Accelerated free-breathing liver fat and R 2 * quantification using multi-echo stack-of-radial MRI with motion-resolved multidimensional regularized reconstruction: Initial retrospective evaluation.

PURPOSE: To improve image quality, mitigate quantification biases and variations for free-breathing liver proton density fat fraction (PDFF) and R 2 * $$ {\mathrm{R}}_2^{\ast } $$ quantification accelerated by radial k-space undersampling. METHODS: A free-breathing multi-echo stack-of-radial MRI method was developed with compressed sensing with multidimensional regularization. It was validated in motion phantoms with reference acquisitions without motion and in 11 subjects (6 patients with nonalcoholic fatty liver disease) with reference breath-hold Cartesian acquisitions. Images, PDFF, and R 2 * $$ {\mathrm{R}}_2^{\ast } $$ maps were reconstructed using different radial view k-space sampling factors and reconstruction settings. Results were compared with reference-standard results using Bland-Altman analysis. Using linear mixed-effects model fitting (p < 0.05 considered significant), mean and SD were evaluated for biases and variations of PDFF and R 2 * $$ {\mathrm{R}}_2^{\ast } $$ , respectively, and coefficient of variation on the first echo image was evaluated as a surrogate for image quality. RESULTS: Using the empirically determined optimal sampling factor of 0.25 in the accelerated in vivo protocols, mean differences and limits of agreement for the proposed method were [-0.5; -33.6, 32.7] s-1 for R 2 * $$ {\mathrm{R}}_2^{\ast } $$ and [-1.0%; -5.8%, 3.8%] for PDFF, close to those of a previous self-gating method using fully sampled radial views: [-0.1; -27.1, 27.0] s-1 for R 2 * $$ {\mathrm{R}}_2^{\ast } $$ and [-0.4%; -4.5%, 3.7%] for PDFF. The proposed method had significantly lower coefficient of variation than other methods (p < 0.001). Effective acquisition time of 64 s or 59 s was achieved, compared with 171 s or 153 s for two baseline protocols with different radial views corresponding to sampling factor of 1.0. CONCLUSION: This proposed method may allow accelerated free-breathing liver PDFF and R 2 * $$ {\mathrm{R}}_2^{\ast } $$ mapping with reduced biases and variations.

Automated abdominal adipose tissue segmentation and volume quantification on longitudinal MRI using 3D convolutional neural networks with multi-contrast inputs.

OBJECTIVE: Increased subcutaneous and visceral adipose tissue (SAT/VAT) volume is associated with risk for cardiometabolic diseases. This work aimed to develop and evaluate automated abdominal SAT/VAT segmentation on longitudinal MRI in adults with overweight/obesity using attention-based competitive dense (ACD) 3D U-Net and 3D nnU-Net with full field-of-view volumetric multi-contrast inputs. MATERIALS AND METHODS: 920 adults with overweight/obesity were scanned twice at multiple 3 T MRI scanners and institutions. The first scan was divided into training/validation/testing sets (n = 646/92/182). The second scan from the subjects in the testing set was used to evaluate the generalizability for longitudinal analysis. Segmentation performance was assessed by measuring Dice scores (DICE-SAT, DICE-VAT), false negatives (FN), and false positives (FP). Volume agreement was assessed using the intraclass correlation coefficient (ICC). RESULTS: ACD 3D U-Net achieved rapid (< 4.8 s/subject) segmentation with high DICE-SAT (median ≥ 0.994) and DICE-VAT (median ≥ 0.976), small FN (median ≤ 0.7%), and FP (median ≤ 1.1%). 3D nnU-Net yielded rapid (< 2.5 s/subject) segmentation with similar DICE-SAT (median ≥ 0.992), DICE-VAT (median ≥ 0.979), FN (median ≤ 1.1%) and FP (median ≤ 1.2%). Both models yielded excellent agreement in SAT/VAT volume versus reference measurements (ICC > 0.997) in longitudinal analysis. DISCUSSION: ACD 3D U-Net and 3D nnU-Net can be automated tools to quantify abdominal SAT/VAT volume rapidly, accurately, and longitudinally in adults with overweight/obesity.

High-resolution prostate diffusion MRI using eddy current-nulled convex optimized diffusion encoding and random matrix theory-based denoising.

