Deep learning how to fit an intravoxel incoherent motion model to diffusion‐weighted MRI

Reproducibility of intravoxel incoherent motion quantification in the liver across field strengths and gradient hardware

PURPOSE

To evaluate reproducibility and interlobar agreement of intravoxel incoherent motion (IVIM) quantification in the liver across field strengths and MR scanners with different gradient hardware.

METHODS

Cramer-Rao lower bound optimization was performed to determine optimized monopolar and motion-robust 2D (b-value and first-order motion moment [M1]) IVIM-DWI acquisitions. Eleven healthy volunteers underwent diffusion MRI of the liver, where each optimized acquisition was obtained five times across three MRI scanners. For each data set, IVIM estimates (diffusion coefficient (D), pseudo-diffusion coefficients (d 1 * $$ {d}_1^{\ast } $$ andd 2 * $$ {d}_2^{\ast } $$ ), blood velocity SDs (Vb1 and Vb2), and perfusion fractions [f1 and f2]) were obtained in the right and left liver lobes using two signal models (pseudo-diffusion and M1-dependent physical) with and without T2 correction (fc1 and fc2) and three fitting techniques (tri-exponential region of interest-based full and segmented fitting and blood velocity SD distribution fitting). Reproducibility and interlobar agreement were compared across methods using within-subject and pairwise coefficients of variation (CVw and CVp), paired sample t-tests, and Bland-Altman analysis.

RESULTS

Using a combination of motion-robust 2D (b-M1) data acquisition, M1-dependent physical signal modeling with T2 correction, and blood velocity SD distribution fitting, multiscanner reproducibility with median CVw = 5.09%, 11.3%, 9.20%, 14.2%, and 12.6% for D, Vb1, Vb2, fc1, and fc2, respectively, and interlobar agreement with CVp = 8.14%, 11.9%, 8.50%, 49.9%, and 42.0%, respectively, was achieved.

CONCLUSION

Recently proposed advanced IVIM acquisition, signal modeling, and fitting techniques may facilitate reproducible IVIM quantification in the liver, as needed for establishment of IVIM-based quantitative biomarkers for detection, staging, and treatment monitoring of diseases.

Physics-guided self-supervised learning for retrospective T1 and T2 mapping from conventional weighted brain MRI: Technical developments and initial validation in glioblastoma

PURPOSE

To develop a self-supervised learning method to retrospectively estimate T1 and T2 values from clinical weighted MRI.

METHODS

A self-supervised learning approach was constructed to estimate T1, T2, and proton density maps from conventional T1- and T2-weighted images. MR physics models were employed to regenerate the weighted images from the network outputs, and the network was optimized based on loss calculated between the synthesized and input weighted images, alongside additional constraints based on prior information. The method was evaluated on healthy volunteer data, with conventional mapping as references. The reproducibility was examined on two 3.0T scanners. Performance in tumor characterization was inspected by applying the method to a public glioblastoma dataset.

RESULTS

For T1 and T2 estimation from three weighted images (T1 MPRAGE, T1 gradient echo sequences, and T2 turbo spin echo), the deep learning method achieved global voxel-wise error ≤9% in brain parenchyma and regional error ≤12.2% in six types of brain tissues. The regional measurements obtained from two scanners showed mean differences ≤2.4% and correlation coefficients >0.98, demonstrating excellent reproducibility. In the 50 glioblastoma patients, the retrospective quantification results were in line with literature reports from prospective methods, and the T2 values were found to be higher in tumor regions, with sensitivity of 0.90 and specificity of 0.92 in a voxel-wise classification task between normal and abnormal regions.

CONCLUSION

The self-supervised learning method is promising for retrospective T1 and T2 quantification from clinical MR images, with the potential to improve the availability of quantitative MRI and facilitate brain tumor characterization.

Diffusion-derived intravoxel-incoherent motion anisotropy relates to CSF and blood flow

This study investigates the feasibility of multi-b-value, multi-directional diffusion MRI for assessing the anisotropy of the cerebral pseudo-diffusion (D*)-tensor. We examine D*-tensor's potential to (1) reflect CSF and blood flow, and (2) detect microvascular architectural alterations in cerebral small vessel disease (cSVD) and aging.

METHODS

Multi-b-value diffusion MRI was acquired in 32 gradient directions for 11 healthy volunteers, and in six directions for 29 patients with cSVD and 14 controls at 3 T. A physics-informed neural network was used to estimate intravoxel incoherent motion (IVIM)-DTI model parameters, including the parenchymal slow diffusion (D-)tensor and the pseudo-diffusion (D*)-tensor, from which the fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD) were derived. Comparisons of D*-tensor metrics were made between lateral, third, and fourth ventricles and between the middle cerebral arteries and superior sagittal sinus. Group differences in D*-tensor metrics in normal-appearing white matter were analyzed using multivariable linear regression, correcting for age and sex.

RESULTS

D*-anisotropy aligned well with CSF flow and arterial blood flow. FA(D*), MD(D*), AD(D*), and RD(D*) were highest in the third, moderate in the fourth, and lowest in the lateral ventricles. The arteries showed higher MD(D*), AD(D*), and RD(D*) than the sagittal sinus. Higher FA(D*) in the normal-appearing white matter was related to cSVD diagnosis and older age, suggesting microvascular architecture alterations.

CONCLUSION

Multi-b-value, multi-directional diffusion analysis using the IVIM-DTI model enables assessment of the cerebral microstructure, fluid flow, and microvascular architecture, providing information on neurodegeneration, glymphatic waste clearance, and the vasculature in one measurement.

ssVERDICT: Self-supervised VERDICT-MRI for enhanced prostate tumor characterization

PURPOSE

Demonstrating and assessing self-supervised machine-learning fitting of the VERDICT (vascular, extracellular and restricted diffusion for cytometry in tumors) model for prostate cancer.

METHODS

We derive a self-supervised neural network for fitting VERDICT (ssVERDICT) that estimates parameter maps without training data. We compare the performance of ssVERDICT to two established baseline methods for fitting diffusion MRI models: conventional nonlinear least squares and supervised deep learning. We do this quantitatively on simulated data by comparing the Pearson's correlation coefficient, mean-squared error, bias, and variance with respect to the simulated ground truth. We also calculate in vivo parameter maps on a cohort of 20 prostate cancer patients and compare the methods' performance in discriminating benign from cancerous tissue via Wilcoxon's signed-rank test.

RESULTS

In simulations, ssVERDICT outperforms the baseline methods (nonlinear least squares and supervised deep learning) in estimating all the parameters from the VERDICT prostate model in terms of Pearson's correlation coefficient, bias, and mean-squared error. In vivo, ssVERDICT shows stronger lesion conspicuity across all parameter maps, and improves discrimination between benign and cancerous tissue over the baseline methods.

CONCLUSION

ssVERDICT significantly outperforms state-of-the-art methods for VERDICT model fitting and shows, for the first time, fitting of a detailed multicompartment biophysical diffusion MRI model with machine learning without the requirement of explicit training labels.

Enhanced parameter estimation in multiparametric arterial spin labeling using artificial neural networks

PURPOSE

Multiparametric arterial spin labeling (MP-ASL) can quantify cerebral blood flow (CBF) and arterial cerebral blood volume (CBVa). However, its accuracy is compromised owing to its intrinsically low SNR, necessitating complex and time-consuming parameter estimation. Deep neural networks (DNNs) offer a solution to these limitations. Therefore, we aimed to develop simulation-based DNNs for MP-ASL and compared the performance of a supervised DNN (DNNSup), physics-informed unsupervised DNN (DNNUns), and the conventional lookup table method (LUT) using simulation and in vivo data.

METHODS

MP-ASL was performed twice during resting state and once during the breath-holding task. First, the accuracy and noise immunity were evaluated in the first resting state. Second, CBF and CBVa values were statistically compared between the first resting state and the breath-holding task using the Wilcoxon signed-rank test and Cliff's delta. Finally, reproducibility of the two resting states was assessed.

RESULTS

Simulation and first resting-state analyses demonstrated that DNNSup had higher accuracy, noise immunity, and a six-fold faster computation time than LUT. Furthermore, all methods detected task-induced CBF and CBVa elevations, with the effect size being larger with the DNNSup (CBF, p = 0.055, Δ = 0.286; CBVa, p = 0.008, Δ = 0.964) and DNNUns (CBF, p = 0.039, Δ = 0.286; CBVa, p = 0.008, Δ = 1.000) than that with LUT (CBF, p = 0.109, Δ = 0.214; CBVa, p = 0.008, Δ = 0.929). Moreover, all the methods exhibited comparable and satisfactory reproducibility.

CONCLUSION

DNNSup outperforms DNNUns and LUT with respect to estimation performance and computation time.

Inter-visit and inter-reader reproducibility of multi-parametric diffusion-weighted MR imaging in longitudinally imaged patients with metabolic dysfunction-associated fatty liver disease and healthy volunteers

BACKGROUND

Despite the widespread use of diffusion-weighted imaging (DWI) in metabolic dysfunction-associated fatty liver disease (MAFLD), MRI acquisition and quantification techniques vary in the literature suggesting the need for established and reproducible protocols. The goal of this study was to assess inter-visit and inter-reader reproducibility of DWI- and IVIM-derived parameters in patients with MAFLD and healthy volunteers using extensive sampling of the "fast" compartment, non-rigid registration, and exclusion voxels with poor fit quality.

METHODS

From June 2019 to April 2023, 31 subjects (20 patients with biopsy-proven MAFLD and 11 healthy volunteers) were included in this IRB-approved study. Subjects underwent MRI examinations twice within 40 days. 3.0 T DWI was acquired using a respiratory-triggered spin-echo diffusion-weighted echo-planar imaging sequence (b-values of 0, 10, 20, 30, 40, 50, 100, 200, 400, 800 s/mm2). DWI series were co-registered prior to voxel-wise non-linear regression of the IVIM model and voxels with poor fit quality were excluded (normalized root mean squared error ≥ 0.05). IVIM parameters (perfusion fraction, f; diffusion coefficient, D; and pseudo-diffusion coefficient, D*), and apparent diffusion coefficients (ADC) were computed from manual segmentation of the right liver lobe performed by two analysts on two MRI examinations.

