Deep Residual Learning for Accelerated MRI Using Magnitude and Phase Networks

Self-supervised learning for MRI reconstruction through mapping resampled k-space data to resampled k-space data

In recent years, significant advancements have been achieved in applying deep learning (DL) to magnetic resonance imaging (MRI) reconstruction, which traditionally relies on fully sampled data. However, real-world clinical scenarios often demonstrate that the fully sampled data can be challenging or impossible to obtain due to physiological constraints, such as organ motion, and physical constraints, such as signal decay. In this paper, we introduce a self-supervised DL approach, termed randomly self-supervised learning via data undersampling (abbreviated as RSSDU), which is proficient in efficiently and accurately reconstructing images from undersampled MRI data without requiring fully sampled datasets as references. The proposed method involves resampling the acquired k-space data twice to generate two subsets using the same undersampling pattern as the original acquisitions, albeit with different acceleration factors. Subsequently, a network is trained to learn to map from one of the sets to the other in a supervised manner. Extensive experiments demonstrate that the RSSDU method outperforms several well-known self-supervised methods, including SSDU and K-band, regarding peak signal-to-noise ratio and structural similarity index measurement.

Illuminating the unseen: Advancing MRI domain generalization through causality

Deep learning methods have shown promise in accelerated MRI reconstruction but face significant challenges under domain shifts between training and testing datasets, such as changes in image contrasts, anatomical regions, and acquisition strategies. To address these challenges, we present the first domain generalization framework specifically designed for accelerated MRI reconstruction to robustness across unseen domains. The framework employs progressive strategies to enforce domain invariance, starting with image-level fidelity consistency to ensure robust reconstruction quality across domains, and feature alignment to capture domain-invariant representations. Advancing beyond these foundations, we propose a novel approach enforcing mechanism-level invariance, termed GenCA-MRI, which aligns intrinsic causal relationships within MRI data. We further develop a computational strategy that significantly reduces the complexity of causal alignment, ensuring its feasibility for real-world applications. Extensive experiments validate the framework's effectiveness, demonstrating both numerical and visual improvements over the baseline algorithm. GenCA-MRI presents the overall best performance, achieving a PSNR improvement up to 2.15 dB on fastMRI and 1.24 dB on IXI dataset at 8× acceleration, with superior performance in preserving anatomical details and mitigating domain-shift problem.

CAMP-Net: Consistency-Aware Multi-Prior Network for Accelerated MRI Reconstruction

Undersampling -space data in magnetic resonance imaging (MRI) reduces scan time but pose challenges in image reconstruction. Considerable progress has been made in reconstructing accelerated MRI. However, restoration of high-frequency image details in highly undersampled data remains challenging. To address this issue, we propose CAMP-Net, an unrolling-based Consistency-Aware Multi-Prior Network for accelerated MRI reconstruction. CAMP-Net leverages complementary multi-prior knowledge and multi-slice information from various domains to enhance reconstruction quality. Specifically, CAMP-Net comprises three interleaved modules for image enhancement, -space restoration, and calibration consistency, respectively. These modules jointly learn priors from data in image domain, -domain, and calibration region, respectively, in data-driven manner during each unrolled iteration. Notably, the encoded calibration prior knowledge extracted from auto-calibrating signals implicitly guides the learning of consistency-aware -space correlation for reliable interpolation of missing -space data. To maximize the benefits of image domain and -domain prior knowledge, the reconstructions are aggregated in a frequency fusion module, exploiting their complementary properties to optimize the trade-off between artifact removal and fine detail preservation. Additionally, we incorporate a surface data fidelity layer during the learning of -domain and calibration domain priors to prevent degradation of the reconstruction caused by padding-induced data imperfections. We evaluate the generalizability and robustness of our method on three large public datasets with varying acceleration factors and sampling patterns. The experimental results demonstrate that our method outperforms state-of-the-art approaches in terms of both reconstruction quality and mapping estimation, particularly in scenarios with high acceleration factors.

DONet: Dual-Octave Network for Fast MR Image Reconstruction

Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration has long been the subject of research. This is commonly achieved by obtaining multiple undersampled images, simultaneously, through parallel imaging. In this article, we propose the dual-octave network (DONet), which is capable of learning multiscale spatial-frequency features from both the real and imaginary components of MR data, for parallel fast MR image reconstruction. More specifically, our DONet consists of a series of dual-octave convolutions (Dual-OctConvs), which are connected in a dense manner for better reuse of features. In each Dual-OctConv, the input feature maps and convolutional kernels are first split into two components (i.e., real and imaginary) and then divided into four groups according to their spatial frequencies. Then, our Dual-OctConv conducts intragroup information updating and intergroup information exchange to aggregate the contextual information across different groups. Our framework provides three appealing benefits: 1) it encourages information interaction and fusion between the real and imaginary components at various spatial frequencies to achieve richer representational capacity; 2) the dense connections between the real and imaginary groups in each Dual-OctConv make the propagation of features more efficient by feature reuse; and 3) DONet enlarges the receptive field by learning multiple spatial-frequency features of both the real and imaginary components. Extensive experiments on two popular datasets (i.e., clinical knee and fastMRI), under different undersampling patterns and acceleration factors, demonstrate the superiority of our model in accelerated parallel MR image reconstruction.

Attention incorporated network for sharing low-rank, image and k-space information during MR image reconstruction to achieve single breath-hold cardiac Cine imaging

Cardiac Cine Magnetic Resonance Imaging (MRI) provides an accurate assessment of heart morphology and function in clinical practice. However, MRI requires long acquisition times, with recent deep learning-based methods showing great promise to accelerate imaging and enhance reconstruction quality. Existing networks exhibit some common limitations that constrain further acceleration possibilities, including single-domain learning, reliance on a single regularization term, and equal feature contribution. To address these limitations, we propose to embed information from multiple domains, including low-rank, image, and k-space, in a novel deep learning network for MRI reconstruction, which we denote as A-LIKNet. A-LIKNet adopts a parallel-branch structure, enabling independent learning in the k-space and image domain. Coupled information sharing layers realize the information exchange between domains. Furthermore, we introduce attention mechanisms into the network to assign greater weights to more critical coils or important temporal frames. Training and testing were conducted on an in-house dataset, including 91 cardiovascular patients and 38 healthy subjects scanned with 2D cardiac Cine using retrospective undersampling. Additionally, we evaluated A-LIKNet on the real-time prospectively undersampled data from the OCMR dataset. The results demonstrate that our proposed A-LIKNet outperforms existing methods and provides high-quality reconstructions. The network can effectively reconstruct highly retrospectively undersampled dynamic MR images up to 24× accelerations, indicating its potential for single breath-hold imaging.

In-vivo high-resolution χ-separation at 7T

A recently introduced quantitative susceptibility mapping (QSM) technique, χ-separation, offers the capability to separate paramagnetic (χpara) and diamagnetic (χdia) susceptibility distribution within the brain. In-vivo high-resolution mapping of iron and myelin distribution, estimated by χ-separation, could provide a deeper understanding of brain substructures, assisting the investigation of their functions and alterations. This can be achieved using 7T MRI, which benefits from a high signal-to-noise ratio and susceptibility effects. However, applying χ-separation at 7T presents difficulties due to the requirement of an R2 map, coupled with issues such as high specific absorption rate (SAR), large B1 transmit field inhomogeneities, and prolonged scan time. To address these challenges, we developed a novel deep neural network, R2PRIMEnet7T, designed to convert a 7T R2* map into a 3T R2' map. Building on this development, we present a new pipeline for χ-separation at 7T, enabling us to generate high-resolution χ-separation maps from multi-echo gradient-echo data. The proposed method is compared with alternative pipelines, such as an end-to-end network and linearly-scaled R2', and is validated against χ-separation maps at 3T, demonstrating its accuracy. The 7T χ-separation maps generated by the proposed method exhibit similar contrasts to those from 3T, while 7T high-resolution maps offer enhanced clarity and detail. Quantitative analysis confirms that the proposed method surpasses the alternative pipelines. The proposed method results well delineate the detailed brain structures associated with iron and myelin. This new pipeline holds promise for analyzing iron and myelin concentration changes in various neurodegenerative diseases through precise structural examination.