OBJECTIVE: To develop and evaluate a technique combining eddy current-nulled convex optimized diffusion encoding (ENCODE) with random matrix theory (RMT)-based denoising to accelerate and improve the apparent signal-to-noise ratio (aSNR) and apparent diffusion coefficient (ADC) mapping in high-resolution prostate diffusion-weighted MRI (DWI). MATERIALS AND METHODS: Eleven subjects with clinical suspicion of prostate cancer were scanned at 3T with high-resolution (HR) (in-plane: 1.0 × 1.0 mm2) ENCODE and standard-resolution (1.6 × 2.2 mm2) bipolar DWI sequences (both had 7 repetitions for averaging, acquisition time [TA] of 5 min 50 s). HR-ENCODE was retrospectively analyzed using three repetitions (accelerated effective TA of 2 min 30 s). The RMT-based denoising pipeline utilized complex DWI signals and Marchenko-Pastur distribution-based principal component analysis to remove additive Gaussian noise in images from multiple coils, b-values, diffusion encoding directions, and repetitions. HR-ENCODE with RMT-based denoising (HR-ENCODE-RMT) was compared with HR-ENCODE in terms of aSNR in prostate peripheral zone (PZ) and transition zone (TZ). Precision and accuracy of ADC were evaluated by the coefficient of variation (CoV) between repeated measurements and mean difference (MD) compared to the bipolar ADC reference, respectively. Differences were compared using two-sided Wilcoxon signed-rank tests (P < 0.05 considered significant). RESULTS: HR-ENCODE-RMT yielded 62% and 56% higher median aSNR than HR-ENCODE (b = 800 s/mm2) in PZ and TZ, respectively (P < 0.001). HR-ENCODE-RMT achieved 63% and 70% lower ADC-CoV than HR-ENCODE in PZ and TZ, respectively (P < 0.001). HR-ENCODE-RMT ADC and bipolar ADC had low MD of 22.7 × 10-6 mm2/s in PZ and low MD of 90.5 × 10-6 mm2/s in TZ. CONCLUSIONS: HR-ENCODE-RMT can shorten the acquisition time and improve the aSNR of high-resolution prostate DWI and achieve accurate and precise ADC measurements in the prostate.

Using Free-Breathing MRI to Quantify Pancreatic Fat and Investigate Spatial Heterogeneity in Children.

BACKGROUND: MRI acquisition for pediatric pancreatic fat quantification is limited by breath-holds (BH). Full segmentation (FS) or small region of interest (ROI) analysis methods may not account for pancreatic fat spatial heterogeneity, which may limit accuracy. PURPOSE: To improve MRI acquisition and analysis for quantifying pancreatic proton-density fat fraction (pPDFF) in children by investigating free-breathing (FB)-MRI, characterizing pPDFF spatial heterogeneity, and relating pPDFF to clinical markers. STUDY TYPE: Prospective. POPULATION: A total of 34 children, including healthy (N = 16, 8 female) and overweight (N = 18, 5 female) subjects. FIELD STRENGTH AND SEQUENCES: 3 T; multiecho gradient-echo three-dimensional (3D) stack-of-stars FB-MRI, multiecho gradient-echo 3D Cartesian BH-MRI. ASSESSMENT: A radiologist measured FS- and ROI-based pPDFF on FB-MRI and BH-MRI PDFF maps, with anatomical images as references. Regional pPDFF in the pancreatic head, body, and tail were measured on FB-MRI. FS-pPDFF, ROI-pPDFF, and regional pPDFF were compared, and related to clinical markers, including hemoglobin A1c. STATISTICAL TESTS: T-test, Bland-Altman analysis, Lin's concordance correlation coefficient (CCC), one-way analysis of variance, and Spearman's rank correlation coefficient were used. P < 0.05 was considered significant. RESULTS: FS-pPDFF and ROI-pPDFF from FB-MRI and BH-MRI had mean difference = 0.4%; CCC was 0.95 for FS-pPDFF and 0.62 for ROI-pPDFF. FS-pPDFF was higher than ROI-pPDFF (10.4% ± 6.4% vs. 4.2% ± 2.8%). Tail-pPDFF (11.6% ± 8.1%) was higher than body-pPDFF (8.9% ± 6.3%) and head-pPDFF (8.7% ± 5.2%). Head-pPDFF and body-pPDFF positively correlated with hemoglobin A1c. DATA CONCLUSION: FB-MRI pPDFF is comparable to BH-MRI. Spatial heterogeneity affects pPDFF quantification. Regional measurements of pPDFF in the head and body were correlated with hemoglobin A1c, a marker of insulin sensitivity. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 2.

