Self-supervised IVIM DWI parameter estimation with a physics based forward model

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.

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.

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.

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.

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.

IVIM-Morph: Motion-compensated quantitative Intra-voxel Incoherent Motion (IVIM) analysis for functional fetal lung maturity assessment from diffusion-weighted MRI data

Quantitative analysis of pseudo-diffusion in diffusion-weighted magnetic resonance imaging (DWI) data shows potential for assessing fetal lung maturation and generating valuable imaging biomarkers. Yet, the clinical utility of DWI data is hindered by unavoidable fetal motion during acquisition. We present IVIM-morph, a self-supervised deep neural network model for motion-corrected quantitative analysis of DWI data using the Intra-voxel Incoherent Motion (IVIM) model. IVIM-morph combines two sub-networks, a registration sub-network, and an IVIM model fitting sub-network, enabling simultaneous estimation of IVIM model parameters and motion. To promote physically plausible image registration, we introduce a biophysically informed loss function that effectively balances registration and model-fitting quality. We validated the efficacy of IVIM-morph by establishing a correlation between the predicted IVIM model parameters of the lung and gestational age (GA) using fetal DWI data of 39 subjects. Our approach was compared against six baseline methods: 1) no motion compensation, 2) affine registration of all DWI images to the initial image, 3) deformable registration of all DWI images to the initial image, 4) deformable registration of each DWI image to its preceding image in the sequence, 5) iterative deformable motion compensation combined with IVIM model parameter estimation, and 6) self-supervised deep-learning-based deformable registration. IVIM-morph exhibited a notably improved correlation with gestational age (GA) when performing in-vivo quantitative analysis of fetal lung DWI data during the canalicular phase. Specifically, over 2 test groups of cases, it achieved an R f 2 of 0.44 and 0.52, outperforming the values of 0.27 and 0.25, 0.25 and 0.00, 0.00 and 0.00, 0.38 and 0.00, and 0.07 and 0.14 obtained by other methods. IVIM-morph shows potential in developing valuable biomarkers for non-invasive assessment of fetal lung maturity with DWI data. Moreover, its adaptability opens the door to potential applications in other clinical contexts where motion compensation is essential for quantitative DWI analysis. The IVIM-morph code is readily available at:https://github.com/TechnionComputationalMRILab/qDWI-Morph.

Improved myelin water fraction mapping with deep neural networks using synthetically generated 3D data

We introduce a generative model for synthesis of large scale 3D datasets for quantitative parameter mapping of myelin water fraction (MWF). Our model combines a MR physics signal decay model with an accurate probabilistic multi-component parametric T2 model. We synthetically generate a wide variety of high quality signals and corresponding parameters from a wide range of naturally occurring prior parameter values. To capture spatial variation, the generative signal decay model is combined with a generative spatial model conditioned on generic tissue segmentations. Synthesized 3D datasets can be used to train any convolutional neural network (CNN) based architecture for MWF estimation. Our source code is available at: https://github.com/quin-med-harvard-edu/synthmap Reduction of acquisition time at the expense of lower SNR, as well as accuracy and repeatability of MWF estimation techniques, are key factors that affect the adoption of MWF mapping in clinical practice. We demonstrate that the synthetically trained CNN provides superior accuracy over the competing methods under the constraints of naturally occurring noise levels as well as on the synthetically generated images at low SNR levels. Normalized root mean squared error (nRMSE) is less than 7% on synthetic data, which is significantly lower than competing methods. Additionally, the proposed method yields a coefficient of variation (CoV) that is at least 4x better than the competing method on intra-session test-retest reference dataset.

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.

Self Supervised Denoising Diffusion Probabilistic Models for Abdominal DW-MRI

Quantitative diffusion weighted MRI in the abdomen provides important markers of disease, however significant limitations exist for its accurate computation. One such limitation is the low signal-to-noise ratio, particularly at high diffusion b-values. To address this, multiple diffusion directional images can be collected at each b-value and geometrically averaged, which invariably leads to longer scan time, blurring due to motion and other artifacts. We propose a novel parameter estimation technique based on self supervised diffusion denoising probabilistic model that can effectively denoise diffusion weighted images and work on single diffusion gradient direction images. Our source code is made available at https://github.com/quin-med-harvard-edu/ssDDPM.

