q-Space Deep Learning: Twelve-Fold Shorter and Model-Free Diffusion MRI Scans

Accelerated diffusion tensor imaging with self-supervision and fine-tuning

Diffusion tensor imaging (DTI) is essential for assessing brain microstructure but requires long acquisition times, limiting clinical use. Recent deep learning (DL) approaches, such as SuperDTI or deepDTI, improve DTI metrics but demand large, high-quality datasets for training. We propose a self-supervised deep learning with fine-tuning (SSDLFT) framework to reduce training data requirements. SSDLFT involves self-supervised pretraining, which denoises data without clean labels, followed by fine-tuning with limited high-quality data. Experiments using Human Connectome Project data show that SSDLFT outperforms traditional methods and other DL approaches in qualitative and quantitative assessments of DWI reconstructions and tensor metrics. SSDLFT's ability to maintain high performance with fewer training subjects and DWIs presents a significant advancement, enhancing DTI's practical applications in clinical and research settings.

Tissue classification from raw diffusion-weighted images using machine learning

BACKGROUND

In diffusion-weighted imaging (DWI), a large collection of diffusion models is available to provide insights into tissue characteristics. However, these models are limited by predefined assumptions and computational challenges, potentially hindering the full extraction of information from the diffusion MR signal.

PURPOSE

This study aimed at developing a MOdel-free Diffusion-wEighted MRI (MODEM) method for tissue differentiation by using a machine learning (ML) algorithm based on raw diffusion images without relying on any specific diffusion model. MODEM has been applied to both simulation data and cervical cancer diffusion images and compared with several diffusion models.

METHODS

With Institutional Review Board approval, 54 cervical cancer patients (median age, 52 years; age range, 29-73 years) participated in the study, including 26 in the early FIGO (International Federation of Gynecology and Obstetrics) stage (IB, 16; IIA, 10) and 28 the late stage (IIB, 8; IIIB, 14; IIIC, 1; IVA, 3; IVB, 2). The participants underwent DWI with 17 b-values (0 to 4500 s/mm2) at 3 Tesla. Synthetic diffusion MRI signals were also generated using Monte-Carlo simulation with Gaussian noise doping under varying substrates. MODEM with multilayer perceptron and five diffusion models (mono-exponential, intra-voxel incoherent-motion, diffusion kurtosis imaging, fractional order calculus, and continuous-time-random-walk models) were employed to distinguish different substrates in the simulation data and differentiate different pathological states (i.e., normal vs. cancerous tissue; and early-stage vs. late-stage cancers) in the cervical cancer dataset. Accuracy and area under the receiver operating characteristic (ROC) curve were evaluated. Mann-Whitney U-test was used to compare the area under the curve (AUC) and accuracy values between MODEM and the five diffusion models.

RESULTS

For the simulation dataset, MODEM produced a higher AUC and better accuracy, particularly in scenarios where the noise level exceeded 5%. For the cervical cancer dataset, MODEM yielded the highest AUC and accuracy in cervical cancer detection (AUC, 0.976; accuracy, 91.9%) and cervical cancer staging (AUC, 0.773; accuracy, 69.2%), significantly outperforming any of the diffusion models (p < 0.05).

CONCLUSIONS

MODEM is useful for cervical cancer detection and staging and offers considerable advantages over analytical diffusion models for tissue characterization.

The role of AI for MRI-analysis in multiple sclerosis-A brief overview

Magnetic resonance imaging (MRI) has played a crucial role in the diagnosis, monitoring and treatment optimization of multiple sclerosis (MS). It is an essential component of current diagnostic criteria for its ability to non-invasively visualize both lesional and non-lesional pathology. Nevertheless, modern day usage of MRI in the clinic is limited by lengthy protocols, error-prone procedures for identifying disease markers (e.g., lesions), and the limited predictive value of existing imaging biomarkers for key disability outcomes. Recent advances in artificial intelligence (AI) have underscored the potential for AI to not only improve, but also transform how MRI is being used in MS. In this short review, we explore the role of AI in MS applications that span the entire life-cycle of an MRI image, from data collection, to lesion segmentation, detection, and volumetry, and finally to downstream clinical and scientific tasks. We conclude with a discussion on promising future directions.

Conditional generative diffusion deep learning for accelerated diffusion tensor and kurtosis imaging

PURPOSE

The purpose of this study was to develop DiffDL, a generative diffusion probabilistic model designed to produce high-quality diffusion tensor imaging (DTI) and diffusion kurtosis imaging (DKI) metrics from a reduced set of diffusion-weighted images (DWIs). This model addresses the challenge of prolonged data acquisition times in diffusion MRI while preserving metric accuracy.

METHODS

DiffDL was trained using data from the Human Connectome Project, including 300 training/validation subjects and 50 testing subjects. High-quality DTI and DKI metrics were generated using many DWIs and combined with subsets of DWIs to form training pairs. A UNet architecture was used for denoising, trained over 500 epochs with a linear noise schedule. Performance was evaluated against conventional DTI/DKI modeling and a reference UNet model using normalized mean absolute error (NMAE), peak signal-to-noise ratio (PSNR), and Pearson correlation coefficient (PCC).

RESULTS

DiffDL showed significant improvements in the quality and accuracy of fractional anisotropy (FA) and mean diffusivity (MD) maps compared to conventional methods and the baseline UNet model. For DKI metrics, DiffDL outperformed conventional DKI modeling and the UNet model across various acceleration scenarios. Quantitative analysis demonstrated superior NMAE, PSNR, and PCC values for DiffDL, capturing the full dynamic range of DTI and DKI metrics. The generative nature of DiffDL allowed for multiple predictions, enabling uncertainty quantification and enhancing performance.

CONCLUSION

The DiffDL framework demonstrated the potential to significantly reduce data acquisition times in diffusion MRI while maintaining high metric quality. Future research should focus on optimizing computational demands and validating the model with clinical cohorts and standard MRI scanners.

Gauge equivariant convolutional neural networks for diffusion MRI

Diffusion MRI (dMRI) is an imaging technique widely used in neuroimaging research, where the signal carries directional information of underlying neuronal fibres based on the diffusivity of water molecules. One of the shortcomings of dMRI is that numerous images, sampled at gradient directions on a sphere, must be acquired to achieve a reliable angular resolution for model-fitting, which translates to longer scan times, higher costs, and barriers to clinical adoption. In this work we introduce gauge equivariant convolutional neural network (gCNN) layers for dMRI that overcome the challenges associated with the signal being acquired on a sphere with antipodal points identified. This is done by noting that the domain is equivalent to the real projective plane, [Formula: see text], which is a non-euclidean and a non-orientable manifold. This is in stark contrast to a rectangular grid which typical convolutional neural networks (CNNs) are designed for. We apply our method to upsample angular resolution for predicting diffusion tensor imaging (DTI) parameters from just six diffusion gradient directions. The symmetries introduced allow gCNNs the ability to train with fewer subjects as compared to a baseline model that involves only 3D convolutions.

