DeepDTI: High-fidelity six-direction diffusion tensor imaging using deep learning

Cycle-conditional diffusion model for noise correction of diffusion-weighted images using unpaired data

Diffusion-weighted imaging (DWI) is a key modality for studying brain microstructure, but its signals are highly susceptible to noise due to the thermal motion of water molecules and interactions with tissue microarchitecture, leading to significant signal attenuation and a low signal-to-noise ratio (SNR). In this paper, we propose a novel approach, a Cycle-Conditional Diffusion Model (Cycle-CDM) using unpaired data learning, aimed at improving DWI quality and reliability through noise correction. Cycle-CDM leverages a cycle-consistent translation architecture to bridge the domain gap between noise-contaminated and noise-free DWIs, enabling the restoration of high-quality images without requiring paired datasets. By utilizing two conditional diffusion models, Cycle-CDM establishes data interrelationships between the two types of DWIs, while incorporating synthesized anatomical priors from the cycle translation process to guide noise removal. In addition, we introduce specific constraints to preserve anatomical fidelity, allowing Cycle-CDM to effectively learn the underlying noise distribution and achieve accurate denoising. Our experiments conducted on simulated datasets, as well as children and adolescents' datasets with strong clinical relevance. Our results demonstrate that Cycle-CDM outperforms comparative methods, such as U-Net, CycleGAN, Pix2Pix, MUNIT and MPPCA, in terms of noise correction performance. We demonstrated that Cycle-CDM can be generalized to DWIs with head motion when they were acquired using different MRI scannsers. Importantly, the denoised DWI data produced by Cycle-CDM exhibit accurate preservation of underlying tissue microstructure, thus substantially improving their medical applicability.

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.

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.

Super-resolution mapping of anisotropic tissue structure with diffusion MRI and deep learning

Diffusion magnetic resonance imaging (diffusion MRI) is widely employed to probe the diffusive motion of water molecules within the tissue. Numerous diseases and processes affecting the central nervous system can be detected and monitored via diffusion MRI thanks to its sensitivity to microstructural alterations in tissue. The latter has prompted interest in quantitative mapping of the microstructural parameters, such as the fiber orientation distribution function (fODF), which is instrumental for noninvasively mapping the underlying axonal fiber tracts in white matter through a procedure known as tractography. However, such applications demand repeated acquisitions of MRI volumes with varied experimental parameters demanding long acquisition times and/or limited spatial resolution. In this work, we present a deep-learning-based approach for increasing the spatial resolution of diffusion MRI data in the form of fODFs obtained through constrained spherical deconvolution. The proposed approach is evaluated on high quality data from the Human Connectome Project, and is shown to generate upsampled results with a greater correspondence to ground truth high-resolution data than can be achieved with ordinary spline interpolation methods. Furthermore, we employ a measure based on the earth mover's distance to assess the accuracy of the upsampled fODFs. At low signal-to-noise ratios, our super-resolution method provides more accurate estimates of the fODF compared to data collected with 8 times smaller voxel volume.

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.

Spherical Harmonics-Based Deep Learning Achieves Generalized and Accurate Diffusion Tensor Imaging

Diffusion tensor imaging (DTI) is a prevalent magnetic resonance imaging (MRI) technique, widely used in clinical and neuroscience research. However, the reliability of DTI is affected by the low signal-to-noise ratio inherent in diffusion-weighted (DW) images. Deep learning (DL) has shown promise in improving the quality of DTI, but its limited generalization to variable acquisition schemes hinders practical applications. This study aims to develop a generalized, accurate, and efficient DL-based DTI method. By leveraging the representation of voxel-wise diffusion MRI (dMRI) signals on the sphere using spherical harmonics (SH), we propose a novel approach that utilizes SH coefficient maps as input to a network for predicting the diffusion tensor (DT) field, enabling improved generalization. Extensive experiments were conducted on simulated and in-vivo datasets, covering various DTI application scenarios. The results demonstrate that the proposed SH-DTI method achieves advanced performance in both quantitative and qualitative analyses of DTI. Moreover, it exhibits remarkable generalization capabilities across different acquisition schemes, centers, and scanners, ensuring its broad applicability in diverse settings.

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.

Accelerated multi-b-value multi-shot diffusion-weighted imaging based on EPI with keyhole and a low-rank tensor constraint

PURPOSE

Multi-Shot (MS) Echo-Planar Imaging (EPI) may improve the in-plane resolution of multi-b-value DWI, yet it also considerably increases the scan time. Here we explored the combination of EPI with Keyhole (EPIK) and a calibrationless reconstruction algorithm for acceleration of multi-b-value MS-DWI.

METHODS

We firstly analyzed the impact of nonuniform phase accrual in EPIK on the reconstructed image. Based on insights gained from the analysis, we developed a calibrationless reconstruction algorithm based on a Space-Contrast-Coil Locally Low-Rank Tensor (SCC-LLRT) constraint for reconstruction of EPIK-acquired data. We compared the algorithm with a modified SPatial-Angular Locally Low-Rank (SPA-LLR) algorithm through simulations, phantoms, and in vivo study. We then compared EPIK with uniformly undersampled EPI for accelerating multi-b-value DWI in 6 healthy subjects.

RESULTS

Through theoretical derivations, we found that the reconstruction of EPIK with a SENSE-encoding-based algorithm, such as SPA-LLR, may cause additional aliasing artifacts due to the frequency-dependent distortion of the coil sensitivity. Results from simulations, phantoms, and in vivo study verified the theoretical finding by showing that the calibrationless SCC-LLRT algorithm reduced aliasing artifacts compared with SPA-LLR. Finally, EPIK with SCC-LLRT substantially reduced the ghosting artifacts compared with uniform undersampled multi-b-value DWI, decreasing the fitting errors in ADC (0.05 ± 0.01 vs 0.10 ± 0.01, P < 0.001) and IVIM mapping (0.026 ± 0.004 vs 0.06 ± 0.006, P < 0.001).

CONCLUSION

The SCC-LLRT algorithm reduced the aliasing artifacts of EPIK by using a calibrationless modeling of the multi-coil data. The dense sampling of k-space center offers EPIK a potential to improve image quality for acceleration of multi-b-value MS-DWI.

Improving quantitative MRI using self-supervised deep learning with model reinforcement: Demonstration for rapid T1 mapping

PURPOSE

This paper proposes a novel self-supervised learning framework that uses model reinforcement, REference-free LAtent map eXtraction with MOdel REinforcement (RELAX-MORE), for accelerated quantitative MRI (qMRI) reconstruction. The proposed method uses an optimization algorithm to unroll an iterative model-based qMRI reconstruction into a deep learning framework, enabling accelerated MR parameter maps that are highly accurate and robust.

