artifact, and the time-consumption is about half of that needed by the Wiener-augmented HOSVD algorithm.

Conclusions

The proposed weighted HOSVD denoising algorithm can suppress noise while better preserving of boundary and quantity in PET images.

Electronic supplementary material

The online version of this article (doi:10.1186/s12938-016-0221-y) contains supplementary material, which is available to authorized users.

Global denoising for 3D MRI

BACKGROUND

Denoising is the primary preprocessing step for subsequent application of MRI. However, most commonly-used patch-based denoising methods are heavily dependent on the degree of patch matching. Due to the large number of voxels in the 3D MRI dataset, the procedure of searching sufficient similarity patches was limited by the empirical compromising between computational efficiency and estimation accuracy, and cannot fulfill the application in multimodal MRI dataset with different SNR and resolutions.

METHODS

In this study, we propose a modified global filtering framework for 3D MRI. For each denoising voxel, the similarity weighting matrix is computed using the reference patch and other patches from the whole dataset. This large weighting matrix is then approximated using the k-means clustering Nyström method to achieve computational viability.

RESULTS

Experiments on both synthetic and in vivo MRI datasets demonstrated that the proposed adaptive Nyström low-rank approximation could achieve competitive estimation compared with exact global filter while reducing the sampling rate by four orders of magnitude. In addition, the corresponding global filter improved patches-based method in both spatial and transform domain.

CONCLUSION

We propose a global denoising framework for 3D MRI which extracts information from the entire dataset to restore each voxel. This large weighting matrix of the global filter is approximated using Nyström low-rank approximation with an adaptive k-means clustering sampling scheme, which significantly reduce the sampling rate as well as the running time. The proposed method is capable of denoising in multimodal MRI dataset and can be used to improve currently used patch-based methods.