Artificial Intelligence for Neuroimaging in Pediatric Cancer

BACKGROUND/OBJECTIVES

Artificial intelligence (AI) is transforming neuroimaging by enhancing diagnostic precision and treatment planning. However, its applications in pediatric cancer neuroimaging remain limited. This review assesses the current state, potential applications, and challenges of AI in pediatric neuroimaging for cancer, emphasizing the unique needs of the pediatric population.

METHODS

A comprehensive literature review was conducted, focusing on AI's impact on pediatric neuroimaging through accelerated image acquisition, reduced radiation, and improved tumor detection. Key methods include convolutional neural networks for tumor segmentation, radiomics for tumor characterization, and several tools for functional imaging. Challenges such as limited pediatric datasets, developmental variability, ethical concerns, and the need for explainable models were analyzed.

RESULTS

AI has shown significant potential to improve imaging quality, reduce scan times, and enhance diagnostic accuracy in pediatric neuroimaging, resulting in improved accuracy in tumor segmentation and outcome prediction for treatment. However, progress is hindered by the scarcity of pediatric datasets, issues with data sharing, and the ethical implications of applying AI in vulnerable populations.

CONCLUSIONS

To overcome current limitations, future research should focus on building robust pediatric datasets, fostering multi-institutional collaborations for data sharing, and developing interpretable AI models that align with clinical practice and ethical standards. These efforts are essential in harnessing the full potential of AI in pediatric neuroimaging and improving outcomes for children with cancer.

Physics-guided self-supervised learning: Demonstration for generalized RF pulse design

PURPOSE

To introduce a new method for generalized RF pulse design using physics-guided self-supervised learning (GPS), which uses the Bloch equations as the guiding physics model.

THEORY AND METHODS

The GPS framework consists of a neural network module and a physics module, where the physics module is a Bloch simulator for MRI applications. For RF pulse design, the neural network module maps an input target profile to an RF pulse, which is subsequently loaded into the physics module. Through the supervision of the physics module, the neural network module designs an RF pulse corresponding to the target profile. GPS was applied to design 1D selective,B 1 $$ {B}_1 $$ -insensitive, saturation, and multidimensional RF pulses, each conventionally requiring dedicated design algorithms. We further demonstrate our method's flexibility and versatility by compensating for experimental and scanner imperfections through online adaptation.

RESULTS

Both simulations and experiments show that GPS can design a variety of RF pulses with corresponding profiles that agree well with the target input. Despite these verifications, GPS-designed pulses have unique differences compared to conventional designs, such as achievingB 1 $$ {B}_1 $$ -insensitivity using different mechanisms and using non-sampled regions of the conventional design to lower its peak power. Experiments, both ex vivo and in vivo, further verify that it can also be used for online adaptation to correct system imperfections, such asB 0 $$ {B}_0 $$ /B 1 + $$ {B}_1^{+} $$ inhomogeneity.

CONCLUSION

This work demonstrates the generalizability, versatility, and flexibility of the GPS method for designing RF pulses and showcases its utility in several applications.

Generalizable Reconstruction for Accelerating MR Imaging via Federated Learning With Neural Architecture Search

Heterogeneous data captured by different scanning devices and imaging protocols can affect the generalization performance of the deep learning magnetic resonance (MR) reconstruction model. While a centralized training model is effective in mitigating this problem, it raises concerns about privacy protection. Federated learning is a distributed training paradigm that can utilize multi-institutional data for collaborative training without sharing data. However, existing federated learning MR image reconstruction methods rely on models designed manually by experts, which are complex and computationally expensive, suffering from performance degradation when facing heterogeneous data distributions. In addition, these methods give inadequate consideration to fairness issues, namely ensuring that the model's training does not introduce bias towards any specific dataset's distribution. To this end, this paper proposes a generalizable federated neural architecture search framework for accelerating MR imaging (GAutoMRI). Specifically, automatic neural architecture search is investigated for effective and efficient neural network representation learning of MR images from different centers. Furthermore, we design a fairness adjustment approach that can enable the model to learn features fairly from inconsistent distributions of different devices and centers, and thus facilitate the model to generalize well to the unseen center. Extensive experiments show that our proposed GAutoMRI has better performances and generalization ability compared with seven state-of-the-art federated learning methods. Moreover, the GAutoMRI model is significantly more lightweight, making it an efficient choice for MR image reconstruction tasks. The code will be made available at https://github.com/ternencewu123/GAutoMRI.

Fourier Convolution Block with global receptive field for MRI reconstruction

Reconstructing images from under-sampled Magnetic Resonance Imaging (MRI) signals significantly reduces scan time and improves clinical practice. However, Convolutional Neural Network (CNN)-based methods, while demonstrating great performance in MRI reconstruction, may face limitations due to their restricted receptive field (RF), hindering the capture of global features. This is particularly crucial for reconstruction, as aliasing artifacts are distributed globally. Recent advancements in Vision Transformers have further emphasized the significance of a large RF. In this study, we proposed a novel global Fourier Convolution Block (FCB) with whole image RF and low computational complexity by transforming the regular spatial domain convolutions into frequency domain. Visualizations of the effective RF and trained kernels demonstrated that FCB improves the RF of reconstruction models in practice. The proposed FCB was evaluated on four popular CNN architectures using brain and knee MRI datasets. Models with FCB achieved superior PSNR and SSIM than baseline models and exhibited more details and texture recovery. The code is publicly available at https://github.com/Haozhoong/FCB.

AutoSamp: Autoencoding k-Space Sampling via Variational Information Maximization for 3D MRI

Accelerated MRI protocols routinely involve a predefined sampling pattern that undersamples the k-space. Finding an optimal pattern can enhance the reconstruction quality, however this optimization is a challenging task. To address this challenge, we introduce a novel deep learning framework, AutoSamp, based on variational information maximization that enables joint optimization of sampling pattern and reconstruction of MRI scans. We represent the encoder as a non-uniform Fast Fourier Transform that allows continuous optimization of k-space sample locations on a non-Cartesian plane, and the decoder as a deep reconstruction network. Experiments on public 3D acquired MRI datasets show improved reconstruction quality of the proposed AutoSamp method over the prevailing variable density and variable density Poisson disc sampling for both compressed sensing and deep learning reconstructions. We demonstrate that our data-driven sampling optimization method achieves 4.4dB, 2.0dB, 0.75dB, 0.7dB PSNR improvements over reconstruction with Poisson Disc masks for acceleration factors of R =5, 10, 15, 25, respectively. Prospectively accelerated acquisitions with 3D FSE sequences using our optimized sampling patterns exhibit improved image quality and sharpness. Furthermore, we analyze the characteristics of the learned sampling patterns with respect to changes in acceleration factor, measurement noise, underlying anatomy, and coil sensitivities. We show that all these factors contribute to the optimization result by affecting the sampling density, k-space coverage and point spread functions of the learned sampling patterns.