RESULTS

All results are reported for f, D, D*, and ADC respectively. For inter-reader agreement on the first visit, ICC were of 0.985, 0.994, 0.986, and 0.993 respectively. For intra-reader agreement of analyst 1 assessed on both imaging examinations, ICC between visits were of 0.805, 0.759, 0.511, and 0.850 respectively. For inter-reader agreement on the first visit, mean bias and 95 % limits of agreement were (0.00 ± 0.03), (-0.01 ± 0.03) × 10-3 mm2/s, (0.70 ± 10.40) × 10-3 mm2/s, and (-0.02 ± 0.04) × 10-3 mm2/s respectively. For intra-reader agreement of analyst 1, mean bias and 95 % limits of agreement were (0.01 ± 0.09) × 10-3 mm2/s, (-0.01 ± 0.21) × 10-3 mm2/s, (-13.37 ± 56.19) × 10-3 mm2/s, and (-0.01 ± 0.16) × 10-3 mm2/s respectively. Except for parameter D* that was associated with between-subjects parameter variability (P = 0.009), there was no significant variability between subjects, examinations, or readers.

CONCLUSION

With our approach, IVIM parameters f, D, D*, and ADC provided excellent inter-reader agreement and good to very good inter-visit or intra-reader agreement, thus showing the reproducibility of IVIM-DWI of the liver in MAFLD patients and volunteers.

Comparison between supervised and physics-informed unsupervised deep neural networks for estimating cerebral perfusion using multi-delay arterial spin labeling MRI

This study aimed to implement a physics-informed unsupervised deep neural network (DNN) to estimate cerebral blood flow (CBF) and arterial transit time (ATT) from multi-delay arterial spin labeling (ASL), and compare its performance with that of a supervised DNN and the conventional method. Supervised and unsupervised DNNs were trained using simulation data. The accuracy and noise immunity of the three methods were compared using simulations and in vivo data. The simulation study investigated the differences between the predicted and ground-truth values and their variations with the noise level. The in vivo study evaluated the predicted values from the original images and noise-induced variations in the predicted values from the synthesized noisy images by adding Rician noise to the original images. The simulation study showed that CBF estimated using the supervised DNN was not biased by noise, whereas that estimated using other methods had a positive bias. Although the ATT with all methods exhibited a similar behavior with noise increase, the ATT with the supervised DNN was less biased. The in vivo study showed that CBF and ATT with the supervised DNN were the most accurate and that the supervised and unsupervised DNNs had the highest noise immunity in CBF and ATT estimations, respectively. Physics-informed unsupervised learning can estimate CBF and ATT from multi-delay ASL signals, and its performance is superior to that of the conventional method. Although noise immunity in ATT estimation was superior with unsupervised learning, other performances were superior with supervised learning.

Calculation of intravoxel incoherent motion parameter maps using a kernelized total difference-based method

Quantitative analysis of diffusion-weighted magnetic resonance imaging (DW-MRI) has been explored for many clinical applications since its development. In particular, the intravoxel incoherent motion (IVIM) model for DW-MRI has been commonly utilized in various organs. However, because of the presence of excessive noise, the IVIM parameter maps obtained from pixel-wise fitting are often unreliable. In this study, we propose a kernelized total difference-based curve-fitting method to estimate the IVIM parameters. Simulated DW-MRI data at five signal-to-noise ratios (i.e., 10, 20, 30, 50, and 100) and real abdominal DW-MRI data acquired on a 1.5-T MRI scanner with nine b-values (i.e., 0, 10, 25, 50, 100, 200, 300, 400, and 500 s/mm2) and six diffusion-encoding gradient directions were used to evaluate the performance of the proposed method. The results were compared with those obtained by three existing methods: trust-region reflective (TRR) algorithm, Bayesian probability (BP), and deep neural network (DNN). Our simulation results showed that the proposed method outperformed the other three comparing methods in terms of root-mean-square error. Moreover, the proposed method could preserve small details in the estimated IVIM parameter maps. The experimental results showed that, compared with the TRR method, the proposed method as well as the BP (and DNN) method could reduce the overestimation of the pseudodiffusion coefficient and improve the quality of IVIM parameter maps. For all studied abdominal organs except the pancreas, both the proposed method and the BP method could provide IVIM parameter estimates close to the reference values; the former had higher precision. The kernelized total difference-based curve-fitting method has the potential to improve the reliability of IVIM parametric imaging.

IVIM parameters mapping with artificial neural network based on mean deviation prior

BACKGROUND

The diffusion and perfusion parameters derived from intravoxel incoherent motion (IVIM) imaging provide promising biomarkers for noninvasively quantifying and managing various diseases. Nevertheless, due to the distribution gap between simulated and real datasets, the out-of-distribution (OOD) problem occurred in supervised learning-based methods degrades their performance and hinders their real applications.

PURPOSE

To address the OOD problem in supervised methods and to further improve the accuracy and stability of IVIM parameter estimation, this work proposes a novel learning framework called IterANN, based on mean deviation prior (MDP) between training and estimated IVIM parameters on the test set.

METHODS

Specifically, MDP indicates that the mean of the estimated IVIM parameters always locates between the mean of IVIM parameters in the test and train sets. In IterANN, we adopt a very simple artificial neural network (ANN) architecture of two hidden layers with 12 neurons per hidden layer, an input layer containing the signals acquired at multiple b-values and an output layer composed of three IVIM parameters ( D $D$ , F $F$ andD S t a r $DStar$ ). Inspired by MDP, the distribution of IVIM parameters in the training set (simulated data) is iteratively updated so that their mean gradually approaches the predicted values of the real data. This aims to achieve a strong correlation between the simulated data and the real data. To validate the effectiveness of IterANN, we compare it with several methods on both simulation and real acquisition datasets, including 21 healthy and 3 tumor subjects, in terms of residual errors of IVIM parameters or DW signals, the coefficients of variation (CV) of IVIM parameters, and the parameter contrast-to-noise ratio (PCNR) between normal and tumor tissues.

RESULTS

On two simulation datasets, the proposed IterANN achieves the lowest residual error in IVIM parameters, especially in the case of low signal-to-noise ratio (SNR = 10), the residual error of D $D$ , F $F$ andD S t a r $DStar$ is decreased by15.82 % / 14.92 % , 81.19 % / 74.04 % , 50.77 % / 1.549 % $15.82\%/14.92\%, 81.19\%/74.04\%, 50.77\%/1.549\%$ (Gaussian distribution /realistic distribution) respectively comparing to the suboptimal method. On real dataset, the IterANN achieves the highest PCNR when comparing the normal and tumor regions. Additionally, the proposed IterANN demonstrated better stability, with its CV being significantly lower than that of other methods in the vast majority of cases (p < 0.01 $p<0.01$ , paired-sample Student's t-test).

CONCLUSIONS

The superior performance of IterANN demonstrates that updating the distribution of the train set based on MDP can effectively solve the OOD problem, which allows us not only to improve the accuracy and stability of the estimated IVIM parameters, but also to increase the potential of IVIM in disease diagnosis.

Improved quantitative parameter estimation for prostate T2 relaxometry using convolutional neural networks

OBJECTIVE

Quantitative parameter mapping conventionally relies on curve fitting techniques to estimate parameters from magnetic resonance image series. This study compares conventional curve fitting techniques to methods using neural networks (NN) for measuring T2 in the prostate.

MATERIALS AND METHODS

Large physics-based synthetic datasets simulating T2 mapping acquisitions were generated for training NNs and for quantitative performance comparisons. Four combinations of different NN architectures and training corpora were implemented and compared with four different curve fitting strategies. All methods were compared quantitatively using synthetic data with known ground truth, and further compared on in vivo test data, with and without noise augmentation, to evaluate feasibility and noise robustness.

RESULTS

In the evaluation on synthetic data, a convolutional neural network (CNN), trained in a supervised fashion using synthetic data generated from naturalistic images, showed the highest overall accuracy and precision amongst the methods. On in vivo data, this best performing method produced low-noise T2 maps and showed the least deterioration with increasing input noise levels.

DISCUSSION

This study showed that a CNN, trained with synthetic data in a supervised manner, may provide superior T2 estimation performance compared to conventional curve fitting, especially in low signal-to-noise regions.

Comparison of methods for intravoxel incoherent motion parameter estimation in the brain from flow-compensated and non-flow-compensated diffusion-encoded data

PURPOSE

Joint analysis of flow-compensated (FC) and non-flow-compensated (NC) diffusion MRI (dMRI) data has been suggested for increased robustness of intravoxel incoherent motion (IVIM) parameter estimation. For this purpose, a set of methods commonly used or previously found useful for IVIM analysis of dMRI data obtained with conventional diffusion encoding were evaluated in healthy human brain.

METHODS

Five methods for joint IVIM analysis of FC and NC dMRI data were compared: (1) direct non-linear least squares fitting, (2) a segmented fitting algorithm with estimation of the diffusion coefficient from higher b-values of NC data, (3) a Bayesian algorithm with uniform prior distributions, (4) a Bayesian algorithm with spatial prior distributions, and (5) a deep learning-based algorithm. Methods were evaluated on brain dMRI data from healthy subjects and simulated data at multiple noise levels. Bipolar diffusion encoding gradients were used with b-values 0-200 s/mm2 and corresponding flow weighting factors 0-2.35 s/mm for NC data and by design 0 for FC data. Data were acquired twice for repeatability analysis.

RESULTS

Measurement repeatability as well as estimation bias and variability were at similar levels or better with the Bayesian algorithm with spatial prior distributions and the deep learning-based algorithm for IVIM parametersD $$ D $$ andf $$ f $$ , and for the Bayesian algorithm only forv d $$ {v}_d $$ , relative to the other methods.

CONCLUSION

A Bayesian algorithm with spatial prior distributions is preferable for joint IVIM analysis of FC and NC dMRI data in the healthy human brain, but deep learning-based algorithms appear promising.

Reproducible Research Practices in Magnetic Resonance Neuroimaging: A Review Informed by Advanced Language Models

MRI has progressed significantly with the introduction of advanced computational methods and novel imaging techniques, but their wider adoption hinges on their reproducibility. This concise review synthesizes reproducible research insights from recent MRI articles to examine the current state of reproducibility in neuroimaging, highlighting key trends and challenges. It also provides a custom generative pretrained transformer (GPT) model, designed specifically for aiding in an automated analysis and synthesis of information pertaining to the reproducibility insights associated with the articles at the core of this review.

