JUST-Net: Jointly unrolled cross-domain optimization based spatio-temporal reconstruction network for accelerated 3D myelin water imaging.

PURPOSE: We introduced a novel reconstruction network, jointly unrolled cross-domain optimization-based spatio-temporal reconstruction network (JUST-Net), aimed at accelerating 3D multi-echo gradient-echo (mGRE) data acquisition and improving the quality of resulting myelin water imaging (MWI) maps. METHOD: An unrolled cross-domain spatio-temporal reconstruction network was designed. The main idea is to combine frequency and spatio-temporal image feature representations and to sequentially implement convolution layers in both domains. The k-space subnetwork utilizes shared information from adjacent frames, whereas the image subnetwork applies separate convolutions in both spatial and temporal dimensions. The proposed reconstruction network was evaluated for both retrospectively and prospectively accelerated acquisition. Furthermore, it was assessed in simulation studies and real-world cases with k-space corruptions to evaluate its potential for motion artifact reduction. RESULTS: The proposed JUST-Net enabled highly reproducible and accelerated 3D mGRE acquisition for whole-brain MWI, reducing the acquisition time from fully sampled 15:23 to 2:22 min within a 3-min reconstruction time. The normalized root mean squared error of the reconstructed mGRE images increased by less than 4.0%, and the correlation coefficients for MWI showed a value of over 0.68 when compared to the fully sampled reference. Additionally, the proposed method demonstrated a mitigating effect on both simulated and clinical motion-corrupted cases. CONCLUSION: The proposed JUST-Net has demonstrated the capability to achieve high acceleration factors for 3D mGRE-based MWI, which is expected to facilitate widespread clinical applications of MWI.

Improving high frequency image features of deep learning reconstructions via k-space refinement with null-space kernel.

PURPOSE: Deep learning (DL) based reconstruction using unrolled neural networks has shown great potential in accelerating MRI. However, one of the major drawbacks is the loss of high-frequency details and textures in the output. The purpose of the study is to propose a novel refinement method that uses null-space kernel to refine k-space and improve blurred image details and textures. METHODS: The proposed method constrains the output of the DL to comply to the linear neighborhood relationship calibrated in the auto-calibration lines. To demonstrate efficacy, we tested our refinement method on the DL reconstruction under a variety of conditions (i.e., dataset, unrolled neural networks, and under-sampling scheme). Specifically, the method was tested on three large-scale public datasets (knee and brain) from fastMRI's multi-coil track. RESULTS: The proposed scheme visually reduces the structural error in the k-space domain, enhance the homogeneity of the k-space intensity. Consequently, reconstructed image shows sharper images with enhanced details and textures. The proposed method is also successful in improving high-frequency image details (SSIM, GMSD) without sacrificing overall image error (PSNR). CONCLUSION: Our findings imply that refining DL output using the proposed method may generally improve DL reconstruction as tested with various large-scale dataset and networks.

Artificial neural network for multi-echo gradient echo-based myelin water fraction estimation.

PURPOSE: To demonstrate robust myelin water fraction (MWF) mapping using an artificial neural network (ANN) with multi-echo gradient-echo (GRE) signal. METHODS: Multi-echo gradient-echo signals simulated with a three-pool exponential model were used to generate the training data set for the ANN, which was designed to yield the MWF. We investigated the performance of our proposed ANN for various conditions using both numerical simulations and in vivo data. Simulations were conducted with various SNRs to investigate the performance of the ANN. In vivo data with high spatial resolutions were applied in the analyses, and results were compared with MWFs derived by the nonlinear least-squares algorithm using a complex three-pool exponential model. RESULTS: The network results for the simulations show high accuracies against noise compared with nonlinear least-squares MWFs: RMS-error value of 5.46 for the nonlinear least-squares MWF and 3.56 for the ANN MWF at an SNR of 150 (relative gain = 34.80%). These effects were also found in the in vivo data, with reduced SDs in the region-of-interest analyses. These effects of the ANN demonstrate the feasibility of acquiring high-resolution myelin water images. CONCLUSION: The simulation results and in vivo data suggest that the ANN facilitates more robust MWF mapping in multi-echo gradient-echo sequences compared with the conventional nonlinear least-squares method.

Improving phase-based conductivity reconstruction by means of deep learning-based denoising of B1+ phase data for 3T MRI.