FEFA: Frequency Enhanced Multi-Modal MRI Reconstruction With Deep Feature Alignment

Integrating complementary information from multiple magnetic resonance imaging (MRI) modalities is often necessary to make accurate and reliable diagnostic decisions. However, the different acquisition speeds of these modalities mean that obtaining information can be time consuming and require significant effort. Reference-based MRI reconstruction aims to accelerate slower, under-sampled imaging modalities, such as T2-modality, by utilizing redundant information from faster, fully sampled modalities, such as T1-modality. Unfortunately, spatial misalignment between different modalities often negatively impacts the final results. To address this issue, we propose FEFA, which consists of cascading FEFA blocks. The FEFA block first aligns and fuses the two modalities at the feature level. The combined features are then filtered in the frequency domain to enhance the important features while simultaneously suppressing the less essential ones, thereby ensuring accurate reconstruction. Furthermore, we emphasize the advantages of combining the reconstruction results from multiple cascaded blocks, which also contributes to stabilizing the training process. Compared to existing registration-then-reconstruction and cross-attention-based approaches, our method is end-to-end trainable without requiring additional supervision, extensive parameters, or heavy computation. Experiments on the public fastMRI, IXI and in-house datasets demonstrate that our approach is effective across various under-sampling patterns and ratios.

An unrolled neural network for accelerated dynamic MRI based on second-order half-quadratic splitting model

The reconstruction of dynamic magnetic resonance images from incomplete k-space data has sparked significant research interest due to its potential to reduce scan time. However, traditional iterative optimization algorithms fail to faithfully reconstruct images at higher acceleration factors and incur long reconstruction time. Furthermore, end-to-end deep learning-based reconstruction algorithms suffer from large model parameters and lack robustness in the reconstruction results. Recently, unrolled deep learning models, have shown immense potential in algorithm stability and applicability flexibility. In this paper, we propose an unrolled deep learning network based on a second-order Half-Quadratic Splitting(HQS) algorithm, where the forward propagation process of this framework strictly follows the computational flow of the HQS algorithm. In particular, we propose a degradation-sense module by associating random sampling patterns with intermediate variables to guide the iterative process. We introduce the Information Fusion Transformer(IFT) to extract both local and non-local prior information from image sequences, thereby removing aliasing artifacts resulting from random undersampling. Finally, we impose low-rank constraints within the HQS algorithm to further enhance the reconstruction results. The experiments demonstrate that each component module of our proposed model contributes to the improvement of the reconstruction task. Our proposed method achieves comparably satisfying performance to the state-of-the-art methods and it exhibits excellent generalization capabilities across different sampling masks. At the low acceleration factor, there is a 0.7% enhancement in the PSNR. Furthermore, when the acceleration factor reached 8 and 12, the PSNR achieves an improvement of 3.4% and 5.8% respectively.

Assessing deep learning reconstruction for faster prostate MRI: visual vs. diagnostic performance metrics

OBJECTIVE

Deep learning (DL) MRI reconstruction enables fast scan acquisition with good visual quality, but the diagnostic impact is often not assessed because of large reader study requirements. This study used existing diagnostic DL to assess the diagnostic quality of reconstructed images.

MATERIALS AND METHODS

A retrospective multisite study of 1535 patients assessed biparametric prostate MRI between 2016 and 2020. Likely clinically significant prostate cancer (csPCa) lesions (PI-RADS ≥ 4) were delineated by expert radiologists. T2-weighted scans were retrospectively undersampled, simulating accelerated protocols. DL reconstruction (DLRecon) and diagnostic DL detection (DLDetect) were developed. The effect on the partial area under (pAUC), the Free-Response Operating Characteristic (FROC) curve, and the structural similarity (SSIM) were compared as metrics for diagnostic and visual quality, respectively. DLDetect was validated with a reader concordance analysis. Statistical analysis included Wilcoxon, permutation, and Cohen's kappa tests for visual quality, diagnostic performance, and reader concordance.

RESULTS

DLRecon improved visual quality at 4- and 8-fold (R4, R8) subsampling rates, with SSIM (range: -1 to 1) improved to 0.78 ± 0.02 (p < 0.001) and 0.67 ± 0.03 (p < 0.001) from 0.68 ± 0.03 and 0.51 ± 0.03, respectively. However, diagnostic performance at R4 showed a pAUC FROC of 1.33 (CI 1.28-1.39) for DL and 1.29 (CI 1.23-1.35) for naive reconstructions, both significantly lower than fully sampled pAUC of 1.58 (DL: p = 0.024, naïve: p = 0.02). Similar trends were noted for R8.

CONCLUSION

DL reconstruction produces visually appealing images but may reduce diagnostic accuracy. Incorporating diagnostic AI into the assessment framework offers a clinically relevant metric essential for adopting reconstruction models into clinical practice.

CLINICAL RELEVANCE STATEMENT

In clinical settings, caution is warranted when using DL reconstruction for MRI scans. While it recovered visual quality, it failed to match the prostate cancer detection rates observed in scans not subjected to acceleration and DL reconstruction.

Deep plug-and-play MRI reconstruction based on multiple complementary priors

Magnetic resonance imaging (MRI) is widely used in clinical diagnosis as a safe, non-invasive, high-resolution medical imaging technology, but long scanning time has been a major challenge for this technology. The undersampling reconstruction method has become an important technical means to accelerate MRI by reducing the data sampling rate while maintaining high-quality imaging. However, traditional undersampling reconstruction techniques such as compressed sensing mainly rely on relatively single sparse or low-rank prior information to reconstruct the image, which has limitations in capturing the comprehensive features of images, resulting in the insufficient performance of the reconstructed image in terms of details and key information. In this paper, we propose a deep plug-and-play multiple complementary priors MRI reconstruction model, which combines traditional low-rank matrix recovery model methods and deep learning methods, and integrates global, local and nonlocal priors to improve reconstruction quality. Specifically, we capture the global features of the image through the matrix nuclear norm, and use the deep convolutional neural network denoiser Swin-Conv-UNet (SCUNet) and block-matching and 3-D filtering (BM3D) algorithm to preserve the local details and structural texture of the image, respectively. In addition, we utilize an efficient half-quadratic splitting (HQS) algorithm to solve the proposed model. The experimental results show that our proposed method has better reconstruction ability than the existing popular methods in terms of visual effects and numerical results.

DIRECTION: Deep cascaded reconstruction residual-based feature modulation network for fast MRI reconstruction

Deep cascaded networks have been extensively studied and applied to accelerate Magnetic Resonance Imaging (MRI) and have shown promising results. Most existing works employ a large cascading number for the sake of superior performances. However, due to the lack of proper guidance, the reconstruction performance can easily reach a plateau and even face degradation if simply increasing the cascading number. In this paper, we aim to boost the reconstruction performance from a novel perspective by proposing a parallel architecture called DIRECTION that fully exploits the guiding value of the reconstruction residual of each subnetwork. Specifically, we introduce a novel Reconstruction Residual-Based Feature Modulation Mechanism (RRFMM) which utilizes the reconstruction residual of the previous subnetwork to guide the next subnetwork at the feature level. To achieve this, a Residual Attention Modulation Block (RAMB) is proposed to generate attention maps using multi-scale residual features to modulate the image features of the corresponding scales. Equipped with this strategy, each subnetwork within the cascaded network possesses its unique optimization objective and emphasis rather than blindly updating its parameters. To further boost the performance, we introduce the Cross-Stage Feature Reuse Connection (CSFRC) and the Reconstruction Dense Connection (RDC), which can reduce information loss and enhance representative ability. We conduct sufficient experiments and evaluate our method on the fastMRI knee dataset using multiple subsampling masks. Comprehensive experimental results show that our method can markedly boost the performance of cascaded networks and significantly outperforms other compared state-of-the-art methods quantitatively and qualitatively.