DIMOND: DIffusion Model OptimizatioN with Deep Learning

Diffusion magnetic resonance imaging is an important tool for mapping tissue microstructure and structural connectivity non-invasively in the in vivo human brain. Numerous diffusion signal models are proposed to quantify microstructural properties. Nonetheless, accurate estimation of model parameters is computationally expensive and impeded by image noise. Supervised deep learning-based estimation approaches exhibit efficiency and superior performance but require additional training data and may be not generalizable. A new DIffusion Model OptimizatioN framework using physics-informed and self-supervised Deep learning entitled "DIMOND" is proposed to address this problem. DIMOND employs a neural network to map input image data to model parameters and optimizes the network by minimizing the difference between the input acquired data and synthetic data generated via the diffusion model parametrized by network outputs. DIMOND produces accurate diffusion tensor imaging results and is generalizable across subjects and datasets. Moreover, DIMOND outperforms conventional methods for fitting sophisticated microstructural models including the kurtosis and NODDI model. Importantly, DIMOND reduces NODDI model fitting time from hours to minutes, or seconds by leveraging transfer learning. In summary, the self-supervised manner, high efficacy, and efficiency of DIMOND increase the practical feasibility and adoption of microstructure and connectivity mapping in clinical and neuroscientific applications.

Multisite MRI Intravoxel Incoherent Motion Repeatability and Reproducibility across 3 T Scanners in a Breast Diffusion Phantom: A BReast Intravoxel Incoherent Motion Multisite (BRIMM) Study

BACKGROUND

Monoexponential apparent diffusion coefficient (ADC) and biexponential intravoxel incoherent motion (IVIM) analysis of diffusion-weighted imaging is helpful in the characterization of breast tumors. However, repeatability/reproducibility studies across scanners and across sites are scarce.

PURPOSE

To evaluate the repeatability and reproducibility of ADC and IVIM parameters (tissue diffusivity (Dt), perfusion fraction (Fp) and pseudo-diffusion (Dp)) within and across sites employing MRI scanners from different vendors utilizing 16-channel breast array coils in a breast diffusion phantom.

STUDY TYPE

Phantom repeatability.

PHANTOM

A breast phantom containing tubes of different polyvinylpyrrolidone (PVP) concentrations, water, fat, and sponge flow chambers, together with an MR-compatible liquid crystal (LC) thermometer.

FIELD STRENGTH/SEQUENCE

Bipolar gradient twice-refocused spin echo sequence and monopolar gradient single spin echo sequence at 3 T.

ASSESSMENT

Studies were performed twice in each of two scanners, located at different sites, on each of 2 days, resulting in four studies per scanner. ADCs of the PVP and water were normalized to the vendor-provided calibrated values at the temperature indicated by the LC thermometer for repeatability/reproducibility comparisons.

STATISTICAL TESTS

ADC and IVIM repeatability and reproducibility within and across sites were estimated via the within-system coefficient of variation (wCV). Pearson correlation coefficient (r) was also computed between IVIM metrics and flow speed. A P value <0.05 was considered statistically significant.

RESULTS

ADC and Dt demonstrated excellent repeatability (<2%; <3%, respectively) and reproducibility (both <5%) at the two sites. Fp and Dp exhibited good repeatability (mean of two sites 3.67% and 5.59%, respectively) and moderate reproducibility (mean of two sites 15.96% and 13.3%, respectively). The mean intersite reproducibility (%) of Fp/Dp/Dt was 50.96/13.68/5.59, respectively. Fp and Dt demonstrated high correlations with flow speed while Dp showed lower correlations. Fp correlations with flow speed were significant at both sites.

DATA CONCLUSION

IVIM reproducibility results were promising and similar to ADC, particularly for Dt. The results were reproducible within both sites, and a progressive trend toward reproducibility across sites except for Fp.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY: Stage 1.

Effects of the Training Data Condition on Arterial Spin Labeling Parameter Estimation Using a Simulation-Based Supervised Deep Neural Network

OBJECTIVE

A simulation-based supervised deep neural network (DNN) can accurately estimate cerebral blood flow (CBF) and arterial transit time (ATT) from multidelay arterial spin labeling signals. However, the performance of deep learning depends on the characteristics of the training data set. We aimed to investigate the effects of the ground truth (GT) ranges of CBF and ATT on the performance of the DNN when training data were prepared using arterial spin labeling signal simulation.

METHODS

Deep neural networks were individually trained using 36 patterns of the training data sets. Simulation test data (1,000,000 points), 17 healthy volunteers, and 1 patient with moyamoya disease were included. The simulation test data were used to evaluate accuracy, precision, and noise immunity of the DNN. The best-performing DNN was determined by the normalized mean absolute error (NMAE), normalized root mean squared error (NRMSE), and normalized coefficient of variation over repeated training (CV Net ). Cerebral blood flow and ATT values and their histograms were compared between the GT and predicted values. For the in vivo data, the dependency of the predicted values on the GT ranges was visually evaluated by comparing CBF and ATT maps between the best-performing DNN and the other DNNs. Moreover, using the synthesized noisy images, noise immunity was compared between the best-performing DNN based on the simulation study and a conventional method.

RESULTS

The simulation study showed that a network trained by the GT of CBF and ATT in the ranges of 0 to 120 mL/100 g/min and 0 to 4500 milliseconds, respectively, had the highest performance (NMAE CBF , 0.150; NRMSE CBF , 0.231; CV NET CBF , 0.028; NMAE ATT , 0.158; NRMSE ATT , 0.257; and CV NET ATT , 0.028). Although the predicted CBF and ATT varied with the GT range of the training data sets, the appropriate settings preserved the accuracy, precision, and noise immunity of the DNN. In addition, the same results were observed in in vivo studies.

CONCLUSIONS

The GT ranges to prepare the training data affected the performance of the simulation-based supervised DNNs. The predicted CBF and ATT values depended on the GT range; inappropriate settings degraded the accuracy, whereas appropriate settings of the GT range provided accurate and precise estimates.

Image denoising and model-independent parameterization for IVIM MRI

Objective. To improve intravoxel incoherent motion imaging (IVIM) magnetic resonance Imaging quality using a new image denoising technique and model-independent parameterization of the signal versusb-value curve.Approach. IVIM images were acquired for 13 head-and-neck patients prior to radiotherapy. Post-radiotherapy scans were also acquired for five of these patients. Images were denoised prior to parameter fitting using neural blind deconvolution, a method of solving the ill-posed mathematical problem of blind deconvolution using neural networks. The signal decay curve was then quantified in terms of several area under the curve (AUC) parameters. Improvements in image quality were assessed using blind image quality metrics, total variation (TV), and the correlations between parameter changes in parotid glands with radiotherapy dose levels. The validity of blur kernel predictions was assessed by the testing the method's ability to recover artificial 'pseudokernels'. AUC parameters were compared with monoexponential, biexponential, and triexponential model parameters in terms of their correlations with dose, contrast-to-noise (CNR) around parotid glands, and relative importance via principal component analysis.Main results. Image denoising improved blind image quality metrics, smoothed the signal versusb-value curve, and strengthened correlations between IVIM parameters and dose levels. Image TV was reduced and parameter CNRs generally increased following denoising.AUCparameters were more correlated with dose and had higher relative importance than exponential model parameters.Significance. IVIM parameters have high variability in the literature and perfusion-related parameters are difficult to interpret. Describing the signal versusb-value curve with model-independent parameters like theAUCand preprocessing images with denoising techniques could potentially benefit IVIM image parameterization in terms of reproducibility and functional utility.

Developing an AI-empowered head-only ultra-high-performance gradient MRI system for high spatiotemporal neuroimaging

Recent advances in neuroscience requires high-resolution MRI to decipher the structural and functional details of the brain. Developing a high-performance gradient system is an ongoing effort in the field to facilitate high spatial and temporal encoding. Here, we proposed a head-only gradient system NeuroFrontier, dedicated for neuroimaging with an ultra-high gradient strength of 650 mT/m and 600 T/m/s. The proposed system features in 1) ultra-high power of 7MW achieved by running two gradient power amplifiers using a novel paralleling method; 2) a force/torque balanced gradient coil design with a two-step mechanical structure that allows high-efficiency and flexible optimization of the peripheral nerve stimulation; 3) a high-density integrated RF system that is miniaturized and customized for the head-only system; 4) an AI-empowered compressed sensing technique that enables ultra-fast acquisition of high-resolution images and AI-based acceleration in q-t space for diffusion MRI (dMRI); and 5) a prospective head motion correction technique that effectively corrects motion artifacts in real-time with 3D optical tracking. We demonstrated the potential advantages of the proposed system in imaging resolution, speed, and signal-to-noise ratio for 3D structural MRI (sMRI), functional MRI (fMRI) and dMRI in neuroscience applications of submillimeter layer-specific fMRI and dMRI. We also illustrated the unique strength of this system for dMRI-based microstructural mapping, e.g., enhanced lesion contrast at short diffusion-times or high b-values, and improved estimation accuracy for cellular microstructures using diffusion-time-dependent dMRI or for neurite microstructures using q-space approaches.

High-fidelity intravoxel incoherent motion parameter mapping using locally low-rank and subspace modeling

PURPOSE

Intravoxel incoherent motion (IVIM) is a quantitative magnetic resonance imaging (MRI) method used to quantify perfusion properties of tissue non-invasively without contrast. However, clinical applications are limited by unreliable parameter estimates, particularly for the perfusion fraction (f) and pseudodiffusion coefficient (D*). This study aims to develop a high-fidelity reconstruction for reliable estimation of IVIM parameters. The proposed method is versatile and amenable to various acquisition schemes and fitting methods.

METHODS

To address current challenges with IVIM, we adapted several advanced reconstruction techniques. We used a low-rank approximation of IVIM images and temporal subspace modeling to constrain the magnetization dynamics of the bi-exponential diffusion signal decay. In addition, motion-induced phase variations were corrected between diffusion directions and b-values, facilitating the use of high SNR real-valued diffusion data. The proposed method was evaluated in simulations and in vivo brain acquisitions in six healthy subjects and six individuals with a history of SARS-CoV-2 infection and compared with the conventionally reconstructed magnitude data. Following reconstruction, IVIM parameters were estimated voxel-wise.

RESULTS

Our proposed method reduced noise contamination in simulations, resulting in a 60%, 58.9%, and 83.9% reduction in the NRMSE for D, f, and D*, respectively, compared to the conventional reconstruction. In vivo, anisotropic properties of D, f, and D* were preserved with the proposed method, highlighting microvascular differences in gray matter between individuals with a history of COVID-19 and those without (p = 0.0210), which wasn't observed with the conventional reconstruction.

CONCLUSION

The proposed method yielded a more reliable estimation of IVIM parameters with less noise than the conventional reconstruction. Further, the proposed method preserved anisotropic properties of IVIM parameter estimates and demonstrated differences in microvascular perfusion in COVID-affected subjects, which weren't observed with conventional reconstruction methods.