PURPOSE: To denoise B1+ phase using a deep learning method for phase-based in vivo electrical conductivity reconstruction in a 3T MR system. METHODS: For B1+ phase deep-learning denoising, a convolutional neural network (U-net) was chosen. Training was performed on data sets from 10 healthy volunteers. Input data were the real and imaginary components of single averaged spin-echo data (SNR = 45), which was used to approximate the B1+ phase. For label data, multiple signal-averaged spin-echo data (SNR = 128) were used. Testing was performed on in silico and in vivo data. Reconstructed conductivity maps were derived using phase-based conductivity reconstructions. Additionally, we investigated the usability of the network to various SNR levels, imaging contrasts, and anatomical sites (ie, T1 , T2 , and proton density-weighted brain images and proton density-weighted breast images. In addition, conductivity reconstructions from deep learning-based denoised data were compared with conventional image filters, which were used for data denoising in electrical properties tomography (ie, the Gaussian filtering and the Savitzky-Golay filtering). RESULTS: The proposed deep learning-based denoising approach showed improvement for B1+ phase for both in silico and in vivo experiments with reduced quantitative error measures compared with other methods. Subsequently, this resulted in an improvement of reconstructed conductivity maps from the denoised B1+ phase with deep learning. CONCLUSION: The results suggest that the proposed approach can be used as an alternative preprocessing method to denoise B1+ maps for phase-based conductivity reconstruction without relying on image filters or signal averaging.

Multi-echo GRE-based conductivity imaging using Kalman phase estimation method.

PURPOSE: To obtain in vivo electrical conductivity images from multi-echo gradient-echo (mGRE) sequence using a zero-TE phase extrapolation algorithm based on the Kalman method. METHODS: For estimation of the zero-TE phase from the mGRE data, an iterative algorithm consisting of a combination of the Kalman filter, Kalman smoother, and expectation maximization was implemented and compared with linear extrapolation methods. Simulations were performed for verification, and phantom and in vivo studies were conducted for validation. RESULTS: Compared with the conventional method that linearly extrapolates the zero-TE phase from the mGRE data, the phase estimation of the proposed method was more stable in situations in which nonlinear phase evolution exists. Numerical simulation results showed that the stability is guaranteed under various nonlinearity levels. Phantom study results show that this method provides improved conductivity imaging compared with the conventional methods. In vivo results demonstrate conductivity images similar to spin echo-based conductivity images with the added benefit of the acquisition of susceptibility images when using mGRE. CONCLUSION: The proposed method improves zero-TE phase extrapolation, especially in regions of nonlinear phase evolution. Improved conductivity imaging using mGRE can be performed.

Data-driven synthetic MRI FLAIR artifact correction via deep neural network.

BACKGROUND: FLAIR (fluid attenuated inversion recovery) imaging via synthetic MRI methods leads to artifacts in the brain, which can cause diagnostic limitations. The main sources of the artifacts are attributed to the partial volume effect and flow, which are difficult to correct by analytical modeling. In this study, a deep learning (DL)-based synthetic FLAIR method was developed, which does not require analytical modeling of the signal. PURPOSE: To correct artifacts in synthetic FLAIR using a DL method. STUDY TYPE: Retrospective. SUBJECTS: A total of 80 subjects with clinical indications (60.6 ± 16.7 years, 38 males, 42 females) were divided into three groups: a training set (56 subjects, 62.1 ± 14.8 years, 25 males, 31 females), a validation set (1 subject, 62 years, male), and the testing set (23 subjects, 57.3 ± 20.4 years, 13 males, 10 females). FIELD STRENGTH/SEQUENCE: 3 T MRI using a multiple-dynamic multiple-echo acquisition (MDME) sequence for synthetic MRI and a conventional FLAIR sequence. ASSESSMENT: Normalized root mean square (NRMSE) and structural similarity (SSIM) were computed for uncorrected synthetic FLAIR and DL-corrected FLAIR. In addition, three neuroradiologists scored the three FLAIR datasets blindly, evaluating image quality and artifacts for sulci/periventricular and intraventricular/cistern space regions. STATISTICAL TESTS: Pairwise Student's t-tests and a Wilcoxon test were performed. RESULTS: For quantitative assessment, NRMSE improved from 4.2% to 2.9% (P < 0.0001) and SSIM improved from 0.85 to 0.93 (P < 0.0001). Additionally, NRMSE values significantly improved from 1.58% to 1.26% (P < 0.001), 3.1% to 1.5% (P < 0.0001), and 2.7% to 1.4% (P < 0.0001) in white matter, gray matter, and cerebral spinal fluid (CSF) regions, respectively, when using DL-corrected FLAIR. For qualitative assessment, DL correction achieved improved overall quality, fewer artifacts in sulci and periventricular regions, and in intraventricular and cistern space regions. DATA CONCLUSION: The DL approach provides a promising method to correct artifacts in synthetic FLAIR. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;50:1413-1423.