Model-based federated learning for accurate MR image reconstruction from undersampled k-space data

Deep learning-based methods have achieved encouraging performances in the field of Magnetic Resonance (MR) image reconstruction. Nevertheless, building powerful and robust deep learning models requires collecting large and diverse datasets from multiple centers. This raises concerns about ethics and data privacy. Recently, federated learning has emerged as a promising solution, enabling the utilization of multi-center data without the need for data transfer between institutions. Despite its potential, existing federated learning methods face challenges due to the high heterogeneity of data from different centers. Aggregation methods based on simple averaging, which are commonly used to combine the client's information, have shown limited reconstruction and generalization capabilities. In this paper, we propose a Model-based Federated learning framework (ModFed) to address these challenges. ModFed has three major contributions: (1) Different from existing data-driven federated learning methods, ModFed designs attention-assisted model-based neural networks that can alleviate the need for large amounts of data on each client; (2) To address the data heterogeneity issue, ModFed proposes an adaptive dynamic aggregation scheme, which can improve the generalization capability and robustness of the trained neural network models; (3) ModFed incorporates a spatial Laplacian attention mechanism and a personalized client-side loss regularization to capture the detailed information for accurate image reconstruction. The effectiveness of the proposed ModFed is evaluated on three in-vivo datasets. Experimental results show that when compared to six existing state-of-the-art federated learning approaches, ModFed achieves better MR image reconstruction performance with increased generalization capability. Codes will be made available at https://github.com/ternencewu123/ModFed.

Knowledge-driven deep learning for fast MR imaging: Undersampled MR image reconstruction from supervised to un-supervised learning

Deep learning (DL) has emerged as a leading approach in accelerating MRI. It employs deep neural networks to extract knowledge from available datasets and then applies the trained networks to reconstruct accurate images from limited measurements. Unlike natural image restoration problems, MRI involves physics-based imaging processes, unique data properties, and diverse imaging tasks. This domain knowledge needs to be integrated with data-driven approaches. Our review will introduce the significant challenges faced by such knowledge-driven DL approaches in the context of fast MRI along with several notable solutions, which include learning neural networks and addressing different imaging application scenarios. The traits and trends of these techniques have also been given which have shifted from supervised learning to semi-supervised learning, and finally, to unsupervised learning methods. In addition, MR vendors' choices of DL reconstruction have been provided along with some discussions on open questions and future directions, which are critical for the reliable imaging systems.

Free-breathing MRI techniques for fat and R2* quantification in the liver

OBJECTIVE

To review the recent advancements in free-breathing MRI techniques for proton-density fat fraction (PDFF) and R2* quantification in the liver, and discuss the current challenges and future opportunities.

MATERIALS AND METHODS

This work focused on recent developments of different MRI pulse sequences, motion management strategies, and reconstruction approaches that enable free-breathing liver PDFF and R2* quantification.

RESULTS

Different free-breathing liver PDFF and R2* quantification techniques have been evaluated in various cohorts, including healthy volunteers and patients with liver diseases, both in adults and children. Initial results demonstrate promising performance with respect to reference measurements. These techniques have a high potential impact on providing a solution to the clinical need of accurate liver fat and iron quantification in populations with limited breath-holding capacity.

DISCUSSION

As these free-breathing techniques progress toward clinical translation, studies of the linearity, bias, and repeatability of free-breathing PDFF and R2* quantification in a larger cohort are important. Scan acceleration and improved motion management also hold potential for further enhancement.

Learning to deep learning: statistics and a paradigm test in selecting a UNet architecture to enhance MRI

OBJECTIVE

This study aims to assess the statistical significance of training parameters in 240 dense UNets (DUNets) used for enhancing low Signal-to-Noise Ratio (SNR) and undersampled MRI in various acquisition protocols. The objective is to determine the validity of differences between different DUNet configurations and their impact on image quality metrics.

MATERIALS AND METHODS

To achieve this, we trained all DUNets using the same learning rate and number of epochs, with variations in 5 acquisition protocols, 24 loss function weightings, and 2 ground truths. We calculated evaluation metrics for two metric regions of interest (ROI). We employed both Analysis of Variance (ANOVA) and Mixed Effects Model (MEM) to assess the statistical significance of the independent parameters, aiming to compare their efficacy in revealing differences and interactions among fixed parameters.

RESULTS

ANOVA analysis showed that, except for the acquisition protocol, fixed variables were statistically insignificant. In contrast, MEM analysis revealed that all fixed parameters and their interactions held statistical significance. This emphasizes the need for advanced statistical analysis in comparative studies, where MEM can uncover finer distinctions often overlooked by ANOVA.

DISCUSSION

These findings highlight the importance of utilizing appropriate statistical analysis when comparing different deep learning models. Additionally, the surprising effectiveness of the UNet architecture in enhancing various acquisition protocols underscores the potential for developing improved methods for characterizing and training deep learning models. This study serves as a stepping stone toward enhancing the transparency and comparability of deep learning techniques for medical imaging applications.

Dual-domain faster Fourier convolution based network for MR image reconstruction

Deep learning methods for fast MRI have shown promise in reconstructing high-quality images from undersampled multi-coil k-space data, leading to reduced scan duration. However, existing methods encounter challenges related to limited receptive fields in dual-domain (k-space and image domains) reconstruction networks, rigid data consistency operations, and suboptimal refinement structures, which collectively restrict overall reconstruction performance. This study introduces a comprehensive framework that addresses these challenges and enhances MR image reconstruction quality. Firstly, we propose Faster Inverse Fourier Convolution (FasterIFC), a frequency domain convolutional operator that significantly expands the receptive field of k-space domain reconstruction networks. Expanding the information extraction range to the entire frequency spectrum according to the spectral convolution theorem in Fourier theory enables the network to easily utilize richer redundant long-range information from adjacent, symmetrical, and diagonal locations of multi-coil k-space data. Secondly, we introduce a novel softer Data Consistency (softerDC) layer, which achieves an enhanced balance between data consistency and smoothness. This layer facilitates the implementation of diverse data consistency strategies across distinct frequency positions, addressing the inflexibility observed in current methods. Finally, we present the Dual-Domain Faster Fourier Convolution Based Network (D2F2), which features a centrosymmetric dual-domain parallel structure based on FasterIFC. This architecture optimally leverages dual-domain data characteristics while substantially expanding the receptive field in both domains. Coupled with the softerDC layer, D2F2 demonstrates superior performance on the NYU fastMRI dataset at multiple acceleration factors, surpassing state-of-the-art methods in both quantitative and qualitative evaluations.

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.

Predictive uncertainty in deep learning-based MR image reconstruction using deep ensembles: Evaluation on the fastMRI data set

PURPOSE

To estimate pixel-wise predictive uncertainty for deep learning-based MR image reconstruction and to examine the impact of domain shifts and architecture robustness.

