Neural networks for parameter estimation in microstructural MRI: Application to a diffusion-relaxation model of white matter

Physics-Informed Autoencoder for Prostate Tissue Microstructure Profiling with Hybrid Multidimensional MRI

Purpose To evaluate the performance of Physics-Informed Autoencoder (PIA), a self-supervised deep learning model, in measuring tissue-based biomarkers for prostate cancer (PCa) using hybrid multidimensional MRI. Materials and Methods This retrospective study introduces PIA, an emerging self-supervised deep learning model that integrates a three-compartment diffusion-relaxation model with hybrid multidimensional MRI. PIA was trained to encode the biophysical model into a deep neural network to predict measurements of tissue-specific biomarkers for PCa without extensive training data requirements. Comprehensive in silico and in vivo experiments, using histopathology measurements as the reference standard, were conducted to validate the model's efficacy in comparison to the traditional nonlinear least squares (NLLS) algorithm. PIA's robustness to noise was tested in in silico experiments with varying signal-to-noise ratio (SNR) conditions, and in vivo performance for estimating volume fractions was evaluated in 21 patients (mean age, 60 years ± 6.6 [SD]; all male) with PCa (71 regions of interest). Evaluation metrics included the intraclass correlation coefficient (ICC) and Pearson correlation coefficient. Results PIA predicted the reference standard tissue parameters with high accuracy, outperforming conventional NLLS methods, especially under noisy conditions (rs = 0.80 vs 0.65, P < .001 for epithelium volume at SNR of 20:1). In in vivo validation, PIA's noninvasive volume fraction estimates matched quantitative histology (ICC, 0.94, 0.85, and 0.92 for epithelium, stroma, and lumen compartments, respectively; P < .001 for all). PIA's measurements strongly correlated with PCa aggressiveness (r = 0.75, P < .001). Furthermore, PIA ran 10 000 faster than NLLS (0.18 second vs 40 minutes per image). Conclusion PIA provided accurate prostate tissue biomarker measurements from MRI data with better robustness to noise and computational efficiency compared with the NLLS algorithm. The results demonstrate the potential of PIA as an accurate, noninvasive, and explainable artificial intelligence method for PCa detection. Keywords: Prostate, Stacked Auto-Encoders, Tissue Characterization, MR-Diffusion-weighted Imaging Supplemental material is available for this article. ©RSNA, 2025 See also commentary by Adams and Bressem in this issue.

In vivo human neurite exchange imaging (NEXI) at 500 mT/m diffusion gradients

Evaluating tissue microstructure and membrane integrity in the living human brain through diffusion-water exchange imaging is challenging due to requirements for a high signal-to-noise ratio and short diffusion times dictated by relatively fast exchange processes. The goal of this work was to demonstrate the feasibility of in vivo imaging of tissue micro-geometries and water exchange within the brain gray matter using the state-of-the-art Connectome 2.0 scanner equipped with an ultra-high-performance gradient system (maximum gradient strength=500 mT/m, maximum slew rate=600 T/m/s). We performed diffusion MRI measurements in 15 healthy volunteers at multiple diffusion times (13-30 ms) and b -values up to 17.5 ms/μm2. The anisotropic Kärger model was applied to estimate the exchange time between intra-neurite and extracellular water in gray matter. The estimated exchange time across the cortical ribbon was around (median±interquartile range) 13±8 ms on Connectome 2.0, substantially faster than that measured using an imaging protocol compatible with Connectome 1.0-alike systems on the same cohort. Our investigation suggested that the NEXI exchange time estimation using a Connectome 1.0 compatible protocol was more prone to residual noise floor biases due to the small time-dependent signal contrasts across diffusion times when the exchange is fast (≤20 ms). Furthermore, spatial variation of exchange time was observed across the cortex, where the motor cortex, somatosensory cortex and visual cortex exhibit longer exchange times compared to other cortical regions. Non-linear fitting for the anisotropic Kärger model was accelerated 100 times using a GPU-based pipeline compared to the conventional CPU-based approach. This study highlighted the importance of the chosen diffusion times and measures to address Rician noise in dMRI data, which can have a substantial impact on the estimated NEXI exchange time and require extra attention when comparing NEXI results between various hardware setups.