Accelerating High b-Value Diffusion-Weighted MRI Using a Convolutional Recurrent Neural Network (CRNN-DWI).

PURPOSE: To develop a novel convolutional recurrent neural network (CRNN-DWI) and apply it to reconstruct a highly undersampled (up to six-fold) multi-b-value, multi-direction diffusion-weighted imaging (DWI) dataset. METHODS: A deep neural network that combines a convolutional neural network (CNN) and recurrent neural network (RNN) was first developed by using a set of diffusion images as input. The network was then used to reconstruct a DWI dataset consisting of 14 b-values, each with three diffusion directions. For comparison, the dataset was also reconstructed with zero-padding and 3D-CNN. The experiments were performed with undersampling rates (R) of 4 and 6. Standard image quality metrics (SSIM and PSNR) were employed to provide quantitative assessments of the reconstructed image quality. Additionally, an advanced non-Gaussian diffusion model was employed to fit the reconstructed images from the different approaches, thereby generating a set of diffusion parameter maps. These diffusion parameter maps from the different approaches were then compared using SSIM as a metric. RESULTS: Both the reconstructed diffusion images and diffusion parameter maps from CRNN-DWI were better than those from zero-padding or 3D-CNN. Specifically, the average SSIM and PSNR of CRNN-DWI were 0.750 ± 0.016 and 28.32 ± 0.69 (R = 4), and 0.675 ± 0.023 and 24.16 ± 0.77 (R = 6), respectively, both of which were substantially higher than those of zero-padding or 3D-CNN reconstructions. The diffusion parameter maps from CRNN-DWI also yielded higher SSIM values for R = 4 (>0.8) and for R = 6 (>0.7) than the other two approaches (for R = 4, <0.7, and for R = 6, <0.65). CONCLUSIONS: CRNN-DWI is a viable approach for reconstructing highly undersampled DWI data, providing opportunities to reduce the data acquisition burden.

Multi-planar 2.5D U-Net for image quality enhancement of dental cone-beam CT.

Cone-beam computed tomography (CBCT) can provide 3D images of a targeted area with the advantage of lower dosage than multidetector computed tomography (MDCT; also simply referred to as CT). However, in CBCT, due to the cone-shaped geometry of the X-ray source and the absence of post-patient collimation, the presence of more scattering rays deteriorates the image quality compared with MDCT. CBCT is commonly used in dental clinics, and image artifacts negatively affect the radiology workflow and diagnosis. Studies have attempted to eliminate image artifacts and improve image quality; however, a vast majority of that work sacrificed structural details of the image. The current study presents a novel approach to reduce image artifacts while preserving details and sharpness in the original CBCT image for precise diagnostic purposes. We used MDCT images as reference high-quality images. Pairs of CBCT and MDCT scans were collected retrospectively at a university hospital, followed by co-registration between the CBCT and MDCT images. A contextual loss-optimized multi-planar 2.5D U-Net was proposed. Images corrected using this model were evaluated quantitatively and qualitatively by dental clinicians. The quantitative metrics showed superior quality in output images compared to the original CBCT. In the qualitative evaluation, the generated images presented significantly higher scores for artifacts, noise, resolution, and overall image quality. This proposed novel approach for noise and artifact reduction with sharpness preservation in CBCT suggests the potential of this method for diagnostic imaging.

Accelerated 3D myelin water imaging using joint spatio-temporal reconstruction.