SE(3) group convolutional neural networks and a study on group convolutions and equivariance for DWI segmentation

We present an SE(3) Group Convolutional Neural Network along with a series of networks with different group actions for segmentation of Diffusion Weighted Imaging data. These networks gradually incorporate group actions that are natural for this type of data, in the form of convolutions that provide equivariant transformations of the data. This knowledge provides a potentially important inductive bias and may alleviate the need for data augmentation strategies. We study the effects of these actions on the performances of the networks by training and validating them using the diffusion data from the Human Connectome project. Unlike previous works that use Fourier-based convolutions, we implement direct convolutions, which are more lightweight. We show how incorporating more actions - using the SE(3) group actions - generally improves the performances of our segmentation while limiting the number of parameters that must be learned.

Self-supervised arbitrary-scale super-angular resolution diffusion MRI reconstruction

BACKGROUND

Diffusion magnetic resonance imaging (dMRI) is currently the unique noninvasive imaging technique to investigate the microstructure of in vivo tissues. To fully explore the complex tissue microstructure at sub-voxel scale, diffusion weighted (DW) images along many diffusion gradient directions are usually acquired, this is undoubtedly time consuming and inhibits their clinical applications. How to estimate the tissue microstructure only from DW images acquired with few diffusion directions remains a challenge.

PURPOSE

To address this challenge, we propose a self-supervised arbitrary scale super-angular resolution diffusion MRI reconstruction network (SARDI-nn), which can generate DW images along any directions from few acquisitions, allowing to overcome the limits of diffusion direction number on exploring the tissue microstructure.

METHODS

SARDI-nn is mainly composed of a diffusion direction-specific DW image feature extraction (DWFE) module and a physics-driven implicit expression and reconstruction (IRR) module. During training, dual downsampling operations are implemented. The first downsampling is used to produce the low-angular resolution (LAR) DW images; the second downsampling is for constructing input and learning target of SARDI-nn. The input LAR DW images pass through a DWFE module (composed of several residual blocks) to extract the feature representations of DW images along input directions, and then these features and the difference between the any querying diffusion direction and the input directions are input into a IRR module to derive the implicit representation and DW image along this query direction. Finally, based on the principle of dMRI, an adaptive weighting method is used to refine the DW image quality. During testing, given any diffusion directions, we can simply infer the corresponding DW images along these directions, accordingly, SARDI-nn can realize arbitrary scale angular super resolution. To test the effectiveness of the proposed method, we compare it with several existing methods in terms of peak signal to noise ratio (PSNR), structural similarity index measure (SSIM), and root mean square error (RMSE) of DW image and microstructure metrics derived from diffusion kurtosis imaging (DKI) and neurite orientation dispersion and density imaging (NODDI) models at different upsampling scales on Human Connectome Project (HCP) and several in-house datasets.

RESULTS

The comparison results demonstrate that our method achieves almost the best performance at all scales, with SSIM of reconstructed DW images improved by 10.04% at the upscale of 3 and 5.9% at the upscale of 15. Regarding the microstructures derived from DKI and NODDI models, when the upscale is not larger than 6, our method outperforms the best supervised learning method. In addition, the test results on external datasets show the well generality of our method.

CONCLUSIONS

SARDI-nn is currently the only method that can reconstruct high-angular resolution DW images with any upscales, which allows the variation of both input diffusion direction number and upscales, therefore, it can be easily extended to any unseen test datasets, not requiring to retrain the model. SARDI-nn provides a promising means for exploring the tissue microstructures from DW images along few diffusion gradient directions.

Attention-Based Q-Space Deep Learning Generalized for Accelerated Diffusion Magnetic Resonance Imaging

Diffusion magnetic resonance imaging (dMRI) is a non-invasive method for capturing the microanatomical information of tissues by measuring the diffusion weighted signals along multiple directions, which is widely used in the quantification of microstructures. Obtaining microscopic parameters requires dense sampling in the q space, leading to significant time consumption. The most popular approach to accelerating dMRI acquisition is to undersample the q-space data, along with applying deep learning methods to reconstruct quantitative diffusion parameters. However, the reliance on a predetermined q-space sampling strategy often constrains traditional deep learning-based reconstructions. The present study proposed a novel deep learning model, named attention-based q-space deep learning (aqDL), to implement the reconstruction with variable q-space sampling strategies. The aqDL maps dMRI data from different scanning strategies onto a common feature space by using a series of Transformer encoders. The latent features are employed to reconstruct dMRI parameters via a multilayer perceptron. The performance of the aqDL model was assessed utilizing the Human Connectome Project datasets at varying undersampling numbers. To validate its generalizability, the model was further tested on two additional independent datasets. Our results showed that aqDL consistently achieves the highest reconstruction accuracy at various undersampling numbers, regardless of whether variable or predetermined q-space scanning strategies are employed. These findings suggest that aqDL has the potential to be used on general clinical dMRI datasets.

Blip-up blip-down circular EPI (BUDA-cEPI) for distortion-free dMRI with rapid unrolled deep learning reconstruction

PURPOSE

BUDA-cEPI has been shown to achieve high-quality, high-resolution diffusion magnetic resonance imaging (dMRI) with fast acquisition time, particularly when used in conjunction with S-LORAKS reconstruction. However, this comes at a cost of more complex reconstruction that is computationally prohibitive. In this work we develop rapid reconstruction pipeline for BUDA-cEPI to pave the way for its deployment in routine clinical and neuroscientific applications. The proposed reconstruction includes the development of ML-based unrolled reconstruction as well as rapid ML-based B0 and eddy current estimations that are needed. The architecture of the unroll network was designed so that it can mimic S-LORAKS regularization well, with the addition of virtual coil channels.

METHODS

BUDA-cEPI RUN-UP - a model-based framework that incorporates off-resonance and eddy current effects was unrolled through an artificial neural network with only six gradient updates. The unrolled network alternates between data consistency (i.e., forward BUDA-cEPI and its adjoint) and regularization steps where U-Net plays a role as the regularizer. To handle the partial Fourier effect, the virtual coil concept was also introduced into the reconstruction to effectively take advantage of the smooth phase prior and trained to predict the ground-truth images obtained by BUDA-cEPI with S-LORAKS.