Intravoxel incoherent motion (IVIM)-derived perfusion fraction mapping for the visual evaluation of MR-guided high intensity focused ultrasound (MR-HIFU) ablation of uterine fibroids

BACKGROUND

A method for periprocedural contrast agent-free visualization of uterine fibroid perfusion could potentially shorten magnetic resonance-guided high intensity focused ultrasound (MR-HIFU) treatment times and improve outcomes. Our goal was to test feasibility of perfusion fraction mapping by intravoxel incoherent motion (IVIM) modeling using diffusion-weighted MRI as method for visual evaluation of MR-HIFU treatment progression.

METHODS

Conventional and T2-corrected IVIM-derived perfusion fraction maps were retrospectively calculated by applying two fitting methods to diffusion-weighted MRI data (b = 0, 50, 100, 200, 400, 600 and 800 s/mm2 at 1.5 T) from forty-four premenopausal women who underwent MR-HIFU ablation treatment of uterine fibroids. Contrast in perfusion fraction maps between areas with low perfusion fraction and surrounding tissue in the target uterine fibroid immediately following MR-HIFU treatment was evaluated. Additionally, the Dice similarity coefficient (DSC) was calculated between delineated areas with low IVIM-derived perfusion fraction and hypoperfusion based on CE-T1w.

RESULTS

Average perfusion fraction ranged between 0.068 and 0.083 in areas with low perfusion fraction based on visual assessment, and between 0.256 and 0.335 in surrounding tissues (all p < 0.001). DSCs ranged from 0.714 to 0.734 between areas with low perfusion fraction and the CE-T1w derived non-perfused areas, with excellent intraobserver reliability of the delineated areas (ICC 0.97).

CONCLUSION

The MR-HIFU treatment effect in uterine fibroids can be visualized using IVIM perfusion fraction mapping, in moderate concordance with contrast enhanced MRI. IVIM perfusion fraction mapping has therefore the potential to serve as a contrast agent-free imaging method to visualize the MR-HIFU treatment progression in uterine fibroids.

Exploring the Potential of Machine Learning Algorithms to Improve Diffusion Nuclear Magnetic Resonance Imaging Models Analysis

Purpose

This paper explores different machine learning (ML) algorithms for analyzing diffusion nuclear magnetic resonance imaging (dMRI) models when analytical fitting shows restrictions. It reviews various ML techniques for dMRI analysis and evaluates their performance on different b-values range datasets, comparing them with analytical methods.

Materials and Methods

After standard fitting for reference, four sets of diffusion-weighted nuclear magnetic resonance images were used to train/test various ML algorithms for prediction of diffusion coefficient (D), pseudo-diffusion coefficient (D*), perfusion fraction (f), and kurtosis (K). ML classification algorithms, including extra-tree classifier (ETC), logistic regression, C-support vector, extra-gradient boost, and multilayer perceptron (MLP), were used to determine the existence of diffusion parameters (D, D*, f, and K) within single voxels. Regression algorithms, including linear regression, polynomial regression, ridge, lasso, random forest (RF), elastic-net, and support-vector machines, were used to estimate the value of the diffusion parameters. Performance was evaluated using accuracy (ACC), area under the curve (AUC) tests, and cross-validation root mean square error (RMSECV). Computational timing was also assessed.

Results

ETC and MLP were the best classifiers, with 94.1% and 91.7%, respectively, for the ACC test and 98.7% and 96.3% for the AUC test. For parameter estimation, RF algorithm yielded the most accurate results The RMSECV percentages were: 8.39% for D, 3.57% for D*, 4.52% for f, and 3.53% for K. After the training phase, the ML methods demonstrated a substantial decrease in computational time, being approximately 232 times faster than the conventional methods.

Conclusions

The findings suggest that ML algorithms can enhance the efficiency of dMRI model analysis and offer new perspectives on the microstructural and functional organization of biological tissues. This paper also discusses the limitations and future directions of ML-based dMRI analysis.

Accelerated IVIM-corrected DTI in acute hamstring injury: towards a clinically feasible acquisition time

BACKGROUND

Intravoxel incoherent motion (IVIM)-corrected diffusion tensor imaging (DTI) potentially enhances return-to-play (RTP) prediction after hamstring injuries. However, the long scan times hamper clinical implementation. We assessed accelerated IVIM-corrected DTI approaches in acute hamstring injuries and explore the sensitivity of the perfusion fraction (f) to acute muscle damage.

METHODS

Athletes with acute hamstring injury received DTI scans of both thighs < 7 days after injury and at RTP. For a subset, DTI scans were repeated with multiband (MB) acceleration. Data from standard and MB-accelerated scans were fitted with standard and accelerated IVIM-corrected DTI approach using high b-values only. Segmentations of the injury and contralateral healthy muscles were contoured. The fitting methods as well as the standard and MB-accelerated scan were compared using linear regression analysis. For sensitivity to injury, Δ(injured minus healthy) DTI parameters between the methods and the differences between injured and healthy muscles were compared (Wilcoxon signed-rank test).

RESULTS

The baseline dataset consisted of 109 athletes (16 with MB acceleration); 64 of them received an RTP scan (8 with MB acceleration). Linear regression of the standard and high-b DTI fitting showed excellent agreement. With both fitting methods, standard and MB-accelerated scans were comparable. Δ(injured minus healthy) was similar between standard and accelerated methods. For all methods, all IVIM-DTI parameters except f were significantly different between injured and healthy muscles.

CONCLUSIONS

High-b DTI fitting with MB acceleration reduced the scan time from 11:08 to 3:40 min:s while maintaining sensitivity to hamstring injuries; f was not different between healthy and injured muscles.

RELEVANCE STATEMENT

The accelerated IVIM-corrected DTI protocol, using fewer b-values and MB acceleration, reduced the scan time to under 4 min without affecting the sensitivity of the quantitative outcome parameters to hamstring injuries. This allows for routine clinical monitoring of hamstring injuries, which could directly benefit injury treatment and monitoring.

KEY POINTS

• Combining high-b DTI-fitting and multiband-acceleration dramatically reduced by two thirds the scan time. • The accelerated IVIM-corrected DTI approaches maintained the sensitivity to hamstring injuries. • The IVIM-derived perfusion fraction was not sensitive to hamstring injuries.

Intrapancreatic fat deposition is unrelated to liver steatosis in metabolic dysfunction-associated steatotic liver disease

Background & Aims

Individuals with obesity may develop intrapancreatic fat deposition (IPFD) and fatty pancreas disease (FPD). Whether this causes inflammation and fibrosis and leads to pancreatic dysfunction is less established than for liver damage in metabolic dysfunction-associated steatotic liver disease (MASLD). Moreover, the interrelations of FPD and MASLD are poorly understood. Therefore, we aimed to assess IPFD and fibro-inflammation in relation to pancreatic function and liver disease severity in individuals with MASLD.

Methods

Seventy-six participants from the Amsterdam MASLD-MASH cohort (ANCHOR) study underwent liver biopsy and multiparametric MRI of the liver and pancreas, consisting of proton-density fat fraction sequences, T1 mapping and intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI).

Results

The prevalence of FPD was 37.3%. There was a clear correlation between pancreatic T1 relaxation time, which indicates fibro-inflammation, and parameters of glycemic dysregulation, namely HbA1c (R = 0.59; p <0.001), fasting glucose (R = 0.51; p <0.001) and the presence of type 2 diabetes (mean 802.0 ms vs. 733.6 ms; p <0.05). In contrast, there was no relation between IPFD and hepatic fat content (R = 0.03; p = 0.80). Pancreatic IVIM diffusion (IVIM-D) was lower in advanced liver fibrosis (p <0.05) and pancreatic perfusion (IVIM-f), reflecting vessel density, inversely correlated to histological MASLD activity (p <0.05).

Conclusions

Consistent relations exist between pancreatic fibro-inflammation on MRI and endocrine function in individuals with MASLD. However, despite shared dysmetabolic drivers, our study suggests IPFD is a separate pathophysiological process from MASLD.

Impact and implications

Metabolic dysfunction-associated steatotic liver disease (MASLD) is the most common chronic liver disease worldwide and 68% of people with type 2 diabetes have MASLD. However, fat infiltration and inflammation in the pancreas are understudied in individuals with MASLD. In this cross-sectional MRI study, we found no relationship between fat accumulation in the pancreas and liver in a cohort of patients with MASLD. However, our results show that inflammatory and fibrotic processes in the pancreas may be interrelated to features of type 2 diabetes and to the severity of liver disease in patients with MASLD. Overall, the results suggest that pancreatic endocrine dysfunction in individuals with MASLD may be more related to glucotoxicity than to lipotoxicity.

Clinical trial number

NTR7191 (Dutch Trial Register).

Evaluation of the Prognostic Value of Pretherapeutic Magnetic Resonance Imaging in Predicting Soft Tissue Sarcoma Radiation Response: A Retrospective Study from a Large Institutional Sarcoma Imaging Database

Background: RT-induced hyalinization/fibrosis was recently evidenced as a significant independent predictor for complete response to neoadjuvant radiotherapy (RT) and survival in patients with soft tissue sarcoma (STS). Purpose: Non-invasive predictive markers of histologic response after neoadjuvant RT of STS are expected. Materials and Methods: From May 2010 to April 2017, patients with a diagnosis of STS who underwent neoadjuvant RT for limb STS were retrieved from a single center prospective clinical imaging database. Tumor Apparent Diffusion Coefficients (ADC) and areas under the time-intensity perfusion curve (AUC) were compared with the histologic necrosis ratio, fibrosis, and cellularity in post-surgical specimens. Results: We retrieved 29 patients. The median ADC value was 134.3 × 10-3 mm2/s. ADC values positively correlated with the post-treatment tumor necrosis ratio (p = 0.013). Median ADC values were lower in patients with less than 50% necrosis and higher in those with more than 50% (120.3 × 10-3 mm2/s and 202.0 × 10-3 mm2/s, respectively (p = 0.020). ADC values higher than 161 × 10-3 mm2/s presented a 95% sensitivity and a 55% specificity for the identification of tumors with more than 50% tumor necrosis ratio. Tumor-to-muscle AUC ratios were associated with histologic fibrosis (p = 0.036). Conclusions: ADC and perfusion AUC correlated, respectively, with radiation-induced tumor necrosis and fibrosis.