METHODS

Unlike conventional deep learning methods which require large amounts of training data, RELAX-MORE is a subject-specific method that can be trained on single-subject data through self-supervised learning, making it accessible and practically applicable to many qMRI studies. Using quantitativeT 1 $$ {\mathrm{T}}_1 $$ mapping as an example, the proposed method was applied to the brain, knee and phantom data.

RESULTS

The proposed method generates high-quality MR parameter maps that correct for image artifacts, removes noise, and recovers image features in regions of imperfect image conditions. Compared with other state-of-the-art conventional and deep learning methods, RELAX-MORE significantly improves efficiency, accuracy, robustness, and generalizability for rapid MR parameter mapping.

CONCLUSION

This work demonstrates the feasibility of a new self-supervised learning method for rapid MR parameter mapping, that is readily adaptable to the clinical translation of qMRI.

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.

DTKGIN: Predicting drug-target interactions based on knowledge graph and intent graph

Knowledge graph intent graph attention mechanism Predicting drug-target interactions (DTIs) plays a crucial role in drug discovery and drug development. Considering the high cost and risk of biological experiments, developing computational approaches to explore the interactions between drugs and targets can effectively reduce the time and cost of drug development. Recently, many methods have made significant progress in predicting DTIs. However, existing approaches still suffer from the high sparsity of DTI datasets and the cold start problem. In this paper, we develop a new model to predict drug-target interactions via a knowledge graph and intent graph named DTKGIN. Our method can effectively capture biological environment information for targets and drugs by mining their associated relations in the knowledge graph and considering drug-target interactions at a fine-grained level in the intent graph. DTKGIN learns the representation of drugs and targets from the knowledge graph and the intent graph. Then the probabilities of interactions between drugs and targets are obtained through the inner product of the representation of drugs and targets. Experimental results show that our proposed method outperforms other state-of-the-art methods in 10-fold cross-validation, especially in cold-start experimental settings. Furthermore, the case studies demonstrate the effectiveness of DTKGIN in predicting potential drug-target interactions. The code is available on GitHub: https://github.com/Royluoyi123/DTKGIN.

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.

Impact of Deep Learning Denoising Algorithm on Diffusion Tensor Imaging of the Growth Plate on Different Spatial Resolutions

To assess the impact of a deep learning (DL) denoising reconstruction algorithm applied to identical patient scans acquired with two different voxel dimensions, representing distinct spatial resolutions, this IRB-approved prospective study was conducted at a tertiary pediatric center in compliance with the Health Insurance Portability and Accountability Act. A General Electric Signa Premier unit (GE Medical Systems, Milwaukee, WI) was employed to acquire two DTI (diffusion tensor imaging) sequences of the left knee on each child at 3T: an in-plane 2.0 × 2.0 mm2 with section thickness of 3.0 mm and a 2 mm3 isovolumetric voxel; neither had an intersection gap. For image acquisition, a multi-band DTI with a fat-suppressed single-shot spin-echo echo-planar sequence (20 non-collinear directions; b-values of 0 and 600 s/mm2) was utilized. The MR vendor-provided a commercially available DL model which was applied with 75% noise reduction settings to the same subject DTI sequences at different spatial resolutions. We compared DTI tract metrics from both DL-reconstructed scans and non-denoised scans for the femur and tibia at each spatial resolution. Differences were evaluated using Wilcoxon-signed ranked test and Bland-Altman plots. When comparing DL versus non-denoised diffusion metrics in femur and tibia using the 2 mm × 2 mm × 3 mm voxel dimension, there were no significant differences between tract count (p = 0.1, p = 0.14) tract volume (p = 0.1, p = 0.29) or tibial tract length (p = 0.16); femur tract length exhibited a significant difference (p < 0.01). All diffusion metrics (tract count, volume, length, and fractional anisotropy (FA)) derived from the DL-reconstructed scans, were significantly different from the non-denoised scan DTI metrics in both the femur and tibial physes using the 2 mm3 voxel size (p < 0.001). DL reconstruction resulted in a significant decrease in femorotibial FA for both voxel dimensions (p < 0.01). Leveraging denoising algorithms could address the drawbacks of lower signal-to-noise ratios (SNRs) associated with smaller voxel volumes and capitalize on their better spatial resolutions, allowing for more accurate quantification of diffusion metrics.

Deep learning-based diffusion tensor cardiac magnetic resonance reconstruction: a comparison study

In vivo cardiac diffusion tensor imaging (cDTI) is a promising Magnetic Resonance Imaging (MRI) technique for evaluating the microstructure of myocardial tissue in living hearts, providing insights into cardiac function and enabling the development of innovative therapeutic strategies. However, the integration of cDTI into routine clinical practice poses challenging due to the technical obstacles involved in the acquisition, such as low signal-to-noise ratio and prolonged scanning times. In this study, we investigated and implemented three different types of deep learning-based MRI reconstruction models for cDTI reconstruction. We evaluated the performance of these models based on the reconstruction quality assessment, the diffusion tensor parameter assessment as well as the computational cost assessment. Our results indicate that the models discussed in this study can be applied for clinical use at an acceleration factor (AF) of × 2 and × 4 , with the D5C5 model showing superior fidelity for reconstruction and the SwinMR model providing higher perceptual scores. There is no statistical difference from the reference for all diffusion tensor parameters at AF × 2 or most DT parameters at AF × 4 , and the quality of most diffusion tensor parameter maps is visually acceptable. SwinMR is recommended as the optimal approach for reconstruction at AF × 2 and AF × 4 . However, we believe that the models discussed in this study are not yet ready for clinical use at a higher AF. At AF × 8 , the performance of all models discussed remains limited, with only half of the diffusion tensor parameters being recovered to a level with no statistical difference from the reference. Some diffusion tensor parameter maps even provide wrong and misleading information.

High-angular resolution diffusion imaging generation using 3d u-net

PURPOSE

To investigate the effects on tractography of artificial intelligence-based prediction of motion-probing gradients (MPGs) in diffusion-weighted imaging (DWI).

METHODS

The 251 participants in this study were patients with brain tumors or epileptic seizures who underwent MRI to depict tractography. DWI was performed with 64 MPG directions and b = 0 s/mm2 images. The dataset was divided into a training set of 191 (mean age 45.7 [± 19.1] years), a validation set of 30 (mean age 41.6 [± 19.1] years), and a test set of 30 (mean age 49.6 [± 18.3] years) patients. Supervised training of a convolutional neural network was performed using b = 0 images and the first 32 axes of MPG images as the input data and the second 32 axes as the reference data. The trained model was applied to the test data, and tractography was performed using (a) input data only; (b) input plus prediction data; and (c) b = 0 images and the 64 MPG data (as a reference).