RESULTS

The introduction of the Virtual Coil concept into the unrolled network was shown to be key to achieving high-quality reconstruction for BUDA-cEPI. With the inclusion of an additional non-diffusion image (b-value = 0 s/mm2), a slight improvement was observed, with the normalized root mean square error further reduced by approximately 5 %. The reconstruction times for S-LORAKS and the proposed unrolled networks were approximately 225 and 3 s per slice, respectively.

CONCLUSION

BUDA-cEPI RUN-UP was shown to reduce the reconstruction time by ∼88× when compared to the state-of-the-art technique, while preserving imaging details as demonstrated through DTI application.

tDKI-Net: A Joint q-t Space Learning Network for Diffusion-Time-Dependent Kurtosis Imaging

Time-dependent diffusion magnetic resonance imaging (TDDMRI) is useful for the non-invasive characterization of tissue microstructure. These models require densely sampled q-t space data for microstructural fitting, leading to very time-consuming acquisition protocols. To overcome this problem, we present a joint q-t space model-tDKI-Net to estimate diffusion-time dependent kurtosis and the transmembrane exchange, using downsampled q-t space data. The tDKI-Net is composed of several q-Encoders and a t-Encoder, designed based on the extragradient mechanism, each integrated with their respective mapping networks. In the tDKI-Net, two types of encoders along with their mapping networks are employed sequentially to generate kurtosis at individual diffusion times and to fit the transmembrane exchange time () using the time-dependent kurtosis according to the Kärger's model. Meanwhile, we proposed a three-stage training strategy, including physics-informed self-supervised pretraining, DKI warm-up, and joint training, to match the network structure. Our results demonstrated that the proposed tDKI-Net could effectively accelerate tDKI scans, resulting in lower estimation error compared with other methods. Our proposed three-stage training strategy demonstrated superior results than those training from scratch, e.g., the normalized root mean square error (NRMSE) of decreased by up to 1.4%. We also investigated the training data size effects and found that although we used one-subject training, the network achieved lower NRMSEs for , and (2.50%, 3.04%, 10.86%) than previous work that used three-subject training (3.8%, 9.5%, 12.1%). tDKI-Net can considerably reduce the scan time by 10.5-fold by joint downsampling the q-t space data without compromising the estimation accuracy.

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.

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.

Deep learning enables accurate brain tissue microstructure analysis based on clinically feasible diffusion magnetic resonance imaging

Diffusion magnetic resonance imaging (dMRI) allows non-invasive assessment of brain tissue microstructure. Current model-based tissue microstructure reconstruction techniques require a large number of diffusion gradients, which is not clinically feasible due to imaging time constraints, and this has limited the use of tissue microstructure information in clinical settings. Recently, approaches based on deep learning (DL) have achieved promising tissue microstructure reconstruction results using clinically feasible dMRI. However, it remains unclear whether the subtle tissue changes associated with disease or age are properly preserved with DL approaches and whether DL reconstruction results can benefit clinical applications. Here, we provide the first evidence that DL approaches to tissue microstructure reconstruction yield reliable brain tissue microstructure analysis based on clinically feasible dMRI scans. Specifically, we reconstructed tissue microstructure from four different brain dMRI datasets with only 12 diffusion gradients, a clinically feasible protocol, and the neurite orientation dispersion and density imaging (NODDI) and spherical mean technique (SMT) models were considered. With these results we show that disease-related and age-dependent alterations of brain tissue were accurately identified. These findings demonstrate that DL tissue microstructure reconstruction can accurately quantify microstructural alterations in the brain based on clinically feasible dMRI.

Anatomically constrained tractography of the fetal brain

Diffusion-weighted Magnetic Resonance Imaging (dMRI) is increasingly used to study the fetal brain in utero. An important computation enabled by dMRI is streamline tractography, which has unique applications such as tract-specific analysis of the brain white matter and structural connectivity assessment. However, due to the low fetal dMRI data quality and the challenging nature of tractography, existing methods tend to produce highly inaccurate results. They generate many false streamlines while failing to reconstruct the streamlines that constitute the major white matter tracts. In this paper, we advocate for anatomically constrained tractography based on an accurate segmentation of the fetal brain tissue directly in the dMRI space. We develop a deep learning method to compute the segmentation automatically. Experiments on independent test data show that this method can accurately segment the fetal brain tissue and drastically improve the tractography results. It enables the reconstruction of highly curved tracts such as optic radiations. Importantly, our method infers the tissue segmentation and streamline propagation direction from a diffusion tensor fit to the dMRI data, making it applicable to routine fetal dMRI scans. The proposed method can facilitate the study of fetal brain white matter tracts with dMRI.

Deep learning microstructure estimation of developing brains from diffusion MRI: A newborn and fetal study

Diffusion-weighted magnetic resonance imaging (dMRI) is widely used to assess the brain white matter. Fiber orientation distribution functions (FODs) are a common way of representing the orientation and density of white matter fibers. However, with standard FOD computation methods, accurate estimation requires a large number of measurements that usually cannot be acquired for newborns and fetuses. We propose to overcome this limitation by using a deep learning method to map as few as six diffusion-weighted measurements to the target FOD. To train the model, we use the FODs computed using multi-shell high angular resolution measurements as target. Extensive quantitative evaluations show that the new deep learning method, using significantly fewer measurements, achieves comparable or superior results than standard methods such as Constrained Spherical Deconvolution and two state-of-the-art deep learning methods. For voxels with one and two fibers, respectively, our method shows an agreement rate in terms of the number of fibers of 77.5% and 22.2%, which is 3% and 5.4% higher than other deep learning methods, and an angular error of 10° and 20°, which is 6° and 5° lower than other deep learning methods. To determine baselines for assessing the performance of our method, we compute agreement metrics using densely sampled newborn data. Moreover, we demonstrate the generalizability of the new deep learning method across scanners, acquisition protocols, and anatomy on two clinical external datasets of newborns and fetuses. We validate fetal FODs, successfully estimated for the first time with deep learning, using post-mortem histological data. Our results show the advantage of deep learning in computing the fiber orientation density for the developing brain from in-vivo dMRI measurements that are often very limited due to constrained acquisition times. Our findings also highlight the intrinsic limitations of dMRI for probing the developing brain microstructure.

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.

Deep learning denoising reconstruction enables faster T2-weighted FLAIR sequence acquisition with satisfactory image quality

INTRODUCTION

Deep learning reconstruction (DLR) technologies are the latest methods attempting to solve the enduring problem of reducing MRI acquisition times without compromising image quality. The clinical utility of this reconstruction technique is yet to be fully established. This study aims to assess whether a commercially available DLR technique applied to 2D T2-weighted FLAIR brain images allows a reduction in scan time, without compromising image quality and thus diagnostic accuracy.