Advanced Diffusion-Weighted MRI for Cancer Microstructure Assessment in Body Imaging, and Its Relationship With Histology

Diffusion-weighted magnetic resonance imaging (DW-MRI) aims to disentangle multiple biological signal sources in each imaging voxel, enabling the computation of innovative maps of tissue microstructure. DW-MRI model development has been dominated by brain applications. More recently, advanced methods with high fidelity to histology are gaining momentum in other contexts, for example, in oncological applications of body imaging, where new biomarkers are urgently needed. The objective of this article is to review the state-of-the-art of DW-MRI in body imaging (ie, not including the nervous system) in oncology, and to analyze its value as compared to reference colocalized histology measurements, given that demonstrating the histological validity of any new DW-MRI method is essential. In this article, we review the current landscape of DW-MRI techniques that extend standard apparent diffusion coefficient (ADC), describing their acquisition protocols, signal models, fitting settings, microstructural parameters, and relationship with histology. Preclinical, clinical, and in/ex vivo studies were included. The most used techniques were intravoxel incoherent motion (IVIM; 36.3% of used techniques), diffusion kurtosis imaging (DKI; 16.7%), vascular, extracellular, and restricted diffusion for cytometry in tumors (VERDICT; 13.3%), and imaging microstructural parameters using limited spectrally edited diffusion (IMPULSED; 11.7%). Another notable category of techniques relates to innovative b-tensor diffusion encoding or joint diffusion-relaxometry. The reviewed approaches provide histologically meaningful indices of cancer microstructure (eg, vascularization/cellularity) which, while not necessarily accurate numerically, may still provide useful sensitivity to microscopic pathological processes. Future work of the community should focus on improving the inter-/intra-scanner robustness, and on assessing histological validity in broader contexts. LEVEL OF EVIDENCE: NA TECHNICAL EFFICACY: Stage 2.

Probing Renal Microstructure and Function with Advanced Diffusion MRI: Concepts, Applications, Challenges, and Future Directions

Diffusion measurements in the kidney are affected not only by renal microstructure but also by physiological processes (i.e., glomerular filtration, water reabsorption, and urine formation). Because of the superposition of passive tissue diffusion, blood perfusion, and tubular pre-urine flow, the limitations of the monoexponential apparent diffusion coefficient (ADC) model in assessing pathophysiological changes in renal tissue are becoming apparent and motivate the development of more advanced diffusion-weighted imaging (DWI) variants. These approaches take advantage of the fact that the length scale probed in DWI measurements can be adjusted by experimental parameters, including diffusion-weighting, diffusion gradient directions and diffusion time. This forms the basis by which advanced DWI models can be used to capture not only passive diffusion effects, but also microcirculation, compartmentalization, tissue anisotropy. In this review, we provide a comprehensive overview of the recent advancements in the field of renal DWI. Following a short introduction on renal structure and physiology, we present the key methodological approaches for the acquisition and analysis of renal DWI data, including intravoxel incoherent motion (IVIM), diffusion tensor imaging (DTI), non-Gaussian diffusion, and hybrid IVIM-DTI. We then briefly summarize the applications of these methods in chronic kidney disease and renal allograft dysfunction. Finally, we discuss the challenges and potential avenues for further development of renal DWI. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 2.

Quantitative diffusion MRI in prostate cancer: Image quality, what we can measure and how it improves clinical assessment

Diffusion-weighted imaging is a dependable method for detection of clinically significant prostate cancer. In prostate tissue, there are several compartments that can be distinguished from each other, based on different water diffusion decay signals observed. Alterations in cell architecture, such as a relative increase in tumor infiltration and decrease in stroma, will influence the observed diffusion signal in a voxel due to impeded random motion of water molecules. The amount of restricted diffusion can be assessed quantitatively by measuring the apparent diffusion coefficient (ADC) value. This is traditionally calculated using a monoexponential decay formula represented by the slope of a line produced between the logarithm of signal intensity decay plotted against selected b-values. However, the choice and number of b-values and their distribution, has a significant effect on the measured ADC values. There have been many models that attempt to use higher-order functions to better describe the observed diffusion signal decay, requiring an increased number and range of b-values. While ADC can probe heterogeneity on a macroscopic level, there is a need to optimize advanced diffusion techniques to better interrogate prostate tissue microstructure. This could be of benefit in clinical challenges such as identifying sparse tumors in normal prostate tissue or better defining tumor margins. This paper reviews the principles of diffusion MRI and novel higher order diffusion signal analysis techniques to improve the detection of prostate cancer.

Assessing within-subject rates of change of placental MRI diffusion metrics in normal pregnancy

PURPOSE

Studying placental development informs when development is abnormal. Most placental MRI studies are cross-sectional and do not study the extent of individual variability throughout pregnancy. We aimed to explore how diffusion MRI measures of placental function and microstructure vary in individual healthy pregnancies throughout gestation.

METHODS

Seventy-nine pregnant, low-risk participants (17 scanned twice and 62 scanned once) were included. T2 -weighted anatomical imaging and a combined multi-echo spin-echo diffusion-weighted sequence were acquired at 3 T. Combined diffusion-relaxometry models were performed using both aT 2 * $$ {\mathrm{T}}_2^{\ast } $$ -ADC and a bicompartmentalT 2 * $$ {\mathrm{T}}_2^{\ast } $$ -intravoxel-incoherent-motion (T 2 * IVIM $$ {\mathrm{T}}_2^{\ast}\;\mathrm{IVIM} $$ ) model fit.

RESULTS

There was a significant decline in placentalT 2 * $$ {\mathrm{T}}_2^{\ast } $$ and ADC (both P < 0.01) over gestation. These declines are consistent in individuals forT 2 * $$ {\mathrm{T}}_2^{\ast } $$ (covariance = -0.47), but not ADC (covariance = -1.04). TheT 2 * IVIM $$ {\mathrm{T}}_2^{\ast}\;\mathrm{IVIM} $$ model identified a consistent decline in individuals over gestation inT 2 * $$ {\mathrm{T}}_2^{\ast } $$ from both the perfusing and diffusing placental compartments, but not in ADC values from either. The placental perfusing compartment fraction increased over gestation (P = 0.0017), but this increase was not consistent in individuals (covariance = 2.57).

CONCLUSION

Whole placentalT 2 * $$ {\mathrm{T}}_2^{\ast } $$ and ADC values decrease over gestation, although onlyT 2 * $$ {\mathrm{T}}_2^{\ast } $$ values showed consistent trends within subjects. There was minimal individual variation in rates of change ofT 2 * $$ {\mathrm{T}}_2^{\ast } $$ values from perfusing and diffusing placental compartments, whereas trends in ADC values from these compartments were less consistent. These findings probably relate to the increased complexity of the bicompartmentalT 2 * IVIM $$ {\mathrm{T}}_2^{\ast}\;\mathrm{IVIM} $$ model, and differences in how different placental regions evolve at a microstructural level. These placental MRI metrics from low-risk pregnancies provide a useful benchmark for clinical cohorts.

Intravoxel incoherent motion magnetic resonance imaging reconstruction from highly under-sampled diffusion-weighted PROPELLER acquisition data via physics-informed residual feedback unrolled network

Objective. The acquisition of diffusion-weighted images for intravoxel incoherent motion (IVIM) imaging is time consuming. This work aims to accelerate the scan through a highly under-sampling diffusion-weighted turbo spin echo PROPELLER (DW-TSE-PROPELLER) scheme and to develop a reconstruction method for accurate IVIM parameter mapping from the under-sampled data.Approach.The proposed under-sampling DW-TSE-PROPELLER scheme for IVIM imaging is that a few blades perb-value are acquired and rotated along theb-value dimension to cover high-frequency information. A physics-informed residual feedback unrolled network (PIRFU-Net) is proposed to directly estimate distortion-free and artifact-free IVIM parametric maps (i.e., the perfusion-free diffusion coefficientDand the perfusion fractionf) from highly under-sampled DW-TSE-PROPELLER data. PIRFU-Net used an unrolled convolution network to explore data redundancy in the k-q space to remove under-sampling artifacts. An empirical IVIM physical constraint was incorporated into the network to ensure that the signal evolution curves along theb-value follow a bi-exponential decay. The residual between the realistic and estimated measurements was fed into the network to refine the parametric maps. Meanwhile, the use of synthetic training data eliminated the need for genuine DW-TSE-PROPELLER data.Main results.The experimental results show that the DW-TSE-PROPELLER acquisition was six times faster than full k-space coverage PROPELLER acquisition and within a clinically acceptable time. Compared with the state-of-the-art methods, the distortion-freeDandfmaps estimated by PIRFU-Net were more accurate and had better-preserved tissue boundaries on a simulated human brain and realistic phantom/rat brain/human brain data.Significance.Our proposed method greatly accelerates IVIM imaging. It is capable of directly and simultaneously reconstructing distortion-free, artifact-free, and accurateDandfmaps from six-fold under-sampled DW-TSE-PROPELLER data.

Integrated intravoxel incoherent motion tensor and diffusion tensor brain MRI in a single fast acquisition

The acquisition of intravoxel incoherent motion (IVIM) data and diffusion tensor imaging (DTI) data from the brain can be integrated into a single measurement, which offers the possibility to determine orientation-dependent (tensorial) perfusion parameters in addition to established IVIM and DTI parameters. The purpose of this study was to evaluate the feasibility of such a protocol with a clinically feasible scan time below 6 min and to use a model-selection approach to find a set of DTI and IVIM tensor parameters that most adequately describes the acquired data. Diffusion-weighted images of the brain were acquired at 3 T in 20 elderly participants with cerebral small vessel disease using a multiband echoplanar imaging sequence with 15 b-values between 0 and 1000 s/mm² and six non-collinear diffusion gradient directions for each b-value. Seven different IVIM-diffusion models with 4 to 14 parameters were implemented, which modeled diffusion and pseudo-diffusion as scalar or tensor quantities. The models were compared with respect to their fitting performance based on the goodness of fit (sum of squared fit residuals, chi² ) and their Akaike weights (calculated from the corrected Akaike information criterion). Lowest chi² values were found using the model with the largest number of model parameters. However, significantly highest Akaike weights indicating the most appropriate models for the acquired data were found with a nine-parameter IVIM-DTI model (with isotropic perfusion modeling) in normal-appearing white matter (NAWM), and with an 11-parameter model (IVIM-DTI with additional pseudo-diffusion anisotropy) in white matter with hyperintensities (WMH) and in gray matter (GM). The latter model allowed for the additional calculation of the fractional anisotropy of the pseudo-diffusion tensor (with a median value of 0.45 in NAWM, 0.23 in WMH, and 0.36 in GM), which is not accessible with the usually performed IVIM acquisitions based on three orthogonal diffusion-gradient directions.