Uncertainty-aware physics-driven deep learning network for free-breathing liver fat and R2 * quantification using self-gated stack-of-radial MRI.

PURPOSE: To develop a deep learning-based method for rapid liver proton-density fat fraction (PDFF) and R2 * quantification with built-in uncertainty estimation using self-gated free-breathing stack-of-radial MRI. METHODS: This work developed an uncertainty-aware physics-driven deep learning network (UP-Net) to (1) suppress radial streaking artifacts because of undersampling after self-gating, (2) calculate accurate quantitative maps, and (3) provide pixel-wise uncertainty maps. UP-Net incorporated a phase augmentation strategy, generative adversarial network architecture, and an MRI physics loss term based on a fat-water and R2 * signal model. UP-Net was trained and tested using free-breathing multi-echo stack-of-radial MRI data from 105 subjects. UP-Net uncertainty scores were calibrated in a validation dataset and used to predict quantification errors for liver PDFF and R2 * in a testing dataset. RESULTS: Compared with images reconstructed using compressed sensing (CS), UP-Net achieved structural similarity index >0.87 and normalized root mean squared error <0.18. Compared with reference quantitative maps generated using CS and graph-cut (GC) algorithms, UP-Net achieved low mean differences (MD) for liver PDFF (-0.36%) and R2 * (-0.37 s-1 ). Compared with breath-holding Cartesian MRI results, UP-Net achieved low MD for liver PDFF (0.53%) and R2 * (6.75 s-1 ). UP-Net uncertainty scores predicted absolute liver PDFF and R2 * errors with low MD of 0.27% and 0.12 s-1 compared to CS + GC results. The computational time for UP-Net was 79 ms/slice, whereas CS + GC required 3.2 min/slice. CONCLUSION: UP-Net rapidly calculates accurate liver PDFF and R2 * maps from self-gated free-breathing stack-of-radial MRI. The pixel-wise uncertainty maps from UP-Net predict quantification errors in the liver.

Undersampling artifact reduction for free-breathing 3D stack-of-radial MRI based on a deep adversarial learning network.

PURPOSE: Stack-of-radial MRI allows free-breathing abdominal scans, however, it requires relatively long acquisition time. Undersampling reduces scan time but can cause streaking artifacts and degrade image quality. This study developed deep learning networks with adversarial loss and evaluated the performance of reducing streaking artifacts and preserving perceptual image sharpness. METHODS: A 3D generative adversarial network (GAN) was developed for reducing streaking artifacts in stack-of-radial abdominal scans. Training and validation datasets were self-gated to 5 respiratory states to reduce motion artifacts and to effectively augment the data. The network used a combination of three loss functions to constrain the anatomy and preserve image quality: adversarial loss, mean-squared-error loss and structural similarity index loss. The performance of the network was investigated for 3-5 times undersampled data from 2 institutions. The performance of the GAN for 5 times accelerated images was compared with a 3D U-Net and evaluated using quantitative NMSE, SSIM and region of interest (ROI) measurements as well as qualitative scores of radiologists. RESULTS: The 3D GAN showed similar NMSE (0.0657 vs. 0.0559, p = 0.5217) and significantly higher SSIM (0.841 vs. 0.798, p < 0.0001) compared to U-Net. ROI analysis showed GAN removed streaks in both the background air and the tissue and was not significantly different from the reference mean and variations. Radiologists' scores showed GAN had a significant improvement of 1.6 point (p = 0.004) on a 4-point scale in streaking score while no significant difference in sharpness score compared to the input. CONCLUSION: 3D GAN removes streaking artifacts and preserves perceptual image details.

Pregnancies complicated by gestational diabetes and fetal growth restriction: an analysis of maternal and fetal body composition using magnetic resonance imaging.