METHODS

47 participants (24 male, mean age 55.9 ± 18.7 SD years, range 20-89 years) underwent routine, clinically indicated brain MRI studies in March 2022, that included a standard-of-care (SOC) T2-weighted FLAIR sequence, and an accelerated acquisition that was reconstructed using the DLR denoising product. Overall image quality, lesion conspicuity, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and artefacts for each sequence, and preferred sequence on direct comparison, were subjectively assessed by two readers.

RESULTS

There was a strong preference for SOC FLAIR sequence for overall image quality (P = 0.01) and head-to-head comparison (P < 0.001). No difference was observed for lesion conspicuity (P = 0.49), perceived SNR (P = 1.0), and perceived CNR (P = 0.84). There was no difference in motion (P = 0.57) nor Gibbs ringing (P = 0.86) artefacts. Phase ghosting (P = 0.038) and pseudolesions were significantly more frequent (P < 0.001) on DLR images.

CONCLUSION

DLR algorithm allowed faster FLAIR acquisition times with comparable image quality and lesion conspicuity. However, an increased incidence and severity of phase ghosting artefact and presence of pseudolesions using this technique may result in a reduction in reading speed, efficiency, and diagnostic confidence.

FlexDTI: flexible diffusion gradient encoding scheme-based highly efficient diffusion tensor imaging using deep learning

Objective. Most deep neural network-based diffusion tensor imaging methods require the diffusion gradients' number and directions in the data to be reconstructed to match those in the training data. This work aims to develop and evaluate a novel dynamic-convolution-based method called FlexDTI for highly efficient diffusion tensor reconstruction with flexible diffusion encoding gradient scheme.Approach. FlexDTI was developed to achieve high-quality DTI parametric mapping with flexible number and directions of diffusion encoding gradients. The method used dynamic convolution kernels to embed diffusion gradient direction information into feature maps of the corresponding diffusion signal. Furthermore, it realized the generalization of a flexible number of diffusion gradient directions by setting the maximum number of input channels of the network. The network was trained and tested using datasets from the Human Connectome Project and local hospitals. Results from FlexDTI and other advanced tensor parameter estimation methods were compared.Main results. Compared to other methods, FlexDTI successfully achieves high-quality diffusion tensor-derived parameters even if the number and directions of diffusion encoding gradients change. It reduces normalized root mean squared error by about 50% on fractional anisotropy and 15% on mean diffusivity, compared with the state-of-the-art deep learning method with flexible diffusion encoding gradient scheme.Significance. FlexDTI can well learn diffusion gradient direction information to achieve generalized DTI reconstruction with flexible diffusion gradient scheme. Both flexibility and reconstruction quality can be taken into account in this network.

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.

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.

Geometric deep learning for diffusion MRI signal reconstruction with continuous samplings (DISCUS)

Diffusion-weighted magnetic resonance imaging (dMRI) permits a detailed in-vivo analysis of neuroanatomical microstructure, invaluable for clinical and population studies. However, many measurements with different diffusion-encoding directions and possibly b-values are necessary to infer the underlying tissue microstructure within different imaging voxels accurately. Two challenges particularly limit the utility of dMRI: long acquisition times limit feasible scans to only a few directional measurements, and the heterogeneity of acquisition schemes across studies makes it difficult to combine datasets. Left unaddressed by previous learning-based methods that only accept dMRI data adhering to the specific acquisition scheme used for training, there is a need for methods that accept and predict signals for arbitrary diffusion encodings. Addressing these challenges, we describe the first geometric deep learning method for continuous dMRI signal reconstruction for arbitrary diffusion sampling schemes for both the input and output. Our method combines the reconstruction accuracy and robustness of previous learning-based methods with the flexibility of model-based methods, for example, spherical harmonics or SHORE. We demonstrate that our method outperforms model-based methods and performs on par with discrete learning-based methods on single-, multi-shell, and grid-based diffusion MRI datasets. Relevant for dMRI-derived analyses, we show that our reconstruction translates to higher-quality estimates of frequently used microstructure models compared to other reconstruction methods, enabling high-quality analyses even from very short dMRI acquisitions.

Ultrafast diffusion tensor imaging based on deep learning and multi-slice information sharing

Objective. Diffusion tensor imaging (DTI) is excellent for non-invasively quantifying tissue microstructure. Theoretically DTI can be achieved with six different diffusion weighted images and one reference image, but the tensor estimation accuracy is poor in this case. Increasing the number of diffusion directions has benefits for the tensor estimation accuracy, which results in long scan time and makes DTI sensitive to motion. It would be beneficial to decrease the scan time of DTI by using fewer diffusion-weighted images without compromising reconstruction quality.Approach. A novel DTI scan scheme was proposed to achieve fast DTI, where only three diffusion directions per slice was required under a specific direction switching manner, and a deep-learning based reconstruction method was utilized using multi-slice information sharing and correspondingT1-weighted image for high-quality DTI reconstruction. A network with two encoders developed from U-Net was implemented for better utilizing the diffusion data redundancy between neighboring slices. The method performed direct nonlinear mapping from diffusion-weighted images to diffusion tensor.Main results. The performance of the proposed method was verified on the Human Connectome Project public data and clinical patient data. High-quality mean diffusivity, fractional anisotropy, and directionally encoded colormap can be achieved with only three diffusion directions per slice.Significance. High-quality DTI-derived maps can be achieved in less than one minute of scan time. The great reduction of scan time will help push the wider application of DTI in clinical practice.

Learning ADC maps from accelerated radial k-space diffusion-weighted MRI in mice using a deep CNN-transformer model

PURPOSE

To accelerate radially sampled diffusion weighted spin-echo (Rad-DW-SE) acquisition method for generating high quality ADC maps.

METHODS

A deep learning method was developed to generate accurate ADC maps from accelerated DWI data acquired with the Rad-DW-SE method. The deep learning method integrates convolutional neural networks (CNNs) with vision transformers to generate high quality ADC maps from accelerated DWI data, regularized by a monoexponential ADC model fitting term. A model was trained on DWI data of 147 mice and evaluated on DWI data of 36 mice, with acceleration factors of 4× and 8× compared to the original acquisition parameters.

RESULTS

Ablation studies and experimental results have demonstrated that the proposed deep learning model generates higher quality ADC maps from accelerated DWI data than alternative deep learning methods under comparison when their performance is quantified in whole images as well as in regions of interest, including tumors, kidneys, and muscles.

CONCLUSIONS

The deep learning method with integrated CNNs and transformers provides an effective means to accurately compute ADC maps from accelerated DWI data acquired with the Rad-DW-SE method.