Differentiation of white matter histopathology using b-tensor encoding and machine learning

Diffusion-weighted magnetic resonance imaging (DW-MRI) is a non-invasive technique that is sensitive to microstructural geometry in neural tissue and is useful for the detection of neuropathology in research and clinical settings. Tensor-valued diffusion encoding schemes (b-tensor) have been developed to enrich the microstructural data that can be obtained through DW-MRI. These advanced methods have proven to be more specific to microstructural properties than conventional DW-MRI acquisitions. Additionally, machine learning methods are particularly useful for the study of multidimensional data sets. In this work, we have tested the reach of b-tensor encoding data analyses with machine learning in different histopathological scenarios. We achieved this in three steps: 1) We induced different levels of white matter damage in rodent optic nerves. 2) We obtained ex vivo DW-MRI data with b-tensor encoding schemes and calculated quantitative metrics using Q-space trajectory imaging. 3) We used a machine learning model to identify the main contributing features and built a voxel-wise probabilistic classification map of histological damage. Our results show that this model is sensitive to characteristics of microstructural damage. In conclusion, b-tensor encoded DW-MRI data analyzed with machine learning methods, have the potential to be further developed for the detection of histopathology and neurodegeneration.

Truly reproducible uniform estimation of the ADC with multi-b diffusion data- Application in prostate diffusion imaging

PURPOSE

The ADC is a well-established parameter for clinical diagnostic applications, but lacks reproducibility because it is also influenced by the choice diffusion weighting level. A framework is evaluated that is based on multi-b measurement over a wider range of diffusion-weighting levels and higher order tissue diffusion modeling with retrospective, fully reproducible ADC calculation.

METHODS

Averaging effect from curve fitting for various model functions at 20 linearly spaced b-values was determined by means of simulations and theoretical calculations. Simulation and patient multi-b image data were used to compare the new approach for diffusion-weighted image and ADC map reconstruction with and without Rician bias correction to an active clinical trial protocol probing three non-zero b-values.

RESULTS

Averaging effect at a certain b-value varies for model function and maximum b-value used. Images and ADC maps from the novel procedure are on-par with the clinical protocol. Higher order modeling and Rician bias correction is feasible, but comes at the cost of longer computation times.

CONCLUSIONS

Application of the new framework makes higher order modeling more feasible in a clinical setting while still providing patient images and reproducible ADC maps of adequate quality.

Improved Quantitative Parameter Estimation for Prostate T2 Relaxometry using Convolutional Neural Networks

This work seeks to evaluate multiple methods for quantitative parameter estimation from standard T2 mapping acquisitions in the prostate. The T2 estimation performance of methods based on neural networks (NN) was quantitatively compared to that of conventional curve fitting techniques. Large physics-based synthetic datasets simulating T2 mapping acquisitions were generated for training NNs and for quantitative performance comparisons. Ten combinations of different NN architectures, training strategies, and training corpora were implemented and compared with four different curve fitting strategies. All methods were compared quantitatively using synthetic data with known ground truth, and further compared on in vivo test data, with and without noise augmentation, to evaluate feasibility and noise robustness. In the evaluation on synthetic data, a convolutional neural network (CNN), trained in a supervised fashion using synthetic data generated from naturalistic images, showed the highest overall accuracy and precision amongst all the methods. On in vivo data, this best-performing method produced low-noise T2 maps and showed the least deterioration with increasing input noise levels. This study showed that a CNN, trained with synthetic data in a supervised manner, may provide superior T2 estimation performance compared to conventional curve fitting, especially in low signal-to-noise regions.

Deep learning intravoxel incoherent motion modeling: Exploring the impact of training features and learning strategies

PURPOSE

The development of advanced estimators for intravoxel incoherent motion (IVIM) modeling is often motivated by a desire to produce smoother parameter maps than least squares (LSQ). Deep neural networks show promise to this end, yet performance may be conditional on a myriad of choices regarding the learning strategy. In this work, we have explored potential impacts of key training features in unsupervised and supervised learning for IVIM model fitting.

METHODS

Two synthetic data sets and one in-vivo data set from glioma patients were used in training of unsupervised and supervised networks for assessing generalizability. Network stability for different learning rates and network sizes was assessed in terms of loss convergence. Accuracy, precision, and bias were assessed by comparing estimations against ground truth after using different training data (synthetic and in vivo).

RESULTS

A high learning rate, small network size, and early stopping resulted in sub-optimal solutions and correlations in fitted IVIM parameters. Extending training beyond early stopping resolved these correlations and reduced parameter error. However, extensive training resulted in increased noise sensitivity, where unsupervised estimates displayed variability similar to LSQ. In contrast, supervised estimates demonstrated improved precision but were strongly biased toward the mean of the training distribution, resulting in relatively smooth, yet possibly deceptive parameter maps. Extensive training also reduced the impact of individual hyperparameters.

CONCLUSION

Voxel-wise deep learning for IVIM fitting demands sufficiently extensive training to minimize parameter correlation and bias for unsupervised learning, or demands a close correspondence between the training and test sets for supervised learning.

Synthetic-to-real domain adaptation with deep learning for fitting the intravoxel incoherent motion model of diffusion-weighted imaging

BACKGROUND

Intravoxel incoherent motion (IVIM) is a type of diffusion-weighted imaging (DWI), and IVIM model parameters (water molecule diffusion rate D_t , pseudo-diffusion coefficient D_p , and tissue perfusion fraction F_p ) have been widely used in the diagnosis and characterization of malignant lesions.

PURPOSE

This study proposes a deep-learning model with synthetic-to-real domain adaptation to fit the IVIM model parameters of DWI.

METHODS

Ninety-eight consecutive patients diagnosed with hepatocellular carcinoma between January 2017 and September 2020 were included in the study, and routine IVIM-DWI serial examinations were performed using a 3.0 T magnetic resonance imaging system in preoperative MR imaging. The proposed method is mainly composed of two modules: a convolutional neural network-based IVIM model fitting network to map b-value images to the IVIM parameter maps and a domain discriminator to improve the accuracy of the IVIM parameter maps in the real data. The proposed method was compared with previously reported fitting methods, including the nonlinear least squares (NLSs), IVIM-NET_optim , and self-supervised U-network methods. The IVIM parameter-fitting performance was assessed by measuring the DWI reconstruction performance and testing the robustness of each method against noise using noise-corrupted data.

RESULTS

The DWI reconstruction performance demonstrates that the proposed method has better reconstruction accuracy for DWI with a low signal-to-noise ratio, which implies that the proposed method improves the fitting accuracy of the IVIM parameters. Noise-corrupt experiments show that the proposed method is more robust against noise-corrupted signals. With the proposed method, no outliers were found in D_t , and outliers were reduced for F_p in the abnormal regions (proposed method: 1.85%; NLS: 5.90%; IVIM-NET_optim : 6.61%; and self-U-net: 25.36%). Moreover, experiments show that the proposed method has a more stable parameter estimation performance than the existing methods in the absence of real data.

CONCLUSIONS

IVIM parameters can be estimated using a synthetic-to-real domain-adaptation framework with deep learning, and the proposed method outperforms previously reported methods.

Parameter estimation for WMTI-Watson model of white matter using encoder-decoder recurrent neural network

PURPOSE

Biophysical modeling of the diffusion MRI (dMRI) signal provides estimates of specific microstructural tissue properties. Although non-linear least squares (NLLS) is the most widespread fitting method, it suffers from local minima and high computational cost. Deep learning approaches are steadily replacing NLLS, but come with the limitation that the model needs to be retrained for each acquisition protocol and noise level. In this study, a novel fitting approach was proposed based on the encoder-decoder recurrent neural network (RNN) to accelerate model estimation with good generalization to various datasets.

METHODS

The white matter tract integrity (WMTI)-Watson model as an implementation of the Standard Model of diffusion in white matter derives its parameters indirectly from the diffusion and kurtosis tensors (DKI). The RNN-based solver, which estimates the WMTI-Watson model from DKI, is therefore more readily translatable to various data, irrespective of acquisition protocols as long as the DKI was pre-computed from the signal. An embedding approach was also used to render the model insensitive to potential differences in distributions between training data and experimental data. The analytical solution, NLLS, RNN-, and a multilayer perceptron (MLP)-based methods were evaluated on synthetic and in vivo datasets of rat and human brain.

RESULTS

The proposed RNN solver showed highly reduced computation time over the analytical solution and NLLS, with similar accuracy but improved robustness, and superior generalizability over MLP.

CONCLUSION

The RNN estimator can be easily applied to various datasets without retraining, which shows great potential for a widespread use.

The quantification of IntraVoxel incoherent motion - MRI maps cannot preserve texture information: An evaluation based on simulated and in-vivo images

BACKGROUND

Radiomics can be applied on parametric maps obtained from IntraVoxel Incoherent Motion (IVIM) MRI to characterize heterogeneity in diffusion and perfusion tissue properties. The purpose of this work is to assess the accuracy and reproducibility of radiomic features computed from IVIM maps using different fitting methods.

METHODS

200 digitally simulated IVIM-MRI images with various SNR containing different combinations of texture patterns were generated from ground truth maps of true diffusion D, pseudo-diffusion D* and perfusion fraction f. Four different methods (segmented least-square LSQ, Bayesian, supervised and unsupervised deep learning DL) were adopted to quantify IVIM maps from simulations and from two real images of liver tumor. Radiomic features were computed from ground truth and estimated maps. Accuracy and reproducibility among quantification methods were assessed.

RESULTS

Almost 50% of radiomic features computed from D maps using DL approaches, 36% using Bayes and 27% using LSQ presented errors lower than 50%. Radiomic features from f and D* maps were accurate only if computed using DL methods from histogram. High reproducibility (ICC>0.8) was found only for D maps among DL and Bayes methods, whereas features from f and D* maps were less reproducible, with LSQ approach in lower agreement with the others.

CONCLUSIONS

Texture patterns were preserved and correctly estimated only on D maps, except for LSQ approach. We suggest limiting radiomic analysis only to histogram and some texture features from D maps, to histogram features from f maps, and to avoid it on D* maps.