Introducing µGUIDE for quantitative imaging via generalized uncertainty-driven inference using deep learning

This work proposes µGUIDE: a general Bayesian framework to estimate posterior distributions of tissue microstructure parameters from any given biophysical model or signal representation, with exemplar demonstration in diffusion-weighted magnetic resonance imaging. Harnessing a new deep learning architecture for automatic signal feature selection combined with simulation-based inference and efficient sampling of the posterior distributions, µGUIDE bypasses the high computational and time cost of conventional Bayesian approaches and does not rely on acquisition constraints to define model-specific summary statistics. The obtained posterior distributions allow to highlight degeneracies present in the model definition and quantify the uncertainty and ambiguity of the estimated parameters.

Diffusion MRI with Machine Learning

Diffusion-weighted magnetic resonance imaging (dMRI) of the brain offers unique capabilities including noninvasive probing of tissue microstructure and structural connectivity. It is widely used for clinical assessment of disease and injury, and for neuroscience research. Analyzing the dMRI data to extract useful information for medical and scientific purposes can be challenging. The dMRI measurements may suffer from strong noise and artifacts, and may exhibit high inter-session and inter-scanner variability in the data, as well as inter-subject heterogeneity in brain structure. Moreover, the relationship between measurements and the phenomena of interest can be highly complex. Recent years have witnessed increasing use of machine learning methods for dMRI analysis. This manuscript aims to assess these efforts, with a focus on methods that have addressed data preprocessing and harmonization, microstructure mapping, tractography, and white matter tract analysis. We study the main findings, strengths, and weaknesses of the existing methods and suggest topics for future research. We find that machine learning may be exceptionally suited to tackle some of the difficult tasks in dMRI analysis. However, for this to happen, several shortcomings of existing methods and critical unresolved issues need to be addressed. There is a pressing need to improve evaluation practices, to increase the availability of rich training datasets and validation benchmarks, as well as model generalizability, reliability, and explainability concerns.

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.

Neural underpinnings of fine motor skills under stress and anxiety: A review

This review offers a comprehensive examination of how stress and anxiety affect motor behavior, particularly focusing on fine motor skills and gait adaptability. We explore the role of several neurochemicals, including brain-derived neurotrophic factor (BDNF) and dopamine, in modulating neural plasticity and motor control under these affective states. The review highlights the importance of developing therapeutic strategies that enhance motor performance by leveraging the interactions between key neurochemicals. Additionally, we investigate the complex interplay between emotional-cognitive states and sensorimotor behaviors, showing how stress and anxiety disrupt neural integration, leading to impairments in skilled movements and negatively impacting quality of life. Synthesizing evidence from human and rodent studies, we provide a detailed understanding of the relationships among stress, anxiety, and motor behavior. Our findings reveal neurophysiological pathways, behavioral outcomes, and potential therapeutic targets, emphasizing the intricate connections between neurobiological mechanisms, environmental factors, and motor performance.

Fast multi-compartment Microstructure Fingerprinting in brain white matter

We proposed two deep neural network based methods to accelerate the estimation of microstructural features of crossing fascicles in the white matter. Both methods focus on the acceleration of a multi-dictionary matching problem, which is at the heart of Microstructure Fingerprinting, an extension of Magnetic Resonance Fingerprinting to diffusion MRI. The first acceleration method uses efficient sparse optimization and a dedicated feed-forward neural network to circumvent the inherent combinatorial complexity of the fingerprinting estimation. The second acceleration method relies on a feed-forward neural network that uses a spherical harmonics representation of the DW-MRI signal as input. The first method exhibits a high interpretability while the second method achieves a greater speedup factor. The accuracy of the results and the speedup factors of several orders of magnitude obtained on in vivo brain data suggest the potential of our methods for a fast quantitative estimation of microstructural features in complex white matter configurations.

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.