Super-resolved q-space learning of diffusion MRI

BACKGROUND

Diffusion magnetic resonance imaging (dMRI) provides a powerful tool to non-invasively investigate neural structures in the living human brain. Nevertheless, its reconstruction performance on neural structures relies on the number of diffusion gradients in the q-space. High-angular (HA) dMRI requires a long scan time, limiting its use in clinical practice, whereas directly reducing the number of diffusion gradients would lead to the underestimation of neural structures.

PURPOSE

We propose a deep compressive sensing-based q-space learning (DCS-qL) approach to estimate HA dMRI from low-angular dMRI.

METHODS

In DCS-qL, we design the deep network architecture by unfolding the proximal gradient descent procedure that addresses the compressive sense problem. In addition, we exploit a lifting scheme to design a network structure with reversible transform properties. For implementation, we apply a self-supervised regression to enhance the signal-to-noise ratio of diffusion data. Then, we utilize a semantic information-guided patch-based mapping strategy for feature extraction, which introduces multiple network branches to handle patches with different tissue labels.

RESULTS

Experimental results show that the proposed approach can yield a promising performance on the tasks of reconstructed HA dMRI images, microstructural indices of neurite orientation dispersion and density imaging, fiber orientation distribution, and fiber bundle estimation.

CONCLUSIONS

The proposed method achieves more accurate neural structures than competing approaches.

Enhancing head and neck tumor management with artificial intelligence: Integration and perspectives

Head and neck tumors (HNTs) constitute a multifaceted ensemble of pathologies that primarily involve regions such as the oral cavity, pharynx, and nasal cavity. The intricate anatomical structure of these regions poses considerable challenges to efficacious treatment strategies. Despite the availability of myriad treatment modalities, the overall therapeutic efficacy for HNTs continues to remain subdued. In recent years, the deployment of artificial intelligence (AI) in healthcare practices has garnered noteworthy attention. AI modalities, inclusive of machine learning (ML), neural networks (NNs), and deep learning (DL), when amalgamated into the holistic management of HNTs, promise to augment the precision, safety, and efficacy of treatment regimens. The integration of AI within HNT management is intricately intertwined with domains such as medical imaging, bioinformatics, and medical robotics. This article intends to scrutinize the cutting-edge advancements and prospective applications of AI in the realm of HNTs, elucidating AI's indispensable role in prevention, diagnosis, treatment, prognostication, research, and inter-sectoral integration. The overarching objective is to stimulate scholarly discourse and invigorate insights among medical practitioners and researchers to propel further exploration, thereby facilitating superior therapeutic alternatives for patients.

Towards Accurate Microstructure Estimation via 3D Hybrid Graph Transformer

Deep learning has drawn increasing attention in microstructure estimation with undersampled diffusion MRI (dMRI) data. A representative method is the hybrid graph transformer (HGT), which achieves promising performance by integrating q -space graph learning and x -space transformer learning into a unified framework. However, this method overlooks the 3D spatial information as it relies on training with 2D slices. To address this limitation, we propose 3D hybrid graph transformer (3D-HGT), an advanced microstructure estimation model capable of making full use of 3D spatial information and angular information. To tackle the large computation burden associated with 3D x -space learning, we propose an efficient q -space learning model based on simplified graph neural networks. Furthermore, we propose a 3D x -space learning module based on the transformer. Extensive experiments on data from the human connectome project show that our 3D-HGT outperforms state-of-the-art methods, including HGT, in both quantitative and qualitative evaluations.

Artificial Intelligence to Reduce or Eliminate the Need for Gadolinium-Based Contrast Agents in Brain and Cardiac MRI: A Literature Review

ABSTRACT

Brain and cardiac MRIs are fundamental noninvasive imaging tools, which can provide important clinical information and can be performed without or with gadolinium-based contrast agents (GBCAs), depending on the clinical indication. It is currently a topic of debate whether it would be feasible to extract information such as standard gadolinium-enhanced MRI while injecting either less or no GBCAs. Artificial intelligence (AI) is a great source of innovation in medical imaging and has been explored as a method to synthesize virtual contrast MR images, potentially yielding similar diagnostic performance without the need to administer GBCAs. If possible, there would be significant benefits, including reduction of costs, acquisition time, and environmental impact with respect to conventional contrast-enhanced MRI examinations. Given its promise, we believe additional research is needed to increase the evidence to make these AI solutions feasible, reliable, and robust enough to be integrated into the clinical framework. Here, we review recent AI studies aimed at reducing or replacing gadolinium in brain and cardiac imaging while maintaining diagnostic image quality.

Validation of deep learning techniques for quality augmentation in diffusion MRI for clinical studies

The objective of this study is to evaluate the efficacy of deep learning (DL) techniques in improving the quality of diffusion MRI (dMRI) data in clinical applications. The study aims to determine whether the use of artificial intelligence (AI) methods in medical images may result in the loss of critical clinical information and/or the appearance of false information. To assess this, the focus was on the angular resolution of dMRI and a clinical trial was conducted on migraine, specifically between episodic and chronic migraine patients. The number of gradient directions had an impact on white matter analysis results, with statistically significant differences between groups being drastically reduced when using 21 gradient directions instead of the original 61. Fourteen teams from different institutions were tasked to use DL to enhance three diffusion metrics (FA, AD and MD) calculated from data acquired with 21 gradient directions and a b-value of 1000 s/mm2. The goal was to produce results that were comparable to those calculated from 61 gradient directions. The results were evaluated using both standard image quality metrics and Tract-Based Spatial Statistics (TBSS) to compare episodic and chronic migraine patients. The study results suggest that while most DL techniques improved the ability to detect statistical differences between groups, they also led to an increase in false positive. The results showed that there was a constant growth rate of false positives linearly proportional to the new true positives, which highlights the risk of generalization of AI-based tasks when assessing diverse clinical cohorts and training using data from a single group. The methods also showed divergent performance when replicating the original distribution of the data and some exhibited significant bias. In conclusion, extreme caution should be exercised when using AI methods for harmonization or synthesis in clinical studies when processing heterogeneous data in clinical studies, as important information may be altered, even when global metrics such as structural similarity or peak signal-to-noise ratio appear to suggest otherwise.

Artificial intelligence for diffusion MRI-based tissue microstructure estimation in the human brain: an overview

Artificial intelligence (AI) has made significant advances in the field of diffusion magnetic resonance imaging (dMRI) and other neuroimaging modalities. These techniques have been applied to various areas such as image reconstruction, denoising, detecting and removing artifacts, segmentation, tissue microstructure modeling, brain connectivity analysis, and diagnosis support. State-of-the-art AI algorithms have the potential to leverage optimization techniques in dMRI to advance sensitivity and inference through biophysical models. While the use of AI in brain microstructures has the potential to revolutionize the way we study the brain and understand brain disorders, we need to be aware of the pitfalls and emerging best practices that can further advance this field. Additionally, since dMRI scans rely on sampling of the q-space geometry, it leaves room for creativity in data engineering in such a way that it maximizes the prior inference. Utilization of the inherent geometry has been shown to improve general inference quality and might be more reliable in identifying pathological differences. We acknowledge and classify AI-based approaches for dMRI using these unifying characteristics. This article also highlighted and reviewed general practices and pitfalls involving tissue microstructure estimation through data-driven techniques and provided directions for building on them.