PURPOSE: To enable acceleration in 3D multi-echo gradient echo (mGRE) acquisition for myelin water imaging (MWI) by combining joint parallel imaging (JPI) and joint deep learning (JDL). METHODS: We implemented a multistep reconstruction process using both advanced parallel imaging and deep learning network which can utilize joint spatiotemporal components between the multi-echo images to further accelerate 3D mGRE acquisition for MWI. In the first step, JPI was performed to estimate missing k-space lines. Next, JDL was implemented to reduce residual artifacts and produce high-fidelity reconstruction by using variable splitting optimization consisting of spatiotemporal denoiser block, data consistency block, and weighted average block. The proposed method was evaluated for MWI with 2D Cartesian uniform under-sampling for each echo, enabling scan times of up to approximately 2 min for 2 mm × 2 mm × 2 mm $2\ {\rm mm} \times 2\ {\rm mm} \times 2\ {\rm mm}$ 3D coverage. RESULTS: The proposed method showed acceptable MWI quality with improved quantitative values compared to both JPI and JDL methods individually. The improved performance of the proposed method was demonstrated by the low normalized mean-square error and high-frequency error norm values of the reconstruction with high similarity to the fully sampled MWI. CONCLUSION: Joint spatiotemporal reconstruction approach by combining JPI and JDL can achieve high acceleration factors for 3D mGRE-based MWI.

Accelerated multicontrast reconstruction for synthetic MRI using joint parallel imaging and variable splitting networks.

PURPOSE: Synthetic magnetic resonance imaging (MRI) requires the acquisition of multicontrast images to estimate quantitative parameter maps, such as T1 , T2 , and proton density (PD). The study aims to develop a multicontrast reconstruction method based on joint parallel imaging (JPI) and joint deep learning (JDL) to enable further acceleration of synthetic MRI. METHODS: The JPI and JDL methods are extended and combined to improve reconstruction for better-quality, synthesized images. JPI is performed as a first step to estimate the missing k-space lines, and JDL is then performed to correct and refine the previous estimate with a trained neural network. For the JDL architecture, the original variable splitting network (VS-Net) is modified and extended to form a joint variable splitting network (JVS-Net) to apply to multicontrast reconstructions. The proposed method is designed and tested for multidynamic multiecho (MDME) images with Cartesian uniform under-sampling using acceleration factors between 4 and 8. RESULTS: It is demonstrated that the normalized root-mean-square error (nRMSE) is lower and the structural similarity index measure (SSIM) values are higher with the proposed method compared to both the JPI and JDL methods individually. The method also demonstrates the potential to produce a set of synthesized contrast-weighted images that closely resemble those from the fully sampled acquisition without erroneous artifacts. CONCLUSION: Combining JPI and JDL enables the reconstruction of highly accelerated synthetic MRIs.

Validation of Deep Learning-Based Artifact Correction on Synthetic FLAIR Images in a Different Scanning Environment.

We investigated the capability of a trained deep learning (DL) model with a convolutional neural network (CNN) in a different scanning environment in terms of ameliorating the quality of synthetic fluid-attenuated inversion recovery (FLAIR) images. The acquired data of 319 patients obtained from the retrospective review were used as test sets for the already trained DL model to correct the synthetic FLAIR images. Quantitative analyses were performed for native synthetic FLAIR and DL-FLAIR images against conventional FLAIR images. Two neuroradiologists assessed the quality and artifact degree of the native synthetic FLAIR and DL-FLAIR images. The quantitative parameters showed significant improvement on DL-FLAIR in all individual tissue segments and total intracranial tissues than on the native synthetic FLAIR (p < 0.0001). DL-FLAIR images showed improved image quality with fewer artifacts than the native synthetic FLAIR images (p < 0.0001). There was no significant difference in the preservation of the periventricular white matter hyperintensities and lesion conspicuity between the two FLAIR image sets (p = 0.217). The quality of synthetic FLAIR images was improved through artifact correction using the trained DL model on a different scan environment. DL-based correction can be a promising solution for ameliorating the quality of synthetic FLAIR images to broaden the clinical use of synthetic magnetic resonance imaging (MRI).

Estimating age-related changes in in vivo cerebral magnetic resonance angiography using convolutional neural network.