Sparse Blind Spherical Deconvolution of diffusion weighted MRI

Diffusion-weighted magnetic resonance imaging provides invaluable insights into in-vivo neurological pathways. However, accurate and robust characterization of white matter fibers microstructure remains challenging. Widely used spherical deconvolution algorithms retrieve the fiber Orientation Distribution Function (ODF) by using an estimation of a response function, i.e., the signal arising from individual fascicles within a voxel. In this paper, an algorithm of blind spherical deconvolution is proposed, which only assumes the axial symmetry of the response function instead of its exact knowledge. This algorithm provides a method for estimating the peaks of the ODF in a voxel without any explicit response function, as well as a method for estimating signals associated with the peaks of the ODF, regardless of how those peaks were obtained. The two stages of the algorithm are tested on Monte Carlo simulations, as well as compared to state-of-the-art methods on real in-vivo data for the orientation retrieval task. Although the proposed algorithm was shown to attain lower angular errors than the state-of-the-art constrained spherical deconvolution algorithm on synthetic data, it was outperformed by state-of-the-art spherical deconvolution algorithms on in-vivo data. In conjunction with state-of-the art methods for axon bundles direction estimation, the proposed method showed its potential for the derivation of per-voxel per-direction metrics on synthetic as well as in-vivo data.

Optimisation of quantitative brain diffusion-relaxation MRI acquisition protocols with physics-informed machine learning

Diffusion-relaxation MRI aims to extract quantitative measures that characterise microstructural tissue properties such as orientation, size, and shape, but long acquisition times are typically required. This work proposes a physics-informed learning framework to extract an optimal subset of diffusion-relaxation MRI measurements for enabling shorter acquisition times, predict non-measured signals, and estimate quantitative parameters. In vivo and synthetic brain 5D-Diffusion-T1-T2∗-weighted MRI data obtained from five healthy subjects were used for training and validation, and from a sixth participant for testing. One fully data-driven and two physics-informed machine learning methods were implemented and compared to two manual selection procedures and Cramér-Rao lower bound optimisation. The physics-informed approaches could identify measurement-subsets that yielded more consistently accurate parameter estimates in simulations than other approaches, with similar signal prediction error. Five-fold shorter protocols yielded error distributions of estimated quantitative parameters with very small effect sizes compared to estimates from the full protocol. Selected subsets commonly included a denser sampling of the shortest and longest inversion time, lowest echo time, and high b-value. The proposed framework combining machine learning and MRI physics offers a promising approach to develop shorter imaging protocols without compromising the quality of parameter estimates and signal predictions.

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.

Comprehensive Brain Tumour Characterisation with VERDICT-MRI: Evaluation of Cellular and Vascular Measures Validated by Histology

The aim of this work was to extend the VERDICT-MRI framework for modelling brain tumours, enabling comprehensive characterisation of both intra- and peritumoural areas with a particular focus on cellular and vascular features. Diffusion MRI data were acquired with multiple b-values (ranging from 50 to 3500 s/mm2), diffusion times, and echo times in 21 patients with brain tumours of different types and with a wide range of cellular and vascular features. We fitted a selection of diffusion models that resulted from the combination of different types of intracellular, extracellular, and vascular compartments to the signal. We compared the models using criteria for parsimony while aiming at good characterisation of all of the key histological brain tumour components. Finally, we evaluated the parameters of the best-performing model in the differentiation of tumour histotypes, using ADC (Apparent Diffusion Coefficient) as a clinical standard reference, and compared them to histopathology and relevant perfusion MRI metrics. The best-performing model for VERDICT in brain tumours was a three-compartment model accounting for anisotropically hindered and isotropically restricted diffusion and isotropic pseudo-diffusion. VERDICT metrics were compatible with the histological appearance of low-grade gliomas and metastases and reflected differences found by histopathology between multiple biopsy samples within tumours. The comparison between histotypes showed that both the intracellular and vascular fractions tended to be higher in tumours with high cellularity (glioblastoma and metastasis), and quantitative analysis showed a trend toward higher values of the intracellular fraction (fic) within the tumour core with increasing glioma grade. We also observed a trend towards a higher free water fraction in vasogenic oedemas around metastases compared to infiltrative oedemas around glioblastomas and WHO 3 gliomas as well as the periphery of low-grade gliomas. In conclusion, we developed and evaluated a multi-compartment diffusion MRI model for brain tumours based on the VERDICT framework, which showed agreement between non-invasive microstructural estimates and histology and encouraging trends for the differentiation of tumour types and sub-regions.