RESULTS

In Q-ball imaging tractography, the average dice similarity coefficient (DSC) of the input plus prediction data was 0.715 (± 0.064), which was significantly higher than that of the input data alone (0.697 [± 0.070]) (p < 0.05). In generalized q-sampling imaging tractography, the average DSC of the input plus prediction data was 0.769 (± 0.091), which was also significantly higher than that of the input data alone (0.738 [± 0.118]) (p < 0.01).

CONCLUSION

Diffusion tractography is improved by adding predicted MPG images generated by an artificial intelligence model.

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.

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.

Self-supervised structural similarity-based convolutional neural network for cardiac diffusion tensor image denoising

BACKGROUND

Diffusion tensor imaging (DTI) is a promising technique for non-invasively investigating the myocardial fiber structures of human heart. However, low signal-to-noise ratio (SNR) has been a major limit of cardiac DTI to prevent us from detecting myocardium structure accurately. Therefore, it is important to remove the effect of noise on diffusion weighted (DW) images.

PURPOSE

Although the conventional and deep learning-based denoising methods have shown the potential to deal with effectively the noise in DW images, most of them are redundant information dependent or require the noise-free images as golden standard. In addition, the existed DW image denoising methods often suffer from problems of over-smoothing. To address these issues, we propose a self-supervised learning model, structural similarity based convolutional neural network with edge-weighted loss (SSECNN), to remove the noise effectively in cardiac DTI.

METHODS

Considering that the DW images acquired along different diffusion directions have structural similarity, and the noise in these DW images is independent and identically distributed, the structural similarity-based matching algorithm is proposed to search for the most similar DW images. Such similar noisy DW image pairs are then used as the input and target of the denoising network SSECNN, which consists of several convolutional and residual blocks. Through the self-supervised training with these image pairs, the network can restore the clean DW images and retain the correlations between the denoised DW images along different directions. To avoid the over-smoothing problem, we design a novel edge-weighted loss which enables the network to adaptively adjust the loss weights with iterations and therefore to improve the detail preserve ability of the model. To verify the superiority of the proposed method, comparisons with state-of-the-art (SOTA) denoising methods are performed on both synthetic and real acquired DTI datasets.

RESULTS

Experimental results show that SSECNN can effectively reduce the noise in the DW images while preserving detailed texture and edge information and therefore achieve better performance in DTI reconstruction. For synthetic dataset, compared to the SOTA method, the root mean square error (RMSE), peak signal-to-noise ratio (PSNR), and structure similarity index measure (SSIM) between the denoised DW images obtained with SSECNN and noise-free DW images are improved by 6.94%, 1.98%, and 0.76% respectively when the noise level is 10%. As for the acquired cardiac DTI dataset, the SSECNN method could significantly improve SNR and contrast to noise ratio (CNR) of cardiac DW images and achieve more regular helix angle (HA) and transverse angle (TA) maps. The ablation experimental results validate that using the structure similarity-based method to search the similar DW image pairs yield the smallest loss, and with the help of the edge-weighted loss, the denoised DW images and diffusion metric maps can preserve more details.

CONCLUSIONS

The proposed SSECNN method can fully explore the similarity between the DW images along different diffusion directions. Using such similarity and an edge-weighted loss enable us to denoise cardiac DTI effectively in a self-supervised manner. Our method can overcome the redundancy information dependence and over-smoothing problem of the SOTA methods.

High angular diffusion tensor imaging estimation from minimal evenly distributed diffusion gradient directions

Diffusion-weighted Imaging (DWI) is a non-invasive imaging technique based on Magnetic Resonance Imaging (MRI) principles to measure water diffusivity and reveal details of the underlying brain micro-structure. By fitting a tensor model to quantify the directionality of water diffusion a Diffusion Tensor Image (DTI) can be derived and scalar measures, such as fractional anisotropy (FA), can then be estimated from the DTI to summarise quantitative microstructural information for clinical studies. In particular, FA has been shown to be a useful research metric to identify tissue abnormalities in neurological disease (e.g. decreased anisotropy as a proxy for tissue damage). However, time constraints in clinical practice lead to low angular resolution diffusion imaging (LARDI) acquisitions that can cause inaccurate FA value estimates when compared to those generated from high angular resolution diffusion imaging (HARDI) acquisitions. In this work, we propose High Angular DTI Estimation Network (HADTI-Net) to estimate an enhanced DTI model from LARDI with a set of minimal and evenly distributed diffusion gradient directions. Extensive experiments have been conducted to show the reliability and generalisation of HADTI-Net to generate high angular DTI estimation from any minimal evenly distributed diffusion gradient directions and to explore the feasibility of applying a data-driven method for this task. The code repository of this work and other related works can be found at https://mri-synthesis.github.io/.

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.

High-fidelity mesoscale in-vivo diffusion MRI through gSlider-BUDA and circular EPI with S-LORAKS reconstruction

PURPOSE

To develop a high-fidelity diffusion MRI acquisition and reconstruction framework with reduced echo-train-length for less T2* image blurring compared to typical highly accelerated echo-planar imaging (EPI) acquisitions at sub-millimeter isotropic resolution.

METHODS

We first proposed a circular-EPI trajectory with partial Fourier sampling on both the readout and phase-encoding directions to minimize the echo-train-length and echo time. We then utilized this trajectory in an interleaved two-shot EPI acquisition with reversed phase-encoding polarity, to aid in the correction of off-resonance-induced image distortions and provide complementary k-space coverage in the missing partial Fourier regions. Using model-based reconstruction with structured low-rank constraint and smooth phase prior, we corrected the shot-to-shot phase variations across the two shots and recover the missing k-space data. Finally, we combined the proposed acquisition/reconstruction framework with an SNR-efficient RF-encoded simultaneous multi-slab technique, termed gSlider, to achieve high-fidelity 720 µm and 500 µm isotropic resolution in-vivo diffusion MRI.

RESULTS

Both simulation and in-vivo results demonstrate the effectiveness of the proposed acquisition and reconstruction framework to provide distortion-corrected diffusion imaging at the mesoscale with markedly reduced T2*-blurring. The in-vivo results of 720 µm and 500 µm datasets show high-fidelity diffusion images with reduced image blurring and echo time using the proposed approaches.

CONCLUSIONS

The proposed method provides high-quality distortion-corrected diffusion-weighted images with ∼40% reduction in the echo-train-length and T2* blurring at 500µm-isotropic-resolution compared to standard multi-shot EPI.