A microstructure estimation Transformer inspired by sparse representation for diffusion MRI

Diffusion magnetic resonance imaging (dMRI) is an important tool in characterizing tissue microstructure based on biophysical models, which are typically multi-compartmental models with mathematically complex and highly non-linear forms. Resolving microstructures from these models with conventional optimization techniques is prone to estimation errors and requires dense sampling in the q-space with a long scan time. Deep learning based approaches have been proposed to overcome these limitations. Motivated by the superior performance of the Transformer in feature extraction than the convolutional structure, in this work, we present a learning-based framework based on Transformer, namely, a Microstructure Estimation Transformer with Sparse Coding (METSC) for dMRI-based microstructural parameter estimation. To take advantage of the Transformer while addressing its limitation in large training data requirement, we explicitly introduce an inductive bias-model bias into the Transformer using a sparse coding technique to facilitate the training process. Thus, the METSC is composed with three stages, an embedding stage, a sparse representation stage, and a mapping stage. The embedding stage is a Transformer-based structure that encodes the signal in a high-level space to ensure the core voxel of a patch is represented effectively. In the sparse representation stage, a dictionary is constructed by solving a sparse reconstruction problem that unfolds the Iterative Hard Thresholding (IHT) process. The mapping stage is essentially a decoder that computes the microstructural parameters from the output of the second stage, based on the weighted sum of normalized dictionary coefficients where the weights are also learned. We tested our framework on two dMRI models with downsampled q-space data, including the intravoxel incoherent motion (IVIM) model and the neurite orientation dispersion and density imaging (NODDI) model. The proposed method achieved up to 11.25 folds of acceleration while retaining high fitting accuracy for NODDI fitting, reducing the mean squared error (MSE) up to 70% compared with the previous q-space learning approach. METSC outperformed the other state-of-the-art learning-based methods, including the model-free and model-based methods. The network also showed robustness against noise and generalizability across different datasets. The superior performance of METSC indicates its potential to improve dMRI acquisition and model fitting in clinical applications.

Image downsampling expedited adaptive least-squares (IDEAL) fitting improves intravoxel incoherent motion (IVIM) analysis in the human kidney

PURPOSE

To improve the reliability of intravoxel incoherent motion (IVIM) model parameter estimation for the DWI in the kidney using a novel image downsampling expedited adaptive least-squares (IDEAL) approach.

METHODS

The robustness of IDEAL was investigated using simulated DW-MRI data corrupted with different levels of Rician noise. Subsequently, the performance of the proposed method was tested by fitting bi- and triexponential IVIM model to in vivo renal DWI data acquired on a clinical 3 Tesla MRI scanner and compared to conventional approaches (fixed D* and segmented fitting).

RESULTS

The numerical simulations demonstrated that the IDEAL algorithm provides robust estimates of the IVIM parameters in the presence of noise (SNR of 20) as indicated by relatively low absolute percentage bias (maximal sMdPB <20%) and normalized RMSE (maximal RMSE <28%). The analysis of the in vivo data showed that the IDEAL-based IVIM parameter maps were less noisy and more visually appealing than those obtained using the fixed D* and segmented methods. Further, coefficients of variation for nearly all IVIM parameters were significantly reduced in cortex and medulla for IDEAL-based biexponential (coefficients of variation: 4%-50%) and triexponential (coefficients of variation: 7.5%-75%) IVIM modelling compared to the segmented (coefficients of variation: 4%-120%) and fixed D* (coefficients of variation: 17%-174%) methods, reflecting greater accuracy of this method.

CONCLUSION

The proposed fitting algorithm yields more robust IVIM parameter estimates and is less susceptible to poor SNR than the conventional fitting approaches. Thus, the IDEAL approach has the potential to improve the reliability of renal DW-MRI analysis for clinical applications.

Joint estimation of relaxation and diffusion tissue parameters for prostate cancer with relaxation-VERDICT MRI

This work presents a biophysical model of diffusion and relaxation MRI for prostate called relaxation vascular, extracellular and restricted diffusion for cytometry in tumours (rVERDICT). The model includes compartment-specific relaxation effects providing T1/T2 estimates and microstructural parameters unbiased by relaxation properties of the tissue. 44 men with suspected prostate cancer (PCa) underwent multiparametric MRI (mp-MRI) and VERDICT-MRI followed by targeted biopsy. We estimate joint diffusion and relaxation prostate tissue parameters with rVERDICT using deep neural networks for fast fitting. We tested the feasibility of rVERDICT estimates for Gleason grade discrimination and compared with classic VERDICT and the apparent diffusion coefficient (ADC) from mp-MRI. The rVERDICT intracellular volume fraction f_ic discriminated between Gleason 3 + 3 and 3 + 4 (p = 0.003) and Gleason 3 + 4 and ≥ 4 + 3 (p = 0.040), outperforming classic VERDICT and the ADC from mp-MRI. To evaluate the relaxation estimates we compare against independent multi-TE acquisitions, showing that the rVERDICT T2 values are not significantly different from those estimated with the independent multi-TE acquisition (p > 0.05). Also, rVERDICT parameters exhibited high repeatability when rescanning five patients (R² = 0.79-0.98; CV = 1-7%; ICC = 92-98%). The rVERDICT model allows for accurate, fast and repeatable estimation of diffusion and relaxation properties of PCa sensitive enough to discriminate Gleason grades 3 + 3, 3 + 4 and ≥ 4 + 3.

The future of MRI in radiation therapy: Challenges and opportunities for the MR community

Radiation therapy is a major component of cancer treatment pathways worldwide. The main aim of this treatment is to achieve tumor control through the delivery of ionizing radiation while preserving healthy tissues for minimal radiation toxicity. Because radiation therapy relies on accurate localization of the target and surrounding tissues, imaging plays a crucial role throughout the treatment chain. In the treatment planning phase, radiological images are essential for defining target volumes and organs-at-risk, as well as providing elemental composition (e.g., electron density) information for radiation dose calculations. At treatment, onboard imaging informs patient setup and could be used to guide radiation dose placement for sites affected by motion. Imaging is also an important tool for treatment response assessment and treatment plan adaptation. MRI, with its excellent soft tissue contrast and capacity to probe functional tissue properties, holds great untapped potential for transforming treatment paradigms in radiation therapy. The MR in Radiation Therapy ISMRM Study Group was established to provide a forum within the MR community to discuss the unmet needs and fuel opportunities for further advancement of MRI for radiation therapy applications. During the summer of 2021, the study group organized its first virtual workshop, attended by a diverse international group of clinicians, scientists, and clinical physicists, to explore our predictions for the future of MRI in radiation therapy for the next 25 years. This article reviews the main findings from the event and considers the opportunities and challenges of reaching our vision for the future in this expanding field.

Precision of region of interest-based tri-exponential intravoxel incoherent motion quantification and the role of the Intervoxel spatial distribution of flow velocities

PURPOSE

The purpose of this work was to obtain precise tri-exponential intravoxel incoherent motion (IVIM) quantification in the liver using 2D (b-value and first-order motion moment [M1 ]) IVIM-DWI acquisitions and region of interest (ROI)-based fitting techniques.

METHODS

Diffusion MRI of the liver was performed in 10 healthy volunteers using three IVIM-DWI acquisitions: conventional monopolar, optimized monopolar, and optimized 2D (b-M1 ). For each acquisition, bi-exponential and tri-exponential full, segmented, and over-segmented ROI-based fitting and a newly proposed blood velocity SDdistribution (BVD) fitting technique were performed to obtain IVIM estimates in the right and left liver lobes. Fitting quality was evaluated using corrected Akaike information criterion. Precision metrics (test-retest repeatability, inter-reader reproducibility, and inter-lobar agreement) were evaluated using Bland-Altman analysis, repeatability/reproducibility coefficients (RPCs), and paired sample t-tests. Precision was compared across acquisitions and fitting methods.

RESULTS

High repeatability and reproducibility was observed in the estimations of the diffusion coefficient (Dtri  = [1.03 ± 0.11] × 10-3  mm2 /s; RPCs ≤ 1.34 × 10-4  mm2 /s), perfusion fractions (F1  = 3.19 ± 1.89% and F2  = 16.4 ± 2.07%; RPCs ≤ 2.51%), and blood velocity SDs (Vb,1  = 1.44 ± 0.14 mm/s and Vb,2  = 3.62 ± 0.13 mm/s; RPCs ≤ 0.41 mm/s) in the right liver lobe using the 2D (b-M1 ) acquisition in conjunction with BVD fitting. Using these methods, significantly larger (p < 0.01) estimates of Dtri and F1 were observed in the left lobe in comparison to the right lobe, while estimates of Vb,1 and Vb,2 demonstrated high interlobar agreement (RPCs ≤ 0.45 mm/s).

CONCLUSIONS

The 2D (b-M1 ) IVIM-DWI data acquisition in conjunction with BVD fitting enables highly precise tri-exponential IVIM quantification in the right liver lobe.

An unsupervised convolutional neural network method for estimation of intravoxel incoherent motion parameters

Objective. Intravoxel incoherent motion (IVIM) imaging obtained by fitting a biexponential model to multiple b-value diffusion-weighted magnetic resonance imaging (DW-MRI) has been shown to be a promising tool for different clinical applications. Recently, several deep neural network (DNN) methods were proposed to generate IVIM imaging. Approach. In this study, we proposed an unsupervised convolutional neural network (CNN) method for estimation of IVIM parameters. We used both simulated and real abdominal DW-MRI data to evaluate the performance of the proposed CNN-based method, and compared the results with those obtained from a non-linear least-squares fit (TRR, trust-region reflective algorithm) and a feed-forward backward-propagation DNN-based method. Main results. The simulation results showed that both the DNN- and CNN-based methods had lower coefficients of variation than the TRR method, but the CNN-based method provided more accurate parameter estimates. The results obtained from real DW-MRI data showed that the TRR method produced many biased IVIM parameter estimates that hit the upper and lower parameter bounds. In contrast, both the DNN- and CNN-based methods yielded less biased IVIM parameter estimates. Overall, the perfusion fraction and diffusion coefficient obtained from the DNN- and CNN-based methods were close to literature values. However, compared with the CNN-based method, both the TRR and DNN-based methods tended to yield increased pseudodiffusion coefficients (55%–180%). Significance. Our preliminary results suggest that it is feasible to estimate IVIM parameters using CNN.

A supervised deep neural network approach with standardized targets for enhanced accuracy of IVIM parameter estimation from multi-SNR images

Extraction of intravoxel incoherent motion (IVIM) parameters from noisy diffusion-weighted (DW) images using a biexponential fitting model is computationally challenging, and the reliability of the estimated perfusion-related quantities represents a limitation of this technique. Artificial intelligence can overcome the current limitations and be a suitable solution to advance use of this technique in both preclinical and clinical settings. The purpose of this work was to develop a deep neural network (DNN) approach, trained on numerical simulated phantoms with different signal to noise ratios (SNRs), to improve IVIM parameter estimation. The proposed approach is based on a supervised fully connected DNN having 3 hidden layers, 18 inputs and 3 targets with standardized values. 14 × 10³ simulated DW images, based on a Shepp-Logan phantom, were randomly generated with varying SNRs (ranging from 10 to 100). 7 × 10³ images (1000 for each SNR) were used for training. Performance accuracy was assessed in simulated images and the proposed approach was compared with the state-of-the-art Bayesian approach and other DNN algorithms. The DNN approach was also evaluated in vivo on a high-field MRI preclinical scanner. Our DNN approach showed an overall improvement in accuracy when compared with the Bayesian approach and other DNN methods in most of the simulated conditions. The in vivo results demonstrated the feasibility of the proposed approach in real settings and generated quantitative results comparable to those obtained using the Bayesian and unsupervised approaches, especially for D and f, and with lower variability in homogeneous regions. The DNN architecture proposed in this work outlines two innovative features as compared with other studies: (1) the use of standardized targets to improve the estimation of parameters, and (2) the implementation of a single DNN to enhance the IVIM fitting at different SNRs, providing a valuable alternative tool to compute IVIM parameters in conditions of high background noise.