Neural network algorithms predict new diffusion MRI data for multi-compartmental analysis of brain microstructure in a clinical setting

High angular resolution diffusion imaging (HARDI) is a promising method for advanced analysis of brain microstructure. However, comprehensive HARDI analysis requires multiple acquisitions of diffusion images (multi-shell HARDI), which is time consuming and often impractical in clinical settings. This study aimed to establish neural network models that can predict new diffusion datasets from clinically feasible brain diffusion MRI for multi-shell HARDI. The development included 2 algorithms: multi-layer perceptron (MLP) and convolutional neural network (CNN). Both followed a voxel-based approach for model training (70%), validation (15%), and testing (15%). The investigations involved 2 multi-shell HARDI datasets: 1) 11 healthy subjects from the Human Connectome Project (HCP); and 2) 10 local subjects with multiple sclerosis (MS). To assess outcomes, we conducted neurite orientation dispersion and density imaging using both predicted and original data and compared their orientation dispersion index (ODI) and neurite density index (NDI) in different brain tissues with 2 measures: peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). Results showed that both models achieved robust predictions, which provided competitive ODI and NDI, especially in brain white matter. The CNN outperformed MLP with the HCP data on both PSNR (p < 0.001) and SSIM (p < 0.01). With the MS data, the models performed similarly. Overall, the optimized neural networks can help generate non-acquired brain diffusion MRI, which will make advanced HARDI analysis possible in clinical practice following further validation. Enabling detailed characterization of brain microstructure will allow enhanced understanding of brain function in both health and disease.

Deep learning prediction of diffusion MRI data with microstructure-sensitive loss functions

Deep learning prediction of diffusion MRI (DMRI) data relies on the utilization of effective loss functions. Existing losses typically measure the signal-wise differences between the predicted and target DMRI data without considering the quality of derived diffusion scalars that are eventually utilized for quantification of tissue microstructure. Here, we propose two novel loss functions, called microstructural loss and spherical variance loss, to explicitly consider the quality of both the predicted DMRI data and derived diffusion scalars. We apply these loss functions to the prediction of multi-shell data and enhancement of angular resolution. Evaluation based on infant and adult DMRI data indicates that both microstructural loss and spherical variance loss improve the quality of derived diffusion scalars.

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.

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.

Deep Learning for Image Enhancement and Correction in Magnetic Resonance Imaging-State-of-the-Art and Challenges

Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast for clinical diagnoses and research which underpin many recent breakthroughs in medicine and biology. The post-processing of reconstructed MR images is often automated for incorporation into MRI scanners by the manufacturers and increasingly plays a critical role in the final image quality for clinical reporting and interpretation. For image enhancement and correction, the post-processing steps include noise reduction, image artefact correction, and image resolution improvements. With the recent success of deep learning in many research fields, there is great potential to apply deep learning for MR image enhancement, and recent publications have demonstrated promising results. Motivated by the rapidly growing literature in this area, in this review paper, we provide a comprehensive overview of deep learning-based methods for post-processing MR images to enhance image quality and correct image artefacts. We aim to provide researchers in MRI or other research fields, including computer vision and image processing, a literature survey of deep learning approaches for MR image enhancement. We discuss the current limitations of the application of artificial intelligence in MRI and highlight possible directions for future developments. In the era of deep learning, we highlight the importance of a critical appraisal of the explanatory information provided and the generalizability of deep learning algorithms in medical imaging.

Resting state network mapping in individuals using deep learning

Introduction

Resting state functional MRI (RS-fMRI) is currently used in numerous clinical and research settings. The localization of resting state networks (RSNs) has been utilized in applications ranging from group analysis of neurodegenerative diseases to individual network mapping for pre-surgical planning of tumor resections. Reproducibility of these results has been shown to require a substantial amount of high-quality data, which is not often available in clinical or research settings.

Methods

In this work, we report voxelwise mapping of a standard set of RSNs using a novel deep 3D convolutional neural network (3DCNN). The 3DCNN was trained on publicly available functional MRI data acquired in n = 2010 healthy participants. After training, maps that represent the probability of a voxel belonging to a particular RSN were generated for each participant, and then used to calculate mean and standard deviation (STD) probability maps, which are made publicly available. Further, we compared our results to previously published resting state and task-based functional mappings.

Results

Our results indicate this method can be applied in individual subjects and is highly resistant to both noisy data and fewer RS-fMRI time points than are typically acquired. Further, our results show core regions within each network that exhibit high average probability and low STD.

Discussion

The 3DCNN algorithm can generate individual RSN localization maps, which are necessary for clinical applications. The similarity between 3DCNN mapping results and task-based fMRI responses supports the association of specific functional tasks with RSNs.

Accelerated cardiac diffusion tensor imaging using deep neural network

Cardiac diffusion tensor imaging (DTI) is a noninvasive method for measuring the microstructure of the myocardium. However, its long scan time significantly hinders its wide application. In this study, we developed a deep learning framework to obtain high-quality DTI parameter maps from six diffusion-weighted images (DWIs) by combining deep-learning-based image generation and tensor fitting, and named the new framework FG-Net. In contrast to frameworks explored in previous deep-learning-based fast DTI studies, FG-Net generates inter-directional DWIs from six input DWIs to supplement the loss information and improve estimation accuracy for DTI parameters. FG-Net was evaluated using two datasets ofex vivohuman hearts. The results showed that FG-Net can generate fractional anisotropy, mean diffusivity maps, and helix angle maps from only six raw DWIs, with a quantification error of less than 5%. FG-Net outperformed conventional tensor fitting and black-box network fitting in both qualitative and quantitative metrics. We also demonstrated that the proposed FG-Net can achieve highly accurate fractional anisotropy and helix angle maps in DWIs with differentb-values.

SuperMAP: Deep ultrafast MR relaxometry with joint spatiotemporal undersampling

PURPOSE

To develop an ultrafast and robust MR parameter mapping network using deep learning.