Computational approaches for the reconstruction of optic nerve fibers along the visual pathway from medical images: a comprehensive review

Optic never fibers in the visual pathway play significant roles in vision formation. Damages of optic nerve fibers are biomarkers for the diagnosis of various ophthalmological and neurological diseases; also, there is a need to prevent the optic nerve fibers from getting damaged in neurosurgery and radiation therapy. Reconstruction of optic nerve fibers from medical images can facilitate all these clinical applications. Although many computational methods are developed for the reconstruction of optic nerve fibers, a comprehensive review of these methods is still lacking. This paper described both the two strategies for optic nerve fiber reconstruction applied in existing studies, i.e., image segmentation and fiber tracking. In comparison to image segmentation, fiber tracking can delineate more detailed structures of optic nerve fibers. For each strategy, both conventional and AI-based approaches were introduced, and the latter usually demonstrates better performance than the former. From the review, we concluded that AI-based methods are the trend for optic nerve fiber reconstruction and some new techniques like generative AI can help address the current challenges in optic nerve fiber reconstruction.

Diffusion MRI data analysis assisted by deep learning synthesized anatomical images (DeepAnat)

Diffusion MRI is a useful neuroimaging tool for non-invasive mapping of human brain microstructure and structural connections. The analysis of diffusion MRI data often requires brain segmentation, including volumetric segmentation and cerebral cortical surfaces, from additional high-resolution T1-weighted (T1w) anatomical MRI data, which may be unacquired, corrupted by subject motion or hardware failure, or cannot be accurately co-registered to the diffusion data that are not corrected for susceptibility-induced geometric distortion. To address these challenges, this study proposes to synthesize high-quality T1w anatomical images directly from diffusion data using convolutional neural networks (CNNs) (entitled "DeepAnat"), including a U-Net and a hybrid generative adversarial network (GAN), and perform brain segmentation on synthesized T1w images or assist the co-registration using synthesized T1w images. The quantitative and systematic evaluations using data of 60 young subjects provided by the Human Connectome Project (HCP) show that the synthesized T1w images and results for brain segmentation and comprehensive diffusion analysis tasks are highly similar to those from native T1w data. The brain segmentation accuracy is slightly higher for the U-Net than the GAN. The efficacy of DeepAnat is further validated on a larger dataset of 300 more elderly subjects provided by the UK Biobank. Moreover, the U-Nets trained and validated on the HCP and UK Biobank data are shown to be highly generalizable to the diffusion data from Massachusetts General Hospital Connectome Diffusion Microstructure Dataset (MGH CDMD) acquired with different hardware systems and imaging protocols and therefore can be used directly without retraining or with fine-tuning for further improved performance. Finally, it is quantitatively demonstrated that the alignment between native T1w images and diffusion images uncorrected for geometric distortion assisted by synthesized T1w images substantially improves upon that by directly co-registering the diffusion and T1w images using the data of 20 subjects from MGH CDMD. In summary, our study demonstrates the benefits and practical feasibility of DeepAnat for assisting various diffusion MRI data analyses and supports its use in neuroscientific applications.

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.

BCM-DTI: A fragment-oriented method for drug-target interaction prediction using deep learning

The identification of drug-target interaction (DTI) is significant in drug discovery and development, which is usually of high cost in time and money due to large amount of molecule and protein space. The application of deep learning in predicting DTI pairs can overcome these limitations through feature engineering. However, most works do the features extraction using the whole drug and target, which do not take the theoretical basis of pharmacological reaction that the interaction is closely related to some substructure of molecule and protein into consideration, thus poor in performance. On the other hand, some substructure-oriented studies only consider a single type of fragment, e.g., functional group. To address these issues, we propose an end-to-end predicting framework for drug-target interaction named BCM-DTI that takes diverse fragment types into account, including branch chain, common substructure and motif/fragments, and applies a feature learning module based on CNN to learn the synergistic effect between these fragments. We implement BCM-DTI on four public datasets, and the results show that BCM-DTI outperforms state-of-the-art approaches and requires lower training cost.

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.

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.

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.

Ligand Binding Prediction Using Protein Structure Graphs and Residual Graph Attention Networks

Computational prediction of ligand–target interactions is a crucial part of modern drug discovery as it helps to bypass high costs and labor demands of in vitro and in vivo screening. As the wealth of bioactivity data accumulates, it provides opportunities for the development of deep learning (DL) models with increasing predictive powers. Conventionally, such models were either limited to the use of very simplified representations of proteins or ineffective voxelization of their 3D structures. Herein, we present the development of the PSG-BAR (Protein Structure Graph-Binding Affinity Regression) approach that utilizes 3D structural information of the proteins along with 2D graph representations of ligands. The method also introduces attention scores to selectively weight protein regions that are most important for ligand binding. Results: The developed approach demonstrates the state-of-the-art performance on several binding affinity benchmarking datasets. The attention-based pooling of protein graphs enables identification of surface residues as critical residues for protein–ligand binding. Finally, we validate our model predictions against an experimental assay on a viral main protease (Mpro)—the hallmark target of SARS-CoV-2 coronavirus.

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.

MAGNIMS recommendations for harmonization of MRI data in MS multicenter studies

•

Sharing data from cooperative studies is essential to develop new biomarkers in MS.

•

Differences in MRI acquisition, analysis, storage represent a substantial constraint.

•

We review the state of the art and developments in the harmonization of MRI.

•

We provide recommendations to harmonize large MRI datasets in the MS field.

There is an increasing need of sharing harmonized data from large, cooperative studies as this is essential to develop new diagnostic and prognostic biomarkers. In the field of multiple sclerosis (MS), the issue has become of paramount importance due to the need to translate into the clinical setting some of the most recent MRI achievements. However, differences in MRI acquisition parameters, image analysis and data storage across sites, with their potential bias, represent a substantial constraint. This review focuses on the state of the art, recent technical advances, and desirable future developments of the harmonization of acquisition, analysis and storage of large-scale multicentre MRI data of MS cohorts. Huge efforts are currently being made to achieve all the requirements needed to provide harmonized MRI datasets in the MS field, as proper management of large imaging datasets is one of our greatest opportunities and challenges in the coming years. Recommendations based on these achievements will be provided here. Despite the advances that have been made, the complexity of these tasks requires further research by specialized academical centres, with dedicated technical and human resources. Such collective efforts involving different professional figures are of crucial importance to offer to MS patients a personalised management while minimizing consumption of resources.

Mitigating transmit‐B 1 artifacts by predicting parallel transmission images with deep learning: A feasibility study using high‐resolution whole‐brain diffusion at 7 Tesla

Purpose

To propose a novel deep learning (DL) approach to transmit‐B₁ (B₁⁺)‐artifact mitigation without direct use of parallel transmission (pTx), by predicting pTx images from single‐channel transmission (sTx) images.

Methods

A deep encoder–decoder convolutional neural network was constructed and trained to learn the mapping from sTx to pTx images. The feasibility was demonstrated using 7 T Human‐Connectome Project (HCP)‐style diffusion MRI. The training dataset comprised images acquired on 5 healthy subjects using commercial Nova RF coils. Relevant hyperparameters were tuned with a nested cross‐validation, and the generalization performance evaluated using a regular cross‐validation.