INTRODUCTION: Maternal body composition may influence fetal body composition. OBJECTIVE: The objective of this pilot study was to investigate the relationship between maternal and fetal body composition. METHODS: Three pregnant women cohorts were studied: healthy, gestational diabetes (GDM), and fetal growth restriction (FGR). Maternal body composition (visceral adipose tissue volume (VAT), subcutaneous adipose tissue volume (SAT), pancreatic and hepatic proton-density fat fraction (PDFF) and fetal body composition (abdominal SAT and hepatic PDFF) were measured using MRI between 30 to 36 weeks gestation. RESULTS: Compared to healthy and FGR fetuses, GDM fetuses had greater hepatic PDFF (5.2 [4.2, 5.5]% vs. 3.2 [3, 3.3]% vs. 1.9 [1.4, 3.7]%, p = 0.004). Fetal hepatic PDFF was associated with maternal SAT (r = 0.47, p = 0.02), VAT (r = 0.62, p = 0.002), and pancreatic PDFF (r = 0.54, p = 0.008). When controlling for maternal SAT, GDM increased fetal hepatic PDFF by 0.9 ([0.51, 1.3], p = 0.001). CONCLUSION: In this study, maternal SAT, VAT, and GDM status were positively associated with fetal hepatic PDFF.

Free-breathing radial magnetic resonance elastography of the liver in children at 3 T: a pilot study.

BACKGROUND: Magnetic resonance (MR) elastography of the liver measures hepatic stiffness, which correlates with the histopathological staging of liver fibrosis. Conventional Cartesian gradient-echo (GRE) MR elastography requires breath-holding, which is challenging for children. Non-Cartesian radial free-breathing MR elastography is a potential solution to this problem. OBJECTIVE: To investigate radial free-breathing MR elastography for measuring hepatic stiffness in children. MATERIALS AND METHODS: In this prospective pilot study, 14 healthy children and 9 children with liver disease were scanned at 3 T using 2-D Cartesian GRE breath-hold MR elastography (22 s/slice) and 2-D radial GRE free-breathing MR elastography (163 s/slice). Each sequence was acquired twice. Agreement in the stiffness measurements was evaluated using Lin's concordance correlation coefficient (CCC) and within-subject mean difference. The repeatability was assessed using the within-subject coefficient of variation and intraclass correlation coefficient (ICC). RESULTS: Fourteen healthy children and seven children with liver disease completed the study. Median (±interquartile range) normalized measurable liver areas were 62.6% (±26.4%) and 44.1% (±39.6%) for scan 1, and 60.3% (±21.8%) and 43.9% (±44.2%) for scan 2, for Cartesian and radial techniques, respectively. Hepatic stiffness from the Cartesian and radial techniques had close agreement with CCC of 0.89 and 0.94, and mean difference of 0.03 kPa and -0.01 kPa, for scans 1 and 2. Cartesian and radial techniques achieved similar repeatability with within-subject coefficient of variation=1.9% and 3.4%, and ICC=0.93 and 0.92, respectively. CONCLUSION: In this pilot study, radial free-breathing MR elastography was repeatable and in agreement with Cartesian breath-hold MR elastography in children.

Free-breathing 3D stack-of-radial MRI quantification of liver fat and R2* in adults with fatty liver disease.

PURPOSE: To investigate the agreement, intra-session repeatability, and inter-reader agreement of liver proton-density fat fraction (PDFF) and R2* quantification using free-breathing 3D stack-of-radial MRI, with and without self-gated motion compensation, compared to reference breath-hold techniques in subjects with fatty liver disease (FLD). METHODS: In this institutional review board-approved prospective study, thirty-eight adults with FLD and/or iron overload (24 male, 58 ± 12 years) were imaged at 3T using free-breathing stack-of-radial MRI, breath-hold 3D Cartesian MRI, and breath-hold single-voxel MR spectroscopy (SVS). Each sequence was acquired twice in random order. To assess agreement compared to reference breath-hold techniques, the dependency of liver PDFF and/or R2* quantification on the sequence, radial sampling factor, and radial self-gating temporal resolution was assessed by calculating the Bayesian mean difference (MDB) of the posteriors. Intra-session repeatability and inter-reader agreement (two independent readers) were assessed by the coefficient of repeatability (CR) and intraclass correlation coefficient (ICC), respectively. RESULTS: Thirty-five participants (21 male, 57 ± 12 years) were included for analysis. Both free-breathing radial MRI techniques (with and without self-gating) achieved ICC ≥ 0.92 for quantifying PDFF and R2*, and quantified PDFF with MDB < 1.2% compared to breath-hold techniques. Free-breathing radial MRI required self-gating to accurately quantify R2* (MDB < 10s-1 with self-gating; MDB < 50s-1 without self-gating). The radial sampling factor affected PDFF and R2* quantification while the radial self-gating temporal resolution only affected R2* quantification. Repeated self-gated free-breathing radial MRI scans achieved CR < 3% and CR < 27 s-1 for PDFF and R2*, respectively. CONCLUSION: A free-breathing stack-of-radial MRI technique with self-gating demonstrated agreement, repeatability, and inter-reader agreement compared to reference breath-hold techniques for quantification of liver PDFF and R2* in adults with FLD.