THEORY AND METHODS

We design a deep learning framework called SuperMAP that directly converts a series of undersampled (both in k-space and parameter-space) parameter-weighted images into several quantitative maps, bypassing the conventional exponential fitting procedure. We also present a novel technique to simultaneously reconstruct T1rho and T2 relaxation maps within a single scan. Full data were acquired and retrospectively undersampled for training and testing using traditional and state-of-the-art techniques for comparison. Prospective data were also collected to evaluate the trained network. The performance of all methods is evaluated using the parameter qualification errors and other metrics in the segmented regions of interest.

RESULTS

SuperMAP achieved accurate T1rho and T2 mapping with high acceleration factors (R = 24 and R = 32). It exploited both spatial and temporal information and yielded low error (normalized mean square error of 2.7% at R = 24 and 2.8% at R = 32) and high resemblance (structural similarity of 97% at R = 24 and 96% at R = 32) to the gold standard. The network trained with retrospectively undersampled data also works well for the prospective data (with a slightly lower acceleration factor). SuperMAP is also superior to conventional methods.

CONCLUSION

Our results demonstrate the feasibility of generating superfast MR parameter maps through very few undersampled parameter-weighted images. SuperMAP can simultaneously generate T1rho and T2 relaxation maps in a short scan time.

Accelerating Cardiac Diffusion Tensor Imaging With a U-Net Based Model: Toward Single Breath-Hold

BACKGROUND

In vivo cardiac diffusion tensor imaging (cDTI) characterizes myocardial microstructure. Despite its potential clinical impact, considerable technical challenges exist due to the inherent low signal-to-noise ratio.

PURPOSE

To reduce scan time toward one breath-hold by reconstructing diffusion tensors for in vivo cDTI with a fitting-free deep learning approach.

STUDY TYPE

Retrospective.

POPULATION

A total of 197 healthy controls, 547 cardiac patients.

FIELD STRENGTH/SEQUENCE

A 3 T, diffusion-weighted stimulated echo acquisition mode single-shot echo-planar imaging sequence.

ASSESSMENT

A U-Net was trained to reconstruct the diffusion tensor elements of the reference results from reduced datasets that could be acquired in 5, 3 or 1 breath-hold(s) (BH) per slice. Fractional anisotropy (FA), mean diffusivity (MD), helix angle (HA), and sheetlet angle (E2A) were calculated and compared to the same measures when using a conventional linear-least-square (LLS) tensor fit with the same reduced datasets. A conventional LLS tensor fit with all available data (12 ± 2.0 [mean ± sd] breath-holds) was used as the reference baseline.

STATISTICAL TESTS

Wilcoxon signed rank/rank sum and Kruskal-Wallis tests. Statistical significance threshold was set at P = 0.05. Intersubject measures are quoted as median [interquartile range].

RESULTS

For global mean or median results, both the LLS and U-Net methods with reduced datasets present a bias for some of the results. For both LLS and U-Net, there is a small but significant difference from the reference results except for LLS: MD 5BH (P = 0.38) and MD 3BH (P = 0.09). When considering direct pixel-wise errors the U-Net model outperformed significantly the LLS tensor fit for reduced datasets that can be acquired in three or just one breath-hold for all parameters.

DATA CONCLUSION

Diffusion tensor prediction with a trained U-Net is a promising approach to minimize the number of breath-holds needed in clinical cDTI studies.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 1.

Bundle geodesic convolutional neural network for diffusion-weighted imaging segmentation

Purpose

Applying machine learning techniques to magnetic resonance diffusion-weighted imaging (DWI) data is challenging due to the size of individual data samples and the lack of labeled data. It is possible, though, to learn general patterns from a very limited amount of training data if we take advantage of the geometry of the DWI data. Therefore, we present a tissue classifier based on a Riemannian deep learning framework for single-shell DWI data.

Approach

The framework consists of three layers: a lifting layer that locally represents and convolves data on tangent spaces to produce a family of functions defined on the rotation groups of the tangent spaces, i.e., a (not necessarily continuous) function on a bundle of rotational functions on the manifold; a group convolution layer that convolves this function with rotation kernels to produce a family of local functions over each of the rotation groups; a projection layer using maximization to collapse this local data to form manifold based functions.

Results

Experiments show that our method achieves the performance of the same level as state-of-the-art while using way fewer parameters in the model ( < 10 % ). Meanwhile, we conducted a model sensitivity analysis for our method. We ran experiments using a proportion (69.2%, 53.3%, and 29.4%) of the original training set and analyzed how much data the model needs for the task. Results show that this does reduce the overall classification accuracy mildly, but it also boosts the accuracy for minority classes.

Conclusions

This work extended convolutional neural networks to Riemannian manifolds, and it shows the potential in understanding structural patterns in the brain, as well as in aiding manual data annotation.

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.

Hybrid Graph Transformer for Tissue Microstructure Estimation with Undersampled Diffusion MRI Data

Advanced contemporary diffusion models for tissue microstructure often require diffusion MRI (DMRI) data with sufficiently dense sampling in the diffusion wavevector space for reliable model fitting, which might not always be feasible in practice. A potential remedy to this problem is by using deep learning techniques to predict high-quality diffusion microstructural indices from sparsely sampled data. However, existing methods are either agnostic to the data geometry in the diffusion wavevector space ( q -space) or limited to leveraging information from only local neighborhoods in the physical coordinate space ( x -space). Here, we propose a hybrid graph transformer (HGT) to explicitly consider the q -space geometric structure with a graph neural network (GNN) and make full use of spatial information with a novel residual dense transformer (RDT). The RDT consists of multiple densely connected transformer layers and a residual connection to facilitate model training. Extensive experiments on the data from the Human Connectome Project (HCP) demonstrate that our method significantly improves the quality of microstructural estimations over existing state-of-the-art methods.

qMRI-BIDS: An extension to the brain imaging data structure for quantitative magnetic resonance imaging data

The Brain Imaging Data Structure (BIDS) established community consensus on the organization of data and metadata for several neuroimaging modalities. Traditionally, BIDS had a strong focus on functional magnetic resonance imaging (MRI) datasets and lacked guidance on how to store multimodal structural MRI datasets. Here, we present and describe the BIDS Extension Proposal 001 (BEP001), which adds a range of quantitative MRI (qMRI) applications to the BIDS. In general, the aim of qMRI is to characterize brain microstructure by quantifying the physical MR parameters of the tissue via computational, biophysical models. By proposing this new standard, we envision standardization of qMRI through multicenter dissemination of interoperable datasets. This way, BIDS can act as a catalyst of convergence between qMRI methods development and application-driven neuroimaging studies that can help develop quantitative biomarkers for neural tissue characterization. In conclusion, this BIDS extension offers a common ground for developers to exchange novel imaging data and tools, reducing the entrance barrier for qMRI in the field of neuroimaging.

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.