Results

Our DL method effectively improved the image quality for sTx images by restoring the signal dropout, with quality measures (including normalized root‐mean‐square error, peak SNR, and structural similarity index measure) improved in most brain regions. The improved image quality was translated into improved performances for diffusion tensor imaging analysis; our method improved accuracy for fractional anisotropy and mean diffusivity estimations, reduced the angular errors of principal eigenvectors, and improved the fiber orientation delineation relative to sTx images. Moreover, the final DL model trained on data of all 5 subjects was successfully used to predict pTx images for unseen new subjects (randomly selected from the 7 T HCP database), effectively recovering the signal dropout and improving color‐coded fractional anisotropy maps with largely reduced noise levels.

Conclusion

The proposed DL method has potential to provide images with reduced B1⁺ artifacts in healthy subjects even when pTx resources are inaccessible on the user side.

FOD-Net: A deep learning method for fiber orientation distribution angular super resolution

Mapping the human connectome using fiber-tracking permits the study of brain connectivity and yields new insights into neuroscience. However, reliable connectome reconstruction using diffusion magnetic resonance imaging (dMRI) data acquired by widely available clinical protocols remains challenging, thus limiting the connectome/tractography clinical applications. Here we develop fiber orientation distribution (FOD) network (FOD-Net), a deep-learning-based framework for FOD angular super-resolution. Our method enhances the angular resolution of FOD images computed from common clinical-quality dMRI data, to obtain FODs with quality comparable to those produced from advanced research scanners. Super-resolved FOD images enable superior tractography and structural connectome reconstruction from clinical protocols. The method was trained and tested with high-quality data from the Human Connectome Project (HCP) and further validated with a local clinical 3.0T scanner as well as with another public available multicenter-multiscanner dataset. Using this method, we improve the angular resolution of FOD images acquired with typical single-shell low-angular-resolution dMRI data (e.g., 32 directions, b=1000s/mm²) to approximate the quality of FODs derived from time-consuming, multi-shell high-angular-resolution dMRI research protocols. We also demonstrate tractography improvement, removing spurious connections and bridging missing connections. We further demonstrate that connectomes reconstructed by super-resolved FODs achieve comparable results to those obtained with more advanced dMRI acquisition protocols, on both HCP and clinical 3.0T data. Advances in deep-learning approaches used in FOD-Net facilitate the generation of high quality tractography/connectome analysis from existing clinical MRI environments. Our code is freely available at https://github.com/ruizengalways/FOD-Net.

What's new and what's next in diffusion MRI preprocessing

Diffusion MRI (dMRI) provides invaluable information for the study of tissue microstructure and brain connectivity, but suffers from a range of imaging artifacts that greatly challenge the analysis of results and their interpretability if not appropriately accounted for. This review will cover dMRI artifacts and preprocessing steps, some of which have not typically been considered in existing pipelines or reviews, or have only gained attention in recent years: brain/skull extraction, B-matrix incompatibilities w.r.t the imaging data, signal drift, Gibbs ringing, noise distribution bias, denoising, between- and within-volumes motion, eddy currents, outliers, susceptibility distortions, EPI Nyquist ghosts, gradient deviations, B1 bias fields, and spatial normalization. The focus will be on "what's new" since the notable advances prior to and brought by the Human Connectome Project (HCP), as presented in the predecessing issue on "Mapping the Connectome" in 2013. In addition to the development of novel strategies for dMRI preprocessing, exciting progress has been made in the availability of open source tools and reproducible pipelines, databases and simulation tools for the evaluation of preprocessing steps, and automated quality control frameworks, amongst others. Finally, this review will consider practical considerations and our view on "what's next" in dMRI preprocessing.

Rapid MR relaxometry using deep learning: An overview of current techniques and emerging trends

Quantitative mapping of MR tissue parameters such as the spin-lattice relaxation time (T1 ), the spin-spin relaxation time (T2 ), and the spin-lattice relaxation in the rotating frame (T1ρ ), referred to as MR relaxometry in general, has demonstrated improved assessment in a wide range of clinical applications. Compared with conventional contrast-weighted (eg T1 -, T2 -, or T1ρ -weighted) MRI, MR relaxometry provides increased sensitivity to pathologies and delivers important information that can be more specific to tissue composition and microenvironment. The rise of deep learning in the past several years has been revolutionizing many aspects of MRI research, including image reconstruction, image analysis, and disease diagnosis and prognosis. Although deep learning has also shown great potential for MR relaxometry and quantitative MRI in general, this research direction has been much less explored to date. The goal of this paper is to discuss the applications of deep learning for rapid MR relaxometry and to review emerging deep-learning-based techniques that can be applied to improve MR relaxometry in terms of imaging speed, image quality, and quantification robustness. The paper is comprised of an introduction and four more sections. Section 2 describes a summary of the imaging models of quantitative MR relaxometry. In Section 3, we review existing "classical" methods for accelerating MR relaxometry, including state-of-the-art spatiotemporal acceleration techniques, model-based reconstruction methods, and efficient parameter generation approaches. Section 4 then presents how deep learning can be used to improve MR relaxometry and how it is linked to conventional techniques. The final section concludes the review by discussing the promise and existing challenges of deep learning for rapid MR relaxometry and potential solutions to address these challenges.

SDnDTI: Self-supervised deep learning-based denoising for diffusion tensor MRI

Diffusion tensor magnetic resonance imaging (DTI) is a widely adopted neuroimaging method for the in vivo mapping of brain tissue microstructure and white matter tracts. Nonetheless, the noise in the diffusion-weighted images (DWIs) decreases the accuracy and precision of DTI derived microstructural parameters and leads to prolonged acquisition time for achieving improved signal-to-noise ratio (SNR). Deep learning-based image denoising using convolutional neural networks (CNNs) has superior performance but often requires additional high-SNR data for supervising the training of CNNs, which reduces the feasibility of supervised learning-based denoising in practice. In this work, we develop a self-supervised deep learning-based method entitled "SDnDTI" for denoising DTI data, which does not require additional high-SNR data for training. Specifically, SDnDTI divides multi-directional DTI data into many subsets of six DWI volumes and transforms DWIs from each subset to along the same diffusion-encoding directions through the diffusion tensor model, generating multiple repetitions of DWIs with identical image contrasts but different noise observations. SDnDTI removes noise by first denoising each repetition of DWIs using a deep 3-dimensional CNN with the average of all repetitions with higher SNR as the training target, following the same approach as normal supervised learning based denoising methods, and then averaging CNN-denoised images for achieving higher SNR. The denoising efficacy of SDnDTI is demonstrated in terms of the similarity of output images and resultant DTI metrics compared to the ground truth generated using substantially more DWI volumes on two datasets with different spatial resolutions, b-values and numbers of input DWI volumes provided by the Human Connectome Project (HCP) and the Lifespan HCP in Aging. The SDnDTI results preserve image sharpness and textural details and substantially improve upon those from the raw data. The results of SDnDTI are comparable to those from supervised learning-based denoising and outperform those from state-of-the-art conventional denoising algorithms including BM4D, AONLM and MPPCA. By leveraging domain knowledge of diffusion MRI physics, SDnDTI makes it easier to use CNN-based denoising methods in practice and has the potential to benefit a wider range of research and clinical applications that require accelerated DTI acquisition and high-quality DTI data for mapping of tissue microstructure, fiber tracts and structural connectivity in the living human brain.