dtiRIM: A generalisable deep learning method for diffusion tensor imaging

Diffusion weighted MRI is an indispensable tool for routine patient screening and diagnostics of pathology. Recently, several deep learning methods have been proposed to quantify diffusion parameters, but poor generalisation to new data prevents broader use of these methods, as they require retraining of the neural network for each new scan protocol. In this work, we present the dtiRIM, a new deep learning method for Diffusion Tensor Imaging (DTI) based on the Recurrent Inference Machines. Thanks to its ability to learn how to solve inverse problems and to use the diffusion tensor model to promote data consistency, the dtiRIM can generalise to variations in the acquisition settings. This enables a single trained network to produce high quality tensor estimates for a variety of cases. We performed extensive validation of our method using simulation and in vivo data, and compared it to the Iterated Weighted Linear Least Squares (IWLLS), the approach of the state-of-the-art MRTrix3 software, and to an implementation of the Maximum Likelihood Estimator (MLE). Our results show that dtiRIM predictions present low dependency on tissue properties, anatomy and scanning parameters, with results comparable to or better than both IWLLS and MLE. Further, we demonstrate that a single dtiRIM model can be used for a diversity of data sets without significant loss in quality, representing, to our knowledge, the first generalisable deep learning based solver for DTI.

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.

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.

The distortions of the free water model for diffusion MRI data when assuming single compartment relaxometry and proton density

Objective.To document the bias of thesimplifiedfree water model of diffusion MRI (dMRI) signal vis-à-vis aspecificmodel which, in addition to diffusion, incorporates compartment-specific proton density (PD), T1 recovery during repetition time (TR), and T2 decay during echo time (TE).Approach.Both models assume that volume fractionfof the total signal in any voxel arises from the free water compartment (fw) such as cerebrospinal fluid or edema, and the remainder (1-f) from hindered water (hw) which is constrained by cellular structures such as white matter (WM). Thespecificandsimplifiedmodels are compared on a synthetic dataset, using a range of PD, T1 and T2 values. We then fit the models to anin vivohealthy brain dMRI dataset. For bothsyntheticandin vivodata we use experimentally feasible TR, TE, signal-to-noise ratio (SNR) and physiologically plausible diffusion profiles.Main results.From the simulations we see that the difference between the estimatedsimplified fandspecific fis largest for mid-range ground-truthf, and it increases as SNR increases. The estimation of volume fractionfis sensitive to the choice of model,simplifiedorspecific, but the estimated diffusion parameters are robust to small perturbations in the simulation.Specific fis more accurate and precise thansimplified f. In the white matter (WM) regions of thein vivoimages,specific fis lower thansimplified f.Significance.In dMRI models for free water, accounting for compartment specific PD, T1 and T2, in addition to diffusion, improves the estimation of model parameters. This extra model specification attenuates the estimation bias of compartmental volume fraction without affecting the estimation of other diffusion parameters.

Reproducibility of the Standard Model of diffusion in white matter on clinical MRI systems

Estimating intra- and extra-axonal microstructure parameters, such as volume fractions and diffusivities, has been one of the major efforts in brain microstructure imaging with MRI. The Standard Model (SM) of diffusion in white matter has unified various modeling approaches based on impermeable narrow cylinders embedded in locally anisotropic extra-axonal space. However, estimating the SM parameters from a set of conventional diffusion MRI (dMRI) measurements is ill-conditioned. Multidimensional dMRI helps resolve the estimation degeneracies, but there remains a need for clinically feasible acquisitions that yield robust parameter maps. Here we find optimal multidimensional protocols by minimizing the mean-squared error of machine learning-based SM parameter estimates for two 3T scanners with corresponding gradient strengths of 40and80mT/m. We assess intra-scanner and inter-scanner repeatability for 15-minute optimal protocols by scanning 20 healthy volunteers twice on both scanners. The coefficients of variation all SM parameters except free water fraction are ≲10% voxelwise and 1-4% for their region-averaged values. As the achieved SM reproducibility outcomes are similar to those of conventional diffusion tensor imaging, our results enable robust in vivo mapping of white matter microstructure in neuroscience research and in the clinic.