Although age-related changes of cerebral arteries were observed in in vivo magnetic resonance angiography (MRA), standard tools or methods measuring those changes were limited. In this study, we developed and evaluated a model to measure age-related changes in the cerebral arteries from 3D MRA using a 3D deep convolutional neural network. From participants without any medical abnormality, training (n = 800) and validation sets (n = 88) of 3D MRA were built. After preprocessing and data augmentation, a 3D convolutional neural network was trained to estimate each subject's chronological age from in vivo MRA data. There was good correlation between chronological age and predicted age (r = 0.83) in an independent test set (n = 354). The predicted age difference (PAD) of the test set was 2.41 ± 6.22. Interaction term between age and sex was significant for PAD (p = 0.008). After correcting for age and interaction term, men showed higher PAD (p < 0.001). Hypertension was associated with higher PAD with marginal significance (p = 0.073). We suggested that PAD might be a potential measurement of cerebral vascular aging.

Synthesizing T1 weighted MPRAGE image from multi echo GRE images via deep neural network.

For quantitative neuroimaging studies using multi-echo gradient echo (mGRE) images, additional T1-weighted magnetization prepared rapid gradient echo (MPRAGE) images are often acquired to supplement the insufficient morphometric information of mGRE for tissue segmentation which require lengthened scan time and additional processing such as image registration. This study investigated the feasibility of generating synthetic MPRAGE images from mGRE images using a deep convolutional neural network. Tissue segmentation results derived from the synthetic MPRAGE showed good agreement with those from actual MPRAGE (DSC = 0.882 ±â€¯0.017). There was no statistically significant difference between the mean susceptibility values obtained with the regions of interest from synthetic and actual MPRAGEs and high correlation between the two measurements.

Regulation of root patterns in mammalian teeth.

Mammalian teeth have diverse pattern of the crown and root. The patterning mechanism of the root position and number is relatively unknown compared to that of the crown. The root number does not always match to the cusp number, which has prevented the complete understanding of root patterning. In the present study, to elucidate the mechanism of root pattern formation, we examined (1) the pattern of cervical tongues, which are tongue-like epithelial processes extending from cervical loops, (2) factors influencing the cervical tongue pattern and (3) the relationship among patterns of cusp, cervical tongue and root in multi-rooted teeth. We found a simple mechanism of cervical tongue formation in which the lateral growth of dental mesenchyme in the cuspal region pushes the cervical loop outward, and the cervical tongue appears in the intercuspal region subsequently. In contrast, when lateral growth was physically inhibited, cervical tongue formation was suppressed. Furthermore, by building simple formulas to predict the maximum number of cervical tongues and roots based on the cusp pattern, we demonstrated a positive relationship among cusp, cervical tongue and root numbers. These results suggest that the cusp pattern and the lateral growth of cusps are important in the regulation of the root pattern.

Endothelium- and smooth muscle-dependent vasodilator effects of Citrus aurantium L. var. amara: Focus on Ca(2+) modulation.

Neroli, the essential oil of Citrus aurantium L. var. amara, is a well-characterized alleviative agent used to treat cardiovascular symptoms. However, because it has been found to have multiple effects, its mechanism of action requires further exploration. We sought to clarify the mechanism underlying the actions of neroli in mouse aorta. In aortic rings from mice precontracted with prostaglandin F2 alpha, neroli induced vasodilation. However, relaxation effect of neroli was decreased in endothelium-denuded ring or pre-incubation with the nitric oxide synthase inhibitor NG-Nitro-l-arginine-methyl ester (L-NAME). And also, neroli-induced relaxation was also partially reversed by 1H-[1,2,4] oxadiazolo [4,3-a] quinoxalin-1-one (ODQ), a soluble guanylyl cyclase (sGC) inhibitor. In addition, neroli inhibited extracellular Ca(2+)-dependent, depolarization-induced contraction, an effect that was concentration dependent. Pretreatment with the non-selective cation channel blocker, Ni(2+), attenuated neroli-induced relaxation, whereas the K(+) channel blocker, tetraethylammonium chloride, had no effect. In the presence of verapamil, added to prevent Ca(2+) influx via smooth muscle voltage-gated Ca(2+) channels, neroli-induced relaxation was reduced by the ryanodine receptor (RyR) inhibitor ruthenium red. Our findings further indicate that the endothelial component of neroli-induced vasodilation is partly mediated by the NO-sGC pathway, whereas the smooth muscle component involves modulation of intracellular Ca(2+) concentration through inhibition of cation channel-mediated extracellular Ca(2+) influx and store-operated Ca(2+) release mediated by the RyR signaling pathway.