Automated Segmentation and Connectivity Analysis for Normal Pressure Hydrocephalus

Objective and Impact Statement. We propose an automated method of predicting Normal Pressure Hydrocephalus (NPH) from CT scans. A deep convolutional network segments regions of interest from the scans. These regions are then combined with MRI information to predict NPH. To our knowledge, this is the first method which automatically predicts NPH from CT scans and incorporates diffusion tractography information for prediction. Introduction. Due to their low cost and high versatility, CT scans are often used in NPH diagnosis. No well-defined and effective protocol currently exists for analysis of CT scans for NPH. Evans' index, an approximation of the ventricle to brain volume using one 2D image slice, has been proposed but is not robust. The proposed approach is an effective way to quantify regions of interest and offers a computational method for predicting NPH. Methods. We propose a novel method to predict NPH by combining regions of interest segmented from CT scans with connectome data to compute features which capture the impact of enlarged ventricles by excluding fiber tracts passing through these regions. The segmentation and network features are used to train a model for NPH prediction. Results. Our method outperforms the current state-of-the-art by 9 precision points and 29 recall points. Our segmentation model outperforms the current state-of-the-art in segmenting the ventricle, gray-white matter, and subarachnoid space in CT scans. Conclusion. Our experimental results demonstrate that fast and accurate volumetric segmentation of CT brain scans can help improve the NPH diagnosis process, and network properties can increase NPH prediction accuracy.

High-fidelity fast volumetric brain MRI using synergistic wave-controlled aliasing in parallel imaging and a hybrid denoising generative adversarial network (HDnGAN)

PURPOSE

The goal of this study is to leverage an advanced fast imaging technique, wave-controlled aliasing in parallel imaging (Wave-CAIPI), and a generative adversarial network (GAN) for denoising to achieve accelerated high-quality high-signal-to-noise-ratio (SNR) volumetric MRI.

METHODS

Three-dimensional (3D) T₂ -weighted fluid-attenuated inversion recovery (FLAIR) image data were acquired on 33 multiple sclerosis (MS) patients using a prototype Wave-CAIPI sequence (acceleration factor R = 3×2, 2.75 minutes) and a standard T₂ -SPACE FLAIR sequence (R = 2, 7.25 minutes). A hybrid denoising GAN entitled "HDnGAN" consisting of a 3D generator and a 2D discriminator was proposed to denoise highly accelerated Wave-CAIPI images. HDnGAN benefits from the improved image synthesis performance provided by the 3D generator and increased training samples from a limited number of patients for training the 2D discriminator. HDnGAN was trained and validated on data from 25 MS patients with the standard FLAIR images as the target and evaluated on data from 8 MS patients not seen during training. HDnGAN was compared to other denoising methods including AONLM, BM4D, MU-Net, and 3D GAN in qualitative and quantitative analysis of output images using the mean squared error (MSE) and VGG perceptual loss compared to standard FLAIR images, and a reader assessment by two neuroradiologists regarding sharpness, SNR, lesion conspicuity, and overall quality. Finally, the performance of these denoising methods was compared at higher noise levels using simulated data with added Rician noise.

RESULTS

HDnGAN effectively denoised low-SNR Wave-CAIPI images with sharpness and rich textural details, which could be adjusted by controlling the contribution of the adversarial loss to the total loss when training the generator. Quantitatively, HDnGAN (λ = 10^-3 ) achieved low MSE and the lowest VGG perceptual loss. The reader study showed that HDnGAN (λ = 10^-3 ) significantly improved the SNR of Wave-CAIPI images (P<0.001), outperformed AONLM (P = 0.015), BM4D (P<0.001), MU-Net (P<0.001) and 3D GAN (λ = 10^-3 ) (P<0.001) regarding image sharpness, and outperformed MU-Net (P<0.001) and 3D GAN (λ = 10^-3 ) (P = 0.001) regarding lesion conspicuity. The overall quality score of HDnGAN (λ = 10^-3 ) (4.25±0.43) was significantly higher than those from Wave-CAIPI (3.69±0.46, P = 0.003), BM4D (3.50±0.71, P = 0.001), MU-Net (3.25±0.75, P<0.001), and 3D GAN (λ = 10^-3 ) (3.50±0.50, P<0.001), with no significant difference compared to standard FLAIR images (4.38±0.48, P = 0.333). The advantages of HDnGAN over other methods were more obvious at higher noise levels.

CONCLUSION

HDnGAN provides robust and feasible denoising while preserving rich textural detail in empirical volumetric MRI data. Our study using empirical patient data and systematic evaluation supports the use of HDnGAN in combination with modern fast imaging techniques such as Wave-CAIPI to achieve high-fidelity fast volumetric MRI and represents an important step to the clinical translation of GANs. This article is protected by copyright. All rights reserved.

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

Specific features of white matter microstructure can be investigated by using biophysical models to interpret relaxation-diffusion MRI brain data. Although more intricate models have the potential to reveal more details of the tissue, they also incur time-consuming parameter estimation that may converge to inaccurate solutions due to a prevalence of local minima in a degenerate fitting landscape. Machine-learning fitting algorithms have been proposed to accelerate the parameter estimation and increase the robustness of the attained estimates. So far, learning-based fitting approaches have been restricted to microstructural models with a reduced number of independent model parameters where dense sets of training data are easy to generate. Moreover, the degree to which machine learning can alleviate the degeneracy problem is poorly understood. For conventional least-squares solvers, it has been shown that degeneracy can be avoided by acquisition with optimized relaxation-diffusion-correlation protocols that include tensor-valued diffusion encoding. Whether machine-learning techniques can offset these acquisition requirements remains to be tested. In this work, we employ artificial neural networks to vastly accelerate the parameter estimation for a recently introduced relaxation-diffusion model of white matter microstructure. We also develop strategies for assessing the accuracy and sensitivity of function fitting networks and use those strategies to explore the impact of the acquisition protocol. The developed learning-based fitting pipelines were tested on relaxation-diffusion data acquired with optimal and sub-optimal acquisition protocols. Networks trained with an optimized protocol were observed to provide accurate parameter estimates within short computational times. Comparing neural networks and least-squares solvers, we found the performance of the former to be less affected by sub-optimal protocols; however, model fitting networks were still susceptible to degeneracy issues and their use could not fully replace a careful design of the acquisition protocol.