Neurite Exchange Imaging (NEXI): A minimal model of diffusion in gray matter with inter-compartment water exchange

Biophysical models of diffusion in white matter have been center-stage over the past two decades and are essentially based on what is now commonly referred to as the "Standard Model" (SM) of non-exchanging anisotropic compartments with Gaussian diffusion. In this work, we focus on diffusion MRI in gray matter, which requires rethinking basic microstructure modeling blocks. In particular, at least three contributions beyond the SM need to be considered for gray matter: water exchange across the cell membrane - between neurites and the extracellular space; non-Gaussian diffusion along neuronal and glial processes - resulting from structural disorder; and signal contribution from soma. For the first contribution, we propose Neurite Exchange Imaging (NEXI) as an extension of the SM of diffusion, which builds on the anisotropic Kärger model of two exchanging compartments. Using datasets acquired at multiple diffusion weightings (b) and diffusion times (t) in the rat brain in vivo, we investigate the suitability of NEXI to describe the diffusion signal in the gray matter, compared to the other two possible contributions. Our results for the diffusion time window 20-45 ms show minimal diffusivity time-dependence and more pronounced kurtosis decay with time, which is well fit by the exchange model. Moreover, we observe lower signal for longer diffusion times at high b. In light of these observations, we identify exchange as the mechanism that best explains these signal signatures in both low-b and high-b regime, and thereby propose NEXI as the minimal model for gray matter microstructure mapping. We finally highlight multi-b multi-t acquisition protocols as being best suited to estimate NEXI model parameters reliably. Using this approach, we estimate the inter-compartment water exchange time to be 15 - 60 ms in the rat cortex and hippocampus in vivo, which is of the same order or shorter than the diffusion time in typical diffusion MRI acquisitions. This suggests water exchange as an essential component for interpreting diffusion MRI measurements in gray matter.

Diffusion tensor estimation with transformer neural networks

Diffusion tensor imaging (DTI) is a widely used method for studying brain white matter development and degeneration. However, standard DTI estimation methods depend on a large number of high-quality measurements. This would require long scan times and can be particularly difficult to achieve with certain patient populations such as neonates. Here, we propose a method that can accurately estimate the diffusion tensor from only six diffusion-weighted measurements. Our method achieves this by learning to exploit the relationships between the diffusion signals and tensors in neighboring voxels. Our model is based on transformer networks, which represent the state of the art in modeling the relationship between signals in a sequence. In particular, our model consists of two such networks. The first network estimates the diffusion tensor based on the diffusion signals in a neighborhood of voxels. The second network provides more accurate tensor estimations by learning the relationships between the diffusion signals as well as the tensors estimated by the first network in neighboring voxels. Our experiments with three datasets show that our proposed method achieves highly accurate estimations of the diffusion tensor and is significantly superior to three competing methods. Estimations produced by our method with six diffusion-weighted measurements are comparable with those of standard estimation methods with 30-88 diffusion-weighted measurements. Hence, our method promises shorter scan times and more reliable assessment of brain white matter, particularly in non-cooperative patients such as neonates and infants.

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

PURPOSE

To assess the robustness and repeatability of intravoxel incoherent motion model (IVIM) parameter estimation for the diffusion-weighted MRI in the abdominal organs under the constraints of noisy diffusion signal using a novel neural network method.

METHODS

Clinically acquired abdominal scans of Crohn's disease patients were retrospectively analyzed with regions segmented in the kidney cortex, spleen, liver, and bowel. A novel IVIM parameter fitting method based on the principle of a physics guided self-supervised convolutional neural network that does not require reference parameter estimates for training was compared to a conventional non-linear least squares (NNLS) algorithm, and a voxelwise trained artificial neural network (ANN).

RESULTS

Results showed substantial increase in parameter robustness to the noise corrupted signal. In an intra-session repeatability experiment, the proposed method showed reduced coefficient of variation (CoV) over multiple acquisitions in comparison to conventional NLLS method and comparable performance to ANN. The use of D and f estimates from the proposed method led to the smallest misclassification error in linear discriminant analysis for characterization between normal and abnormal Crohn's disease bowel tissue. The fitting of D∗ parameter remains to be challenging.

CONCLUSION

The proposed method yields robust estimates of D and f IVIM parameters under the constraints of noisy diffusion signal. This indicates a potential for the use of the proposed method in conjunction with accelerated DW-MRI acquisition strategies, which would typically result in lower signal to noise ratio.