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.

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.

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.

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.

Uncertainty-aware self-supervised neural network for liverT1ρmapping with relaxation constraint

Objective.T1ρmapping is a promising quantitative MRI technique for the non-invasive assessment of tissue properties. Learning-based approaches can mapT1ρfrom a reduced number ofT1ρweighted images but requires significant amounts of high-quality training data. Moreover, existing methods do not provide the confidence level of theT1ρestimation. We aim to develop a learning-based liverT1ρmapping approach that can mapT1ρwith a reduced number of images and provide uncertainty estimation.Approach. We proposed a self-supervised neural network that learns aT1ρmapping using the relaxation constraint in the learning process. Epistemic uncertainty and aleatoric uncertainty are modelled for theT1ρquantification network to provide a Bayesian confidence estimation of theT1ρmapping. The uncertainty estimation can also regularize the model to prevent it from learning imperfect data. Main results. We conducted experiments onT1ρdata collected from 52 patients with non-alcoholic fatty liver disease. The results showed that when only collecting twoT1ρ-weighted images, our method outperformed the existing methods forT1ρquantification of the liver. Our uncertainty estimation can further regularize the model to improve the performance of the model and it is consistent with the confidence level of liverT1ρvalues.Significance. Our method demonstrates the potential for accelerating theT1ρmapping of the liver by using a reduced number of images. It simultaneously provides uncertainty ofT1ρquantification which is desirable in clinical applications.

The stability of oncologic MRI radiomic features and the potential role of deep learning: a review

The use of MRI radiomic models for the diagnosis, prognosis and treatment response prediction of tumors has been increasingly reported in literature. However, its widespread adoption in clinics is hampered by issues related to features stability. In the MRI radiomic workflow, the main factors that affect radiomic features computation can be found in the image acquisition and reconstruction phase, in the image pre-processing steps, and in the segmentation of the region of interest on which radiomic indices are extracted. Deep Neural Networks (DNNs), having shown their potentiality in the medical image processing and analysis field, can be seen as an attractive strategy to partially overcome the issues related to radiomic stability and mitigate their impact. In fact, DNN approaches can be prospectively integrated in the MRI radiomic workflow to improve image quality, obtain accurate and reproducible segmentations and generate standardized images. In this review, DNN methods that can be included in the image processing steps of the radiomic workflow are described and discussed, in the light of a detailed analysis of the literature in the context of MRI radiomic reliability.

A Clustering Approach to Improve IntraVoxel Incoherent Motion Maps from DW-MRI Using Conditional Auto-Regressive Bayesian Model

The Intra-Voxel Incoherent Motion (IVIM) model allows to estimate water diffusion and perfusion-related coefficients in biological tissues using diffusion weighted MR images. Among the available approaches to fit the IVIM bi-exponential decay, a segmented Bayesian algorithm with a Conditional Auto-Regressive (CAR) prior spatial regularization has been recently proposed to produce more reliable coefficient estimation. However, the CAR spatial regularization can generate inaccurate coefficient estimation, especially at the interfaces between different tissues. To overcome this problem, the segmented CAR model was coupled in this work with a k-means clustering approach, to separate different tissues and exclude voxels from other regions in the CAR prior specification. The proposed approach was compared with the original Bayesian CAR method without clustering and with a state-of-the-art Bayesian approach without CAR. The approaches were tested and compared on simulated images by calculating the estimation error and the coefficient of variation (CV). Furthermore, the proposed method was applied to some illustrative real images of oncologic patients. On simulated images, the proposed innovation reduced the average error of 47%, 21% and 58% for D, f and D*, respectively, compared to the state-of-the-art Bayesian approach, and of 48% and 34% for D and f, respectively, compared to the original CAR, while it achieved the same error for D*. The clustering approach was also able to consistently reduce the CV for each coefficient. On real images, the novel approach did not alter the IVIM maps obtained by the original CAR method, with the advantage of reducing their typical blotchy appearance at the boundaries. The proposed approach represents a valuable improvement over the state-of-the-art Bayesian CAR method and provides more reliable IVIM coefficient estimation, and is less sensitive to bias and inconsistency at tissue/tissue and tissue/background interfaces.