Deep learning-based parameter estimation in fetal diffusion-weighted MRI

Diffusion-weighted magnetic resonance imaging (DW-MRI) of fetal brain is challenged by frequent fetal motion and signal to noise ratio that is much lower than non-fetal imaging. As a result, accurate and robust parameter estimation in fetal DW-MRI remains an open problem. Recently, deep learning techniques have been successfully used for DW-MRI parameter estimation in non-fetal subjects. However, none of those prior works has addressed the fetal brain because obtaining reliable fetal training data is challenging. To address this problem, in this work we propose a novel methodology that utilizes fetal scans as well as scans from prematurely-born infants. High-quality newborn scans are used to estimate accurate maps of the parameter of interest. These parameter maps are then used to generate DW-MRI data that match the measurement scheme and noise distribution that are characteristic of fetal data. In order to demonstrate the effectiveness and reliability of the proposed data generation pipeline, we used the generated data to train a convolutional neural network (CNN) to estimate color fractional anisotropy (CFA). We evaluated the trained CNN on independent sets of fetal data in terms of reconstruction accuracy, precision, and expert assessment of reconstruction quality. Results showed significantly lower reconstruction error (n=100,p<0.001) and higher reconstruction precision (n=20,p<0.001) for the proposed machine learning pipeline compared with standard estimation methods. Expert assessments on 20 fetal test scans showed significantly better overall reconstruction quality (p<0.001) and more accurate reconstruction of 11 regions of interest (p<0.001) with the proposed method.

Magnetic Resonance Imaging Features under Deep Learning Algorithms in Evaluated Cerebral Protection of Craniotomy Evacuation of Hematoma under Propofol Anesthesia

This study aimed to explore the value of magnetic resonance imaging (MRI) features based on deep learning super-resolution algorithms in evaluating the value of propofol anesthesia for brain protection of patients undergoing craniotomy evacuation of the hematoma. An optimized super-resolution algorithm was obtained through the multiscale network reconstruction model based on the traditional algorithm. A total of 100 patients undergoing craniotomy evacuation of hematoma were recruited and rolled into sevoflurane control group and propofol experimental group. Both were evaluated using diffusion tensor imaging (DTI) images based on deep learning super-resolution algorithms. The results showed that the fractional anisotropic image (FA) value of the hind limb corticospinal tract of the affected side of the internal capsule of the experimental group after the operation was 0.67 ± 0.28. The National Institute of Health Stroke Scale (NIHSS) score was 6.14 ± 3.29. The oxygen saturation in jugular venous (SjvO₂) at T4 and T5 was 61.93 ± 6.58% and 59.38 ± 6.2%, respectively, and cerebral oxygen uptake rate (CO₂ER) was 31.12 ± 6.07% and 35.83 ± 7.91%, respectively. The difference in jugular venous oxygen (Da-jvO₂) at T3, T4, and T5 was 63.28 ± 10.15 mL/dL, 64.89 ± 13.11 mL/dL, and 66.03 ± 11.78 mL/dL, respectively. The neuron-specific enolase (NSE) and central-nerve-specific protein (S100β) levels at T5 were 53.85 ± 12.31 ng/mL and 7.49 ± 3.16 ng/mL, respectively. In terms of the number of postoperative complications, the patients in the experimental group were better than the control group under sevoflurane anesthesia, and the differences were substantial (P < 0.05). In conclusion, MRI images based on deep learning super-resolution algorithm have great clinical value in evaluating the degree of brain injury in patients anesthetized with propofol and the protective effect of propofol on brain nerves.

Training data distribution significantly impacts the estimation of tissue microstructure with machine learning

PURPOSE

Supervised machine learning (ML) provides a compelling alternative to traditional model fitting for parameter mapping in quantitative MRI. The aim of this work is to demonstrate and quantify the effect of different training data distributions on the accuracy and precision of parameter estimates when supervised ML is used for fitting.

METHODS

We fit a two- and three-compartment biophysical model to diffusion measurements from in-vivo human brain, as well as simulated diffusion data, using both traditional model fitting and supervised ML. For supervised ML, we train several artificial neural networks, as well as random forest regressors, on different distributions of ground truth parameters. We compare the accuracy and precision of parameter estimates obtained from the different estimation approaches using synthetic test data.

RESULTS

When the distribution of parameter combinations in the training set matches those observed in healthy human data sets, we observe high precision, but inaccurate estimates for atypical parameter combinations. In contrast, when training data is sampled uniformly from the entire plausible parameter space, estimates tend to be more accurate for atypical parameter combinations but may have lower precision for typical parameter combinations.

CONCLUSION

This work highlights that estimation of model parameters using supervised ML depends strongly on the training-set distribution. We show that high precision obtained using ML may mask strong bias, and visual assessment of the parameter maps is not sufficient for evaluating the quality of the estimates.

Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRI

Current deep learning approaches for diffusion MRI modeling circumvent the need for densely-sampled diffusion-weighted images (DWIs) by directly predicting microstructural indices from sparsely-sampled DWIs. However, they implicitly make unrealistic assumptions of static q-space sampling during training and reconstruction. Further, such approaches can restrict downstream usage of variably sampled DWIs for usages including the estimation of microstructural indices or tractography. We propose a generative adversarial translation framework for high-quality DWI synthesis with arbitrary q-space sampling given commonly acquired structural images (e.g., B0, T1, T2). Our translation network linearly modulates its internal representations conditioned on continuous q-space information, thus removing the need for fixed sampling schemes. Moreover, this approach enables downstream estimation of high-quality microstructural maps from arbitrarily subsampled DWIs, which may be particularly important in cases with sparsely sampled DWIs. Across several recent methodologies, the proposed approach yields improved DWI synthesis accuracy and fidelity with enhanced downstream utility as quantified by the accuracy of scalar microstructure indices estimated from the synthesized images. Code is available at https://github.com/mengweiren/q-space-conditioned-dwi-synthesis.

[A diffusion-weighted image denoising algorithm using HOSVD combined with Rician noise corrected model]

OBJECTIVE

To propose a novel diffusion-weighted (DW) image denoising algorithm based on HOSVD to improve the signal-to-noise ratio (SNR) of DW images and the accuracy of subsequent quantization parameters.

METHODS

This HOSVDbased denoising method incorporated the sparse constraint and noise-correction model. The signal expectations with Rician noise were integrated into the traditional HOSVD denoising framework for direct denoising of the DW images with Rician noise. HOSVD denoising was performed directly on each local DW image block to avoid the stripe artifacts. We compared the proposed method with 4 image denoising algorithms (LR + Edge, GL-HOSVD, BM3D and NLM) to verify the effect of the proposed method.