3D Neural Networks for Visceral and Subcutaneous Adipose Tissue Segmentation using Volumetric Multi-Contrast MRI.

Individuals with obesity have larger amounts of visceral (VAT) and subcutaneous adipose tissue (SAT) in their body, increasing the risk for cardiometabolic diseases. The reference standard to quantify SAT and VAT uses manual annotations of magnetic resonance images (MRI), which requires expert knowledge and is time-consuming. Although there have been studies investigating deep learning-based methods for automated SAT and VAT segmentation, the performance for VAT remains suboptimal (Dice scores of 0.43 to 0.89). Previous work had key limitations of not fully considering the multi-contrast information from MRI and the 3D anatomical context, which are critical for addressing the complex spatially varying structure of VAT. An additional challenge is the imbalance between the number and distribution of pixels representing SAT/VAT. This work proposes a network based on 3D U-Net that utilizes the full field-of-view volumetric T1-weighted, water, and fat images from dual-echo Dixon MRI as the multi-channel input to automatically segment SAT and VAT in adults with overweight/obesity. In addition, this work extends the 3D U-Net to a new Attention-based Competitive Dense 3D U-Net (ACD 3D U-Net) trained with a class frequency-balancing Dice loss (FBDL). In an initial testing dataset, the proposed 3D U-Net and ACD 3D U-Net with FBDL achieved 3D Dice scores of (mean ± standard deviation) 0.99 ±0.01 and 0.99±0.01 for SAT, and 0.95±0.04 and 0.96 ±0.04 for VAT, respectively, compared to manual annotations. The proposed 3D networks had rapid inference time (<60 ms/slice) and can enable automated segmentation of SAT and VAT.Clinical relevance- This work developed 3D neural networks to automatically, accurately, and rapidly segment visceral and subcutaneous adipose tissue on MRI, which can help to characterize the risk for cardiometabolic diseases such as diabetes, elevated glucose levels, and hypertension.

Electrical impedance tomography for non-invasive identification of fatty liver infiltrate in overweight individuals.

Non-alcoholic fatty liver disease (NAFLD) is one of the most common causes of cardiometabolic diseases in overweight individuals. While liver biopsy is the current gold standard to diagnose NAFLD and magnetic resonance imaging (MRI) is a non-invasive alternative still under clinical trials, the former is invasive and the latter costly. We demonstrate electrical impedance tomography (EIT) as a portable method for detecting fatty infiltrate. We enrolled 19 overweight subjects to undergo liver MRI scans, followed by EIT measurements. The MRI images provided the a priori knowledge of the liver boundary conditions for EIT reconstruction, and the multi-echo MRI data quantified liver proton-density fat fraction (PDFF%) to validate fat infiltrate. Using the EIT electrode belts, we circumferentially injected pairwise current to the upper abdomen, followed by acquiring the resulting surface-voltage to reconstruct the liver conductivity. Pearson's correlation analyses compared EIT conductivity or MRI PDFF with body mass index, age, waist circumference, height, and weight variables. We reveal that the correlation between liver EIT conductivity or MRI PDFF with demographics is statistically insignificant, whereas liver EIT conductivity is inversely correlated with MRI PDFF (R = -0.69, p = 0.003, n = 16). As a pilot study, EIT conductivity provides a portable method for operator-independent and cost-effective detection of hepatic steatosis.

Deep Learning-Based Parameter Mapping with Uncertainty Estimation for Fat Quantification using Accelerated Free-Breathing Radial MRI.

Deep learning has been applied to remove artifacts from undersampled MRI and to replace time-consuming signal fitting in quantitative MRI, but these have usually been treated as separate tasks, which does not fully exploit the shared information. This work proposes a new two-stage framework that completes these two tasks in a concerted approach and also estimates the pixel-wise uncertainty levels. Results from accelerated free-breathing radial MRI for liver fat quantification demonstrate that the proposed framework can achieve high image quality from undersampled radial data, high accuracy for liver fat quantification, and detect uncertainty caused by noisy input data. The proposed framework achieved 3-fold acceleration to <1 min scan time and reduced the computational time for signal fitting to <100 ms/slice in free-breathing liver fat quantification.