METHODS

Uncertainty prediction could provide a measure for robustness of deep learning (DL)-based MR image reconstruction from undersampled data. DL methods bear the risk of inducing reconstruction errors like in-painting of unrealistic structures or missing pathologies. These errors may be obscured by visual realism of DL reconstruction and thus remain undiscovered. Furthermore, most methods are task-agnostic and not well calibrated to domain shifts. We propose a strategy that estimates aleatoric (data) and epistemic (model) uncertainty, which entails training a deep ensemble (epistemic) with nonnegative log-likelihood (aleatoric) loss in addition to the conventional applied losses terms. The proposed procedure can be paired with any DL reconstruction, enabling investigations of their predictive uncertainties on a pixel level. Five different architectures were investigated on the fastMRI database. The impact on the examined uncertainty of in-distributional and out-of-distributional data with changes to undersampling pattern, imaging contrast, imaging orientation, anatomy, and pathology were explored.

RESULTS

Predictive uncertainty could be captured and showed good correlation to normalized mean squared error. Uncertainty was primarily focused along the aliased anatomies and on hyperintense and hypointense regions. The proposed uncertainty measure was able to detect disease prevalence shifts. Distinct predictive uncertainty patterns were observed for changing network architectures.

CONCLUSION

The proposed approach enables aleatoric and epistemic uncertainty prediction for DL-based MR reconstruction with an interpretable examination on a pixel level.

Fourier Domain Robust Denoising Decomposition and Adaptive Patch MRI Reconstruction

The sparsity of the Fourier transform domain has been applied to magnetic resonance imaging (MRI) reconstruction in k -space. Although unsupervised adaptive patch optimization methods have shown promise compared to data-driven-based supervised methods, the following challenges exist in MRI reconstruction: 1) in previous k -space MRI reconstruction tasks, MRI with noise interference in the acquisition process is rarely considered. 2) Differences in transform domains should be resolved to achieve the high-quality reconstruction of low undersampled MRI data. 3) Robust patch dictionary learning problems are usually nonconvex and NP-hard, and alternate minimization methods are often computationally expensive. In this article, we propose a method for Fourier domain robust denoising decomposition and adaptive patch MRI reconstruction (DDAPR). DDAPR is a two-step optimization method for MRI reconstruction in the presence of noise and low undersampled data. It includes the low-rank and sparse denoising reconstruction model (LSDRM) and the robust dictionary learning reconstruction model (RDLRM). In the first step, we propose LSDRM for different domains. For the optimization solution, the proximal gradient method is used to optimize LSDRM by singular value decomposition and soft threshold algorithms. In the second step, we propose RDLRM, which is an effective adaptive patch method by introducing a low-rank and sparse penalty adaptive patch dictionary and using a sparse rank-one matrix to approximate the undersampled data. Then, the block coordinate descent (BCD) method is used to optimize the variables. The BCD optimization process involves valid closed-form solutions. Extensive numerical experiments show that the proposed method has a better performance than previous methods in image reconstruction based on compressed sensing or deep learning.

JUST-Net: Jointly unrolled cross-domain optimization based spatio-temporal reconstruction network for accelerated 3D myelin water imaging

PURPOSE

We introduced a novel reconstruction network, jointly unrolled cross-domain optimization-based spatio-temporal reconstruction network (JUST-Net), aimed at accelerating 3D multi-echo gradient-echo (mGRE) data acquisition and improving the quality of resulting myelin water imaging (MWI) maps.

METHOD

An unrolled cross-domain spatio-temporal reconstruction network was designed. The main idea is to combine frequency and spatio-temporal image feature representations and to sequentially implement convolution layers in both domains. The k-space subnetwork utilizes shared information from adjacent frames, whereas the image subnetwork applies separate convolutions in both spatial and temporal dimensions. The proposed reconstruction network was evaluated for both retrospectively and prospectively accelerated acquisition. Furthermore, it was assessed in simulation studies and real-world cases with k-space corruptions to evaluate its potential for motion artifact reduction.

RESULTS

The proposed JUST-Net enabled highly reproducible and accelerated 3D mGRE acquisition for whole-brain MWI, reducing the acquisition time from fully sampled 15:23 to 2:22 min within a 3-min reconstruction time. The normalized root mean squared error of the reconstructed mGRE images increased by less than 4.0%, and the correlation coefficients for MWI showed a value of over 0.68 when compared to the fully sampled reference. Additionally, the proposed method demonstrated a mitigating effect on both simulated and clinical motion-corrupted cases.

CONCLUSION

The proposed JUST-Net has demonstrated the capability to achieve high acceleration factors for 3D mGRE-based MWI, which is expected to facilitate widespread clinical applications of MWI.

A noise robust image reconstruction using slice aware cycle interpolator network for parallel imaging in MRI

BACKGROUND

Reducing Magnetic resonance imaging (MRI) scan time has been an important issue for clinical applications. In order to reduce MRI scan time, imaging acceleration was made possible by undersampling k-space data. This is achieved by leveraging additional spatial information from multiple, independent receiver coils, thereby reducing the number of sampled k-space lines.

PURPOSE

The aim of this study is to develop a deep-learning method for parallel imaging with a reduced number of auto-calibration signals (ACS) lines in noisy environments.

METHODS

A cycle interpolator network is developed for robust reconstruction of parallel MRI with a small number of ACS lines in noisy environments. The network estimates missing (unsampled) lines of each coil data, and these estimated missing lines are then utilized to re-estimate the sampled k-space lines. In addition, a slice aware reconstruction technique is developed for noise-robust reconstruction while reducing the number of ACS lines. We conducted an evaluation study using retrospectively subsampled data obtained from three healthy volunteers at 3T MRI, involving three different slice thicknesses (1.5, 3.0, and 4.5 mm) and three different image contrasts (T1w, T2w, and FLAIR).

RESULTS

Despite the challenges posed by substantial noise in cases with a limited number of ACS lines and thinner slices, the slice aware cycle interpolator network reconstructs the enhanced parallel images. It outperforms RAKI, effectively eliminating aliasing artifacts. Moreover, the proposed network outperforms GRAPPA and demonstrates the ability to successfully reconstruct brain images even under severe noisy conditions.

CONCLUSIONS

The slice aware cycle interpolator network has the potential to improve reconstruction accuracy for a reduced number of ACS lines in noisy environments.

Compensating unknown speed of sound in learned fast 3D limited-view photoacoustic tomography

Real-time applications in three-dimensional photoacoustic tomography from planar sensors rely on fast reconstruction algorithms that assume the speed of sound (SoS) in the tissue is homogeneous. Moreover, the reconstruction quality depends on the correct choice for the constant SoS. In this study, we discuss the possibility of ameliorating the problem of unknown or heterogeneous SoS distributions by using learned reconstruction methods. This can be done by modelling the uncertainties in the training data. In addition, a correction term can be included in the learned reconstruction method. We investigate the influence of both and while a learned correction component can improve reconstruction quality further, we show that a careful choice of uncertainties in the training data is the primary factor to overcome unknown SoS. We support our findings with simulated and in vivo measurements in 3D.

Deep Fuzzy Min-Max Neural Network: Analysis and Design

Fuzzy min-max neural network (FMNN) is one kind of three-layer models based on hyperboxes that are constructed in a sequential way. Such a sequential mechanism inevitably leads to the input order and overlap region problem. In this study, we propose a deep FMNN (DFMNN) based on initialization and optimization operation to overcome these limitations. Initialization operation that can solve the input order problem is to design hyperboxes in a simultaneous way, and side parameters have been proposed to control the size of hyperboxes. Optimization operation that can eliminate overlap region problem is realized by means of deep layers, where the number of layers is immediately determined when the overlap among hyperboxes is eliminated. In the optimization process, each layer consists of three sections, namely, the partition section, combination section, and union section. The partition section aims to divide the hyperboxes into a nonoverlapping hyperbox set and an overlapping hyperbox set. The combination section eliminates the overlap problem of overlapping hyperbox set. The union section obtains the optimized hyperbox set in the current layer. DFMNN is evaluated based on a series of benchmark datasets. A comparative analysis illustrates that the proposed DFMNN model outperforms several models previously reported in the literature.