Estimation of Cerebral Blood Flow and Arterial Transit Time From Multi-Delay Arterial Spin Labeling MRI Using a Simulation-Based Supervised Deep Neural Network

BACKGROUND

An inherently poor signal-to-noise ratio (SNR) causes inaccuracy and less precision in cerebral blood flow (CBF) and arterial transit time (ATT) when using arterial spin labeling (ASL). Deep neural network (DNN)-based parameter estimation can solve these problems.

PURPOSE

To reduce the effects of Rician noise on ASL parameter estimation and compute unbiased CBF and ATT using simulation-based supervised DNNs.

STUDY TYPE

Retrospective.

POPULATION

One million simulation test data points, 17 healthy volunteers (five women and 12 men, 33.2 ± 14.6 years of age), and one patient with moyamoya disease.

FIELD STRENGTH/SEQUENCE

3.0 T/Hadamard-encoded pseudo-continuous ASL with a three-dimensional fast spin-echo stack of spirals.

ASSESSMENT

Performances of DNN and conventional methods were compared. For test data, the normalized mean absolute error (NMAE) and normalized root mean squared error (NRMSE) between the ground truth and predicted values were evaluated. For in vivo data, baseline CBF and ATT and their relative changes with respect to SNR using artificial noise-added images were assessed.

STATISTICAL TESTS

One-way analysis of variance with post-hoc Tukey's multiple comparison test, paired t-test, and the Bland-Altman graphical analysis. Statistical significance was defined as P < 0.05.

RESULTS

For both CBF and ATT, NMAE and NRMSE were lower with DNN than with the conventional method. The baseline values were significantly smaller with DNN than with the conventional method (CBF in gray matter, 66 ± 10 vs. 71 ± 12 mL/100 g/min; white matter, 45 ± 6 vs. 46 ± 7 mL/100 g/min; ATT in gray matter, 1424 ± 201 vs. 1471 ± 154 msec). CBF and ATT increased with decreasing SNR; however, their change rates were smaller with DNN than were those with the conventional method. Higher CBF in the prolonged ATT region and clearer contrast in ATT were identified by DNN in a clinical case.

DATA CONCLUSION

DNN outperformed the conventional method in terms of accuracy, precision, and noise immunity.

EVIDENCE LEVEL

3 Technical Efficacy: Stage 1.

Registration and quantification network (RQnet) for IVIM-DKI analysis in MRI

PURPOSE

A deep learning method is proposed for aligning diffusion weighted images (DWIs) and estimating intravoxel incoherent motion-diffusion kurtosis imaging parameters simultaneously.

METHODS

We propose an unsupervised deep learning method that performs 2 tasks: registration and quantification for intravoxel incoherent motion-diffusion kurtosis imaging analysis. A common registration method in diffusion MRI is based on minimizing dissimilarity between various DWIs, which may result in registration errors due to different contrasts in different DWIs. We designed a novel unsupervised deep learning method for both accurate registration and quantification of various diffusion parameters. In order to generate motion-simulated training data and test data, 17 volunteers were scanned without moving their heads, and 4 volunteers moved their heads during the scan in a 3 Tesla MRI. In order to investigate the applicability of the proposed method to other organs, kidney images were also obtained. We compared the registration accuracy of the proposed method, statistical parametric mapping, and a deep learning method with a normalized cross-correlation loss. In the quantification part of the proposed method, a deep learning method that considered the diffusion gradient direction was used.

RESULTS

Simulations and experimental results showed that the proposed method accurately performed registration and quantification for intravoxel incoherent motion-diffusion kurtosis imaging analysis. The registration accuracy of the proposed method was high for all b values. Furthermore, quantification performance was analyzed through simulations and in vivo experiments, where the proposed method showed the best performance among the compared methods.

CONCLUSION

The proposed method aligns the DWIs and accurately quantifies the intravoxel incoherent motion-diffusion kurtosis imaging parameters.

Self-supervised neural network improves tri-exponential intravoxel incoherent motion model fitting compared to least-squares fitting in non-alcoholic fatty liver disease

Recent literature suggests that tri-exponential models may provide additional information and fit liver intravoxel incoherent motion (IVIM) data more accurately than conventional bi-exponential models. However, voxel-wise fitting of IVIM results in noisy and unreliable parameter maps. For bi-exponential IVIM, neural networks (NN) were able to produce superior parameter maps than conventional least-squares (LSQ) generated images. Hence, to improve parameter map quality of tri-exponential IVIM, we developed an unsupervised physics-informed deep neural network (IVIM3-NET). We assessed its performance in simulations and in patients with non-alcoholic fatty liver disease (NAFLD) and compared outcomes with bi-exponential LSQ and NN fits and tri-exponential LSQ fits. Scanning was performed using a 3.0T free-breathing multi-slice diffusion-weighted single-shot echo-planar imaging sequence with 18 b-values. Images were analysed for visual quality, comparing the bi- and tri-exponential IVIM models for LSQ fits and NN fits using parameter-map signal-to-noise ratios (SNR) and adjusted R2. IVIM parameters were compared to histological fibrosis, disease activity and steatosis grades. Parameter map quality improved with bi- and tri-exponential NN approaches, with a significant increase in average parameter-map SNR from 3.38 to 5.59 and 2.45 to 4.01 for bi- and tri-exponential LSQ and NN models respectively. In 33 out of 36 patients, the tri-exponential model exhibited higher adjusted R2 values than the bi-exponential model. Correlating IVIM data to liver histology showed that the bi- and tri-exponential NN outperformed both LSQ models for the majority of IVIM parameters (10 out of 15 significant correlations). Overall, our results support the use of a tri-exponential IVIM model in NAFLD. We show that the IVIM3-NET can be used to improve image quality compared to a tri-exponential LSQ fit and provides promising correlations with histopathology similar to the bi-exponential neural network fit, while generating potentially complementary additional parameters.

IMPULSED model based cytological feature estimation with U-Net: Application to human brain tumor at 3T

PURPOSE

This work introduces and validates a deep-learning-based fitting method, which can rapidly provide accurate and robust estimation of cytological features of brain tumor based on the IMPULSED (imaging microstructural parameters using limited spectrally edited diffusion) model fitting with diffusion-weighted MRI data.

METHODS

The U-Net was applied to rapidly quantify extracellular diffusion coefficient (D_ex ), cell size (d), and intracellular volume fraction (v_in ) of brain tumor. At the training stage, the image-based training data, synthesized by randomizing quantifiable microstructural parameters within specific ranges, was used to train U-Net. At the test stage, the pre-trained U-Net was applied to estimate the microstructural parameters from simulated data and the in vivo data acquired on patients at 3T. The U-Net was compared with conventional non-linear least-squares (NLLS) fitting in simulations in terms of estimation accuracy and precision.

RESULTS

Our results confirm that the proposed method yields better fidelity in simulations and is more robust to noise than the NLLS fitting. For in vivo data, the U-Net yields obvious quality improvement in parameter maps, and the estimations of all parameters are in good agreement with the NLLS fitting. Moreover, our method is several orders of magnitude faster than the NLLS fitting (from about 5 min to <1 s).

CONCLUSION

The image-based training scheme proposed herein helps to improve the quality of the estimated parameters. Our deep-learning-based fitting method can estimate the cell microstructural parameters fast and accurately.

Artificial Intelligence Applied to Pancreatic Imaging: A Narrative Review

The diagnosis, evaluation, and treatment planning of pancreatic pathologies usually require the combined use of different imaging modalities, mainly, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). Artificial intelligence (AI) has the potential to transform the clinical practice of medical imaging and has been applied to various radiological techniques for different purposes, such as segmentation, lesion detection, characterization, risk stratification, or prediction of response to treatments. The aim of the present narrative review is to assess the available literature on the role of AI applied to pancreatic imaging. Up to now, the use of computer-aided diagnosis (CAD) and radiomics in pancreatic imaging has proven to be useful for both non-oncological and oncological purposes and represents a promising tool for personalized approaches to patients. Although great developments have occurred in recent years, it is important to address the obstacles that still need to be overcome before these technologies can be implemented into our clinical routine, mainly considering the heterogeneity among studies.

b value and first-order motion moment optimized data acquisition for repeatable quantitative intravoxel incoherent motion DWI

PURPOSE

To design a b value and first-order motion moment (M1 ) optimized data acquisition for repeatable intravoxel incoherent motion (IVIM) quantification in the liver.

METHODS

Cramer-Rao lower bound optimization was performed to determine optimal monopolar and optimal 2D samplings of the b-M1 space based on noise performance. Monte Carlo simulations were used to evaluate the bias and variability in estimates obtained using the proposed optimal samplings and conventional monopolar sampling. Diffusion MRI of the liver was performed in 10 volunteers using 3 IVIM acquisitions: conventional monopolar, optimized monopolar, and b-M1 -optimized gradient waveforms (designed based on the optimal 2D sampling). IVIM parameter maps of diffusion coefficient, perfusion fraction, and blood velocity SD were obtained using nonlinear least squares fitting. Noise performance (SDs), stability (outlier percentage), and test-retest or scan-rescan repeatability (intraclass correlation coefficients) were evaluated and compared across acquisitions.

RESULTS

Cramer-Rao lower bound and Monte Carlo simulations demonstrated improved noise performance of the optimal 2D sampling in comparison to monopolar samplings. Evaluating the designed b-M1 -optimized waveforms in healthy volunteers, significant decreases (p < 0.05) in the SDs and outlier percentages were observed for measurements of diffusion coefficient, perfusion fraction, and blood velocity SD in comparison to measurements obtained using monopolar samplings. Good-to-excellent repeatability (intraclass correlation coefficients ≥ 0.77) was observed for all 3 parameters in both the right and left liver lobes using the b-M1 -optimized waveforms.

CONCLUSIONS

2D b-M1 -optimized data acquisition enables repeatable IVIM quantification with improved noise performance. 2D acquisitions may advance the establishment of IVIM quantitative biomarkers for liver diseases.