RESULTS

The experimental results showed that the proposed method effectively reduced the noise of DW images while preserving the image details and edge structure information. The proposed algorithm was significantly better than LR +Edge, BM3D and NLM in terms of quantitative metrics of PSNR, SSIM and FA-RMSE and in visual evaluation of denoising images and FA images. GL-HOSVD obtained good denoising results but introduced stripe artifacts at a high noise level during the denoising process. In contrast, the proposed method achieved good denoising results without causing stripe artifacts.

CONCLUSION

This HOSVD-based denoising method allows direct processing of DW images with Rician noise without introducing artifacts and can provide accurate quantitative parameters for diagnostic purposes.

Prospective Deployment of Deep Learning in MRI: A Framework for Important Considerations, Challenges, and Recommendations for Best Practices

Artificial intelligence algorithms based on principles of deep learning (DL) have made a large impact on the acquisition, reconstruction, and interpretation of MRI data. Despite the large number of retrospective studies using DL, there are fewer applications of DL in the clinic on a routine basis. To address this large translational gap, we review the recent publications to determine three major use cases that DL can have in MRI, namely, that of model-free image synthesis, model-based image reconstruction, and image or pixel-level classification. For each of these three areas, we provide a framework for important considerations that consist of appropriate model training paradigms, evaluation of model robustness, downstream clinical utility, opportunities for future advances, as well recommendations for best current practices. We draw inspiration for this framework from advances in computer vision in natural imaging as well as additional healthcare fields. We further emphasize the need for reproducibility of research studies through the sharing of datasets and software. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY STAGE: 2.

SuperDTI: Ultrafast DTI and fiber tractography with deep learning

PURPOSE

To develop a deep learning-based reconstruction framework for ultrafast and robust diffusion tensor imaging and fiber tractography.

METHODS

SuperDTI was developed to learn the nonlinear relationship between DWIs and the corresponding diffusion tensor parameter maps. It bypasses the tensor fitting procedure, which is highly susceptible to noises and motions in DWIs. The network was trained and tested using data sets from the Human Connectome Project and patients with ischemic stroke. Results from SuperDTI were compared against widely used methods for tensor parameter estimation and fiber tracking.

RESULTS

Using training and testing data acquired using the same protocol and scanner, SuperDTI was shown to generate fractional anisotropy and mean diffusivity maps, as well as fiber tractography, from as few as six raw DWIs, with a quantification error of less than 5% in all white-matter and gray-matter regions of interest. It was robust to noises and motions in the testing data. Furthermore, the network trained using healthy volunteer data showed no apparent reduction in lesion detectability when directly applied to stroke patient data.

CONCLUSIONS

Our results demonstrate the feasibility of superfast DTI and fiber tractography using deep learning with as few as six DWIs directly, bypassing tensor fitting. Such a significant reduction in scan time may allow the inclusion of DTI into the clinical routine for many potential applications.

Accelerated in Vivo Cardiac Diffusion-Tensor MRI Using Residual Deep Learning-based Denoising in Participants with Obesity

Purpose

To develop and assess a residual deep learning algorithm to accelerate in vivo cardiac diffusion-tensor MRI (DT-MRI) by reducing the number of averages while preserving image quality and DT-MRI parameters.

Materials and Methods

In this prospective study, a denoising convolutional neural network (DnCNN) for DT-MRI was developed; a total of 26 participants, including 20 without obesity (body mass index [BMI] < 30 kg/m²; mean age, 28 years ± 3 [standard deviation]; 11 women) and six with obesity (BMI ≥ 30 kg/m²; mean age, 48 years ± 11; five women), were recruited from June 19, 2019, to July 29, 2020. DT-MRI data were constructed at four averages (4Av), two averages (2Av), and one average (1Av) without and with the application of the DnCNN (4Av_DnCNN, 2Av_DnCNN, 1Av_DnCNN). All data were compared against the reference DT-MRI data constructed at eight averages (8Av). Image quality, characterized by using the signal-to-noise ratio (SNR) and structural similarity index (SSIM), and the DT-MRI parameters of mean diffusivity (MD), fractional anisotropy (FA), and helix angle transmurality (HAT) were quantified.

Results

No differences were found in image quality or DT-MRI parameters between the accelerated 4Av_DnCNN DT-MRI and the reference 8Av DT-MRI data for the SNR (29.1 ± 2.7 vs 30.5 ± 2.9), SSIM (0.97 ± 0.01), MD (1.3 µm²/msec ± 0.1 vs 1.31 µm²/msec ± 0.11), FA (0.32 ± 0.05 vs 0.30 ± 0.04), or HAT (1.10°/% ± 0.13 vs 1.11°/% ± 0.09). The relationship of a higher MD and lower FA and HAT in individuals with obesity compared with individuals without obesity in reference 8Av DT-MRI measurements was retained in 4Av_DnCNN and 2Av_DnCNN DT-MRI measurements but was not retained in 4Av or 2Av DT-MRI measurements.

Conclusion

Cardiac DT-MRI can be performed at an at least twofold-accelerated rate by using DnCNN to preserve image quality and DT-MRI parameter quantification.Keywords: Adults, Cardiac, Obesity, Technology Assessment, MR-Diffusion Tensor Imaging, Heart, Tissue CharacterizationSupplemental material is available for this article.© RSNA, 2021.

Relevant Biophysical Parameters Discrimination along Corticospinal Tract in Patients with Stroke Using Convolutional Neural Networks

Stroke remains the leading source of long-term disability. As the only direct descending motor pathway, the corticospinal tract (CST) is the primary pathway to innervate spinal motor neurons and one of the most well studied tracts in human neuroanatomy. Its clinical significance can be demonstrated in many distinguished traumatic situations and diseases such as stroke. Along‐tract statistics analysis enables the extraction of quantitative diffusion metrics along specific white matter fiber tracts. Besides quantitative metrics derived from classical diffusion tensor imaging (DTI), such as fractional anisotropy and diffusivities. In this study, we extracted DTI derived quantitative microstructural diffusion metrics along the CST tract in patients with moderate to severe subacute stroke. Respectively DTI metric of individual patient's fiber tract was then plotted. This approach may be useful for future studies that may compare in two different time (acute and chronic). The contribution of this work presents a totally computerized method of DTI image recognition based on conventional neural network (CNN) in order to supply quantitative appraisal of clinical characteristics. The obtained results have achieved an important classification (Accuracy=94.12%) when applying the CNN. The proposed methodology enables us to assess the classification of the used DTI images database within a reduced processing time. Experimental results prove the success of the proposed rating system for a suitable analysis of microstructural diffusion when compared to previous work.