A cross-domain complex convolution neural network for undersampled magnetic resonance image reconstruction

To introduce a new cross-domain complex convolution neural network for accurate MR image reconstruction from undersampled k-space data. Most reconstruction methods utilize neural networks or cascade neural networks in either the image domain and/or the k-space domain. However, these methods encounter several challenges: 1) Applying neural networks directly in the k-space domain is suboptimal for feature extraction; 2) Classic image-domain networks have difficulty in fully extracting texture features; and 3) Existing cross-domain methods still face challenges in extracting and fusing features from both image and k-space domains simultaneously. In this work, we propose a novel deep-learning-based 2-D single-coil complex-valued MR reconstruction network termed TEID-Net. TEID-Net integrates three modules: 1) TE-Net, an image-domain-based sub-network designed to enhance contrast in input features by incorporating a Texture Enhancement Module; 2) ID-Net, an intermediate-domain sub-network tailored to operate in the image-Fourier space, with the specific goal of reducing aliasing artifacts realized by leveraging the superior incoherence property of the decoupled one-dimensional signals; and 3) TEID-Net, a cross-domain reconstruction network in which ID-Nets and TE-Nets are combined and cascaded to boost the quality of image reconstruction further. Extensive experiments have been conducted on the fastMRI and Calgary-Campinas datasets. Results demonstrate the effectiveness of the proposed TEID-Net in mitigating undersampling-induced artifacts and producing high-quality image reconstructions, outperforming several state-of-the-art methods while utilizing fewer network parameters. The cross-domain TEID-Net excels in restoring tissue structures and intricate texture details. The results illustrate that TEID-Net is particularly well-suited for regular Cartesian undersampling scenarios.

Encoding Enhanced Complex CNN for Accurate and Highly Accelerated MRI

Magnetic resonance imaging (MRI) using hyperpolarized noble gases provides a way to visualize the structure and function of human lung, but the long imaging time limits its broad research and clinical applications. Deep learning has demonstrated great potential for accelerating MRI by reconstructing images from undersampled data. However, most existing deep convolutional neural networks (CNN) directly apply square convolution to k-space data without considering the inherent properties of k-space sampling, limiting k-space learning efficiency and image reconstruction quality. In this work, we propose an encoding enhanced (EN2) complex CNN for highly undersampled pulmonary MRI reconstruction. EN2 complex CNN employs convolution along either the frequency or phase-encoding direction, resembling the mechanisms of k-space sampling, to maximize the utilization of the encoding correlation and integrity within a row or column of k-space. We also employ complex convolution to learn rich representations from the complex k-space data. In addition, we develop a feature-strengthened modularized unit to further boost the reconstruction performance. Experiments demonstrate that our approach can accurately reconstruct hyperpolarized 129Xe and 1H lung MRI from 6-fold undersampled k-space data and provide lung function measurements with minimal biases compared with fully sampled images. These results demonstrate the effectiveness of the proposed algorithmic components and indicate that the proposed approach could be used for accelerated pulmonary MRI in research and clinical lung disease patient care.

Image Reconstruction for Accelerated MR Scan With Faster Fourier Convolutional Neural Networks

High quality image reconstruction from undersampled k -space data is key to accelerating MR scanning. Current deep learning methods are limited by the small receptive fields in reconstruction networks, which restrict the exploitation of long-range information, and impede the mitigation of full-image artifacts, particularly in 3D reconstruction tasks. Additionally, the substantial computational demands of 3D reconstruction considerably hinder advancements in related fields. To tackle these challenges, we propose the following: 1) A novel convolution operator named Faster Fourier Convolution (FasterFC), aims at providing an adaptable broad receptive field for spatial domain reconstruction networks with fast computational speed. 2) A split-slice strategy that substantially reduces the computational load of 3D reconstruction, enabling high-resolution, multi-coil, 3D MR image reconstruction while fully utilizing inter-layer and intra-layer information. 3) A single-to-group algorithm that efficiently utilizes scan-specific and data-driven priors to enhance k -space interpolation effects. 4) A multi-stage, multi-coil, 3D fast MRI method, called the faster Fourier convolution based single-to-group network (FAS-Net), comprising a single-to-group k -space interpolation algorithm and a FasterFC-based image domain reconstruction module, significantly minimizes the computational demands of 3D reconstruction through split-slice strategy. Experimental evaluations conducted on the NYU fastMRI and Stanford MRI Data datasets reveal that the FasterFC significantly enhances the quality of both 2D and 3D reconstruction results. Moreover, FAS-Net, characterized as a method that can achieve high-resolution (320, 320, 256), multi-coil, (8 coils), 3D fast MRI, exhibits superior reconstruction performance compared to other state-of-the-art 2D and 3D methods.

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.

A Deep Learning-Based Integrated Framework for Quality-Aware Undersampled Cine Cardiac MRI Reconstruction and Analysis

Cine cardiac magnetic resonance (CMR) imaging is considered the gold standard for cardiac function evaluation. However, cine CMR acquisition is inherently slow and in recent decades considerable effort has been put into accelerating scan times without compromising image quality or the accuracy of derived results. In this article, we present a fully-automated, quality-controlled integrated framework for reconstruction, segmentation and downstream analysis of undersampled cine CMR data. The framework produces high quality reconstructions and segmentations, leading to undersampling factors that are optimised on a scan-by-scan basis. This results in reduced scan times and automated analysis, enabling robust and accurate estimation of functional biomarkers. To demonstrate the feasibility of the proposed approach, we perform simulations of radial k-space acquisitions using in-vivo cine CMR data from 270 subjects from the UK Biobank (with synthetic phase) and in-vivo cine CMR data from 16 healthy subjects (with real phase). The results demonstrate that the optimal undersampling factor varies for different subjects by approximately 1 to 2 seconds per slice. We show that our method can produce quality-controlled images in a mean scan time reduced from 12 to 4 seconds per slice, and that image quality is sufficient to allow clinically relevant parameters to be automatically estimated to lie within 5% mean absolute difference.

Motion Artifact Reduction Using U-Net Model with Three-Dimensional Simulation-Based Datasets for Brain Magnetic Resonance Images

This study aimed to remove motion artifacts from brain magnetic resonance (MR) images using a U-Net model. In addition, a simulation method was proposed to increase the size of the dataset required to train the U-Net model while avoiding the overfitting problem. The volume data were rotated and translated with random intensity and frequency, in three dimensions, and were iterated as the number of slices in the volume data. Then, for every slice, a portion of the motion-free k-space data was replaced with motion k-space data, respectively. In addition, based on the transposed k-space data, we acquired MR images with motion artifacts and residual maps and constructed datasets. For a quantitative evaluation, the root mean square error (RMSE), peak signal-to-noise ratio (PSNR), coefficient of correlation (CC), and universal image quality index (UQI) were measured. The U-Net models for motion artifact reduction with the residual map-based dataset showed the best performance across all evaluation factors. In particular, the RMSE, PSNR, CC, and UQI improved by approximately 5.35×, 1.51×, 1.12×, and 1.01×, respectively, and the U-Net model with the residual map-based dataset was compared with the direct images. In conclusion, our simulation-based dataset demonstrates that U-Net models can be effectively trained for motion artifact reduction.