A generalized deep learning network for fractional anisotropy reconstruction: Application to epilepsy and multiple sclerosis

Fractional anisotropy (FA) is a quantitative map sensitive to microstructural properties of tissues in vivo and it is extensively used to study the healthy and pathological brain. This map is classically calculated by model fitting (standard method) and requires many diffusion weighted (DW) images for data quality and unbiased readings, hence needing the acquisition time of several minutes. Here, we adapted the U-net architecture to be generalized and to obtain good quality FA from DW volumes acquired in 1 minute. Our network requires 10 input DW volumes (hence fast acquisition), is robust to the direction of application of the diffusion gradients (hence generalized), and preserves/improves map quality (hence good quality maps). We trained the network on the human connectome project (HCP) data using the standard model-fitting method on the entire set of DW directions to extract FA (ground truth). We addressed the generalization problem, i.e., we trained the network to be applicable, without retraining, to clinical datasets acquired on different scanners with different DW imaging protocols. The network was applied to two different clinical datasets to assess FA quality and sensitivity to pathology in temporal lobe epilepsy and multiple sclerosis, respectively. For HCP data, when compared to the ground truth FA, the FA obtained from 10 DW volumes using the network was significantly better (p <10-4) than the FA obtained using the standard pipeline. For the clinical datasets, the network FA retained the same microstructural characteristics as the FA calculated with all DW volumes using the standard method. At the subject level, the comparison between white matter (WM) ground truth FA values and network FA showed the same distribution; at the group level, statistical differences of WM values detected in the clinical datasets with the ground truth FA were reproduced when using values from the network FA, i.e., the network retained sensitivity to pathology. In conclusion, the proposed network provides a clinically available method to obtain FA from a generic set of 10 DW volumes acquirable in 1 minute, augmenting data quality compared to direct model fitting, reducing the possibility of bias from sub-sampled data, and retaining FA pathological sensitivity, which is very attractive for clinical applications.

Artificial intelligence and spine imaging: limitations, regulatory issues and future direction

BACKGROUND

As big data and artificial intelligence (AI) in spine care, and medicine as a whole, continue to be at the forefront of research, careful consideration to the quality and techniques utilized is necessary. Predictive modeling, data science, and deep analytics have taken center stage. Within that space, AI and machine learning (ML) approaches toward the use of spine imaging have gathered considerable attention in the past decade. Although several benefits of such applications exist, limitations are also present and need to be considered.

PURPOSE

The following narrative review presents the current status of AI, in particular, ML, with special regard to imaging studies, in the field of spinal research.

METHODS

A multi-database assessment of the literature was conducted up to September 1, 2021, that addressed AI as it related to imaging of the spine. Articles written in English were selected and critically assessed.

RESULTS

Overall, the review discussed the limitations, data quality and applications of ML models in the context of spine imaging. In particular, we addressed the data quality and ML algorithms in spine imaging research by describing preliminary results from a widely accessible imaging algorithm that is currently available for spine specialists to reference for information on severity of spine disease and degeneration which ultimately may alter clinical decision-making. In addition, awareness of the current, under-recognized regulation surrounding the execution of ML for spine imaging was raised.

CONCLUSIONS

Recommendations were provided for conducting high-quality, standardized AI applications for spine imaging.

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.

Differentiating False Positive Lesions from Clinically Significant Cancer and Normal Prostate Tissue Using VERDICT MRI and Other Diffusion Models

False positives on multiparametric MRIs (mp-MRIs) result in many unnecessary invasive biopsies in men with clinically insignificant diseases. This study investigated whether quantitative diffusion MRI could differentiate between false positives, true positives and normal tissue non-invasively. Thirty-eight patients underwent mp-MRI and Vascular, Extracellular and Restricted Diffusion for Cytometry in Tumors (VERDICT) MRI, followed by transperineal biopsy. The patients were categorized into two groups following biopsy: (1) significant cancer—true positive, 19 patients; (2) atrophy/inflammation/high-grade prostatic intraepithelial neoplasia (PIN)—false positive, 19 patients. The clinical apparent diffusion coefficient (ADC) values were obtained, and the intravoxel incoherent motion (IVIM), diffusion kurtosis imaging (DKI) and VERDICT models were fitted via deep learning. Significant differences (p < 0.05) between true positive and false positive lesions were found in ADC, IVIM perfusion fraction (f) and diffusivity (D), DKI diffusivity (DK) (p < 0.0001) and kurtosis (K) and VERDICT intracellular volume fraction (fIC), extracellular−extravascular volume fraction (fEES) and diffusivity (dEES) values. Significant differences between false positives and normal tissue were found for the VERDICT fIC (p = 0.004) and IVIM D. These results demonstrate that model-based diffusion MRI could reduce unnecessary biopsies occurring due to false positive prostate lesions and shows promising sensitivity to benign diseases.

Data harmonisation for information fusion in digital healthcare: A state-of-the-art systematic review, meta-analysis and future research directions

Removing the bias and variance of multicentre data has always been a challenge in large scale digital healthcare studies, which requires the ability to integrate clinical features extracted from data acquired by different scanners and protocols to improve stability and robustness. Previous studies have described various computational approaches to fuse single modality multicentre datasets. However, these surveys rarely focused on evaluation metrics and lacked a checklist for computational data harmonisation studies. In this systematic review, we summarise the computational data harmonisation approaches for multi-modality data in the digital healthcare field, including harmonisation strategies and evaluation metrics based on different theories. In addition, a comprehensive checklist that summarises common practices for data harmonisation studies is proposed to guide researchers to report their research findings more effectively. Last but not least, flowcharts presenting possible ways for methodology and metric selection are proposed and the limitations of different methods have been surveyed for future research.

Role of artificial intelligence in MS clinical practice

Machine learning (ML) and its subset, deep learning (DL), are branches of artificial intelligence (AI) showing promising findings in the medical field, especially when applied to imaging data. Given the substantial role of MRI in the diagnosis and management of patients with multiple sclerosis (MS), this disease is an ideal candidate for the application of AI techniques. In this narrative review, we are going to discuss the potential applications of AI for MS clinical practice, together with their limitations. Among their several advantages, ML algorithms are able to automate repetitive tasks, to analyze more data in less time and to achieve higher accuracy and reproducibility than the human counterpart. To date, these algorithms have been applied to MS diagnosis, prognosis, disease and treatment monitoring. Other fields of application have been improvement of MRI protocols as well as automated lesion and tissue segmentation. However, several challenges remain, including a better understanding of the information selected by AI algorithms, appropriate multicenter and longitudinal validations of results and practical aspects regarding hardware and software integration. Finally, one cannot overemphasize the paramount importance of human supervision, in order to optimize the use and take full advantage of the potential of AI approaches.