A Systematic Review and Identification of the Challenges of Deep Learning Techniques for Undersampled Magnetic Resonance Image Reconstruction

Deep learning (DL) in magnetic resonance imaging (MRI) shows excellent performance in image reconstruction from undersampled k-space data. Artifact-free and high-quality MRI reconstruction is essential for ensuring accurate diagnosis, supporting clinical decision-making, enhancing patient safety, facilitating efficient workflows, and contributing to the validity of research studies and clinical trials. Recently, deep learning has demonstrated several advantages over conventional MRI reconstruction methods. Conventional methods rely on manual feature engineering to capture complex patterns and are usually computationally demanding due to their iterative nature. Conversely, DL methods use neural networks with hundreds of thousands of parameters and automatically learn relevant features and representations directly from the data. Nevertheless, there are some limitations to DL-based techniques concerning MRI reconstruction tasks, such as the need for large, labeled datasets, the possibility of overfitting, and the complexity of model training. Researchers are striving to develop DL models that are more efficient, adaptable, and capable of providing valuable information for medical practitioners. We provide a comprehensive overview of the current developments and clinical uses by focusing on state-of-the-art DL architectures and tools used in MRI reconstruction. This study has three objectives. Our main objective is to describe how various DL designs have changed over time and talk about cutting-edge tactics, including their advantages and disadvantages. Hence, data pre- and post-processing approaches are assessed using publicly available MRI datasets and source codes. Secondly, this work aims to provide an extensive overview of the ongoing research on transformers and deep convolutional neural networks for rapid MRI reconstruction. Thirdly, we discuss several network training strategies, like supervised, unsupervised, transfer learning, and federated learning for rapid and efficient MRI reconstruction. Consequently, this article provides significant resources for future improvement of MRI data pre-processing and fast image reconstruction.

Parallel-stream fusion of scan-specific and scan-general priors for learning deep MRI reconstruction in low-data regimes

Magnetic resonance imaging (MRI) is an essential diagnostic tool that suffers from prolonged scan times. Reconstruction methods can alleviate this limitation by recovering clinically usable images from accelerated acquisitions. In particular, learning-based methods promise performance leaps by employing deep neural networks as data-driven priors. A powerful approach uses scan-specific (SS) priors that leverage information regarding the underlying physical signal model for reconstruction. SS priors are learned on each individual test scan without the need for a training dataset, albeit they suffer from computationally burdening inference with nonlinear networks. An alternative approach uses scan-general (SG) priors that instead leverage information regarding the latent features of MRI images for reconstruction. SG priors are frozen at test time for efficiency, albeit they require learning from a large training dataset. Here, we introduce a novel parallel-stream fusion model (PSFNet) that synergistically fuses SS and SG priors for performant MRI reconstruction in low-data regimes, while maintaining competitive inference times to SG methods. PSFNet implements its SG prior based on a nonlinear network, yet it forms its SS prior based on a linear network to maintain efficiency. A pervasive framework for combining multiple priors in MRI reconstruction is algorithmic unrolling that uses serially alternated projections, causing error propagation under low-data regimes. To alleviate error propagation, PSFNet combines its SS and SG priors via a novel parallel-stream architecture with learnable fusion parameters. Demonstrations are performed on multi-coil brain MRI for varying amounts of training data. PSFNet outperforms SG methods in low-data regimes, and surpasses SS methods with few tens of training samples. On average across tasks, PSFNet achieves 3.1 dB higher PSNR, 2.8% higher SSIM, and 0.3 × lower RMSE than baselines. Furthermore, in both supervised and unsupervised setups, PSFNet requires an order of magnitude lower samples compared to SG methods, and enables an order of magnitude faster inference compared to SS methods. Thus, the proposed model improves deep MRI reconstruction with elevated learning and computational efficiency.

DC-SiamNet: Deep contrastive Siamese network for self-supervised MRI reconstruction

Reconstruction methods based on deep learning have greatly shortened the data acquisition time of magnetic resonance imaging (MRI). However, these methods typically utilize massive fully sampled data for supervised training, restricting their application in certain clinical scenarios and posing challenges to the reconstruction effect when high-quality MR images are unavailable. Recently, self-supervised methods have been developed that only undersampled MRI images participate in the network training. Nevertheless, due to the lack of complete referable MR image data, self-supervised reconstruction is prone to produce incorrect structure contents, such as unnatural texture details and over-smoothed tissue sites. To solve this problem, we propose a self-supervised Deep Contrastive Siamese Network (DC-SiamNet) for fast MR imaging. First, DC-SiamNet performs the reconstruction with a Siamese unrolled structure and obtains visual representations in different iterative phases. Particularly, an attention-weighted average pooling module is employed at the bottleneck layer of the U-shape regularization unit, which can effectively aggregate valuable local information of the underlying feature map in the generated representation vector. Then, a novel hybrid loss function is designed to drive the self-supervised reconstruction and contrastive learning simultaneously by forcing the output consistency across different branches in the frequency domain, the image domain, and the latent space. The proposed method is extensively evaluated with different sampling patterns on the IXI brain dataset and the MRINet knee dataset. Experimental results show that DC-SiamNet can achieve 0.93 in structural similarity and 33.984 dB in peak signal-to-noise ratio on the IXI brain dataset under 8x acceleration. It has better reconstruction accuracy than other methods, and the performance is close to the corresponding model trained with full supervision, especially when the sampling rate is low. In addition, generalization experiments verify that our method has a strong cross-domain reconstruction ability for different contrast brain images.

Value Proposition of FDA-Approved Artificial Intelligence Algorithms for Neuroimaging

PURPOSE

The number of FDA-cleared artificial intelligence (AI) algorithms for neuroimaging has grown in the past decade. The adoption of these algorithms into clinical practice depends largely on whether this technology provides value in the clinical setting. The objective of this study was to analyze trends in FDA-cleared AI algorithms for neuroimaging and understand their value proposition as advertised by the AI developers and vendors.

METHODS

A list of AI algorithms cleared by the FDA for neuroimaging between May 2008 and August 2022 was extracted from the ACR Data Science Institute AI Central database. Product information for each device was collected from the database. For each device, information on the advertised value as presented on the developer's website was collected.

RESULTS

A total of 59 AI neuroimaging algorithms were cleared by the FDA between May 2008 and August 2022. Most of these algorithms (24 of 59) were compatible with noncontrast CT, 21 with MRI, 9 with CT perfusion, 8 with CT angiography, 3 with MR perfusion, and 2 with PET. Six algorithms were compatible with multiple imaging techniques. Of the 59 algorithms, websites were located that discussed the product value for 55 algorithms. The most widely advertised value proposition was improved quality of care (38 of 55 [69.1%]). A total of 24 algorithms (43.6%) proposed saving user time, 9 (15.7%) advertised decreased costs, and 6 (10.9%) described increased revenue. Product websites for 26 algorithms (43.6%) showed user testimonials advertising the value of the technology.

CONCLUSIONS

The results of this study indicate a wide range of value propositions advertised by developers and vendors of AI algorithms for neuroimaging. Most vendors advertised that their products would improve patient care. Further research is necessary to determine whether the value claimed by developers is actually demonstrated in clinical practice.

Trends and hotspots in research on medical images with deep learning: a bibliometric analysis from 2013 to 2023

Background

With the rapid development of the internet, the improvement of computer capabilities, and the continuous advancement of algorithms, deep learning has developed rapidly in recent years and has been widely applied in many fields. Previous studies have shown that deep learning has an excellent performance in image processing, and deep learning-based medical image processing may help solve the difficulties faced by traditional medical image processing. This technology has attracted the attention of many scholars in the fields of computer science and medicine. This study mainly summarizes the knowledge structure of deep learning-based medical image processing research through bibliometric analysis and explores the research hotspots and possible development trends in this field.

Methods

Retrieve the Web of Science Core Collection database using the search terms "deep learning," "medical image processing," and their synonyms. Use CiteSpace for visual analysis of authors, institutions, countries, keywords, co-cited references, co-cited authors, and co-cited journals.

Results

The analysis was conducted on 562 highly cited papers retrieved from the database. The trend chart of the annual publication volume shows an upward trend. Pheng-Ann Heng, Hao Chen, and Klaus Hermann Maier-Hein are among the active authors in this field. Chinese Academy of Sciences has the highest number of publications, while the institution with the highest centrality is Stanford University. The United States has the highest number of publications, followed by China. The most frequent keyword is "Deep Learning," and the highest centrality keyword is "Algorithm." The most cited author is Kaiming He, and the author with the highest centrality is Yoshua Bengio.

Conclusion

The application of deep learning in medical image processing is becoming increasingly common, and there are many active authors, institutions, and countries in this field. Current research in medical image processing mainly focuses on deep learning, convolutional neural networks, classification, diagnosis, segmentation, image, algorithm, and artificial intelligence. The research focus and trends are gradually shifting toward more complex and systematic directions, and deep learning technology will continue to play an important role.

Global attention-enabled texture enhancement network for MR image reconstruction

PURPOSE

Although recent convolutional neural network (CNN) methodologies have shown promising results in fast MR imaging, there is still a desire to explore how they can be used to learn the frequency characteristics of multicontrast images and reconstruct texture details.

METHODS

A global attention-enabled texture enhancement network (GATE-Net) with a frequency-dependent feature extraction module (FDFEM) and convolution-based global attention module (GAM) is proposed to address the highly under-sampling MR image reconstruction problem. First, FDFEM enables GATE-Net to effectively extract high-frequency features from shareable information of multicontrast images to improve the texture details of reconstructed images. Second, GAM with less computation complexity has the receptive field of the entire image, which can fully explore useful shareable information of multi-contrast images and suppress less beneficial shareable information.

RESULTS

The ablation studies are conducted to evaluate the effectiveness of the proposed FDFEM and GAM. Experimental results under various acceleration rates and datasets consistently demonstrate the superiority of GATE-Net, in terms of peak signal-to-noise ratio, structural similarity and normalized mean square error.

CONCLUSION

A global attention-enabled texture enhancement network is proposed. it can be applied to multicontrast MR image reconstruction tasks with different acceleration rates and datasets and achieves superior performance in comparison with state-of-the-art methods.

Frequency Learning via Multi-Scale Fourier Transformer for MRI Reconstruction

Since Magnetic Resonance Imaging (MRI) requires a long acquisition time, various methods were proposed to reduce the time, but they ignored the frequency information and non-local similarity, so that they failed to reconstruct images with a clear structure. In this article, we propose Frequency Learning via Multi-scale Fourier Transformer for MRI Reconstruction (FMTNet), which focuses on repairing the low-frequency and high-frequency information. Specifically, FMTNet is composed of a high-frequency learning branch (HFLB) and a low-frequency learning branch (LFLB). Meanwhile, we propose a Multi-scale Fourier Transformer (MFT) as the basic module to learn the non-local information. Unlike normal Transformers, MFT adopts Fourier convolution to replace self-attention to efficiently learn global information. Moreover, we further introduce a multi-scale learning and cross-scale linear fusion strategy in MFT to interact information between features of different scales and strengthen the representation of features. Compared with normal Transformers, the proposed MFT occupies fewer computing resources. Based on MFT, we design a Residual Multi-scale Fourier Transformer module as the main component of HFLB and LFLB. We conduct several experiments under different acceleration rates and different sampling patterns on different datasets, and the experiment results show that our method is superior to the previous state-of-the-art method.

Joint Image Reconstruction and Super-Resolution for Accelerated Magnetic Resonance Imaging

Magnetic resonance (MR) image reconstruction and super-resolution are two prominent techniques to restore high-quality images from undersampled or low-resolution k-space data to accelerate MR imaging. Combining undersampled and low-resolution acquisition can further improve the acceleration factor. Existing methods often treat the techniques of image reconstruction and super-resolution separately or combine them sequentially for image recovery, which can result in error propagation and suboptimal results. In this work, we propose a novel framework for joint image reconstruction and super-resolution, aiming to efficiently image recovery and enable fast imaging. Specifically, we designed a framework with a reconstruction module and a super-resolution module to formulate multi-task learning. The reconstruction module utilizes a model-based optimization approach, ensuring data fidelity with the acquired k-space data. Moreover, a deep spatial feature transform is employed to enhance the information transition between the two modules, facilitating better integration of image reconstruction and super-resolution. Experimental evaluations on two datasets demonstrate that our proposed method can provide superior performance both quantitatively and qualitatively.

PARCEL: Physics-Based Unsupervised Contrastive Representation Learning for Multi-Coil MR Imaging

With the successful application of deep learning to magnetic resonance (MR) imaging, parallel imaging techniques based on neural networks have attracted wide attention. However, in the absence of high-quality, fully sampled datasets for training, the performance of these methods is limited. And the interpretability of models is not strong enough. To tackle this issue, this paper proposes a Physics-bAsed unsupeRvised Contrastive rEpresentation Learning (PARCEL) method to speed up parallel MR imaging. Specifically, PARCEL has a parallel framework to contrastively learn two branches of model-based unrolling networks from augmented undersampled multi-coil k-space data. A sophisticated co-training loss with three essential components has been designed to guide the two networks in capturing the inherent features and representations for MR images. And the final MR image is reconstructed with the trained contrastive networks. PARCEL was evaluated on two vivo datasets and compared to five state-of-the-art methods. The results show that PARCEL is able to learn essential representations for accurate MR reconstruction without relying on fully sampled datasets. The code will be made available at https://github.com/ternencewu123/PARCEL.

Emerging Trends in Fast MRI Using Deep-Learning Reconstruction on Undersampled k-Space Data: A Systematic Review

Magnetic Resonance Imaging (MRI) is an essential medical imaging modality that provides excellent soft-tissue contrast and high-resolution images of the human body, allowing us to understand detailed information on morphology, structural integrity, and physiologic processes. However, MRI exams usually require lengthy acquisition times. Methods such as parallel MRI and Compressive Sensing (CS) have significantly reduced the MRI acquisition time by acquiring less data through undersampling k-space. The state-of-the-art of fast MRI has recently been redefined by integrating Deep Learning (DL) models with these undersampled approaches. This Systematic Literature Review (SLR) comprehensively analyzes deep MRI reconstruction models, emphasizing the key elements of recently proposed methods and highlighting their strengths and weaknesses. This SLR involves searching and selecting relevant studies from various databases, including Web of Science and Scopus, followed by a rigorous screening and data extraction process using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. It focuses on various techniques, such as residual learning, image representation using encoders and decoders, data-consistency layers, unrolled networks, learned activations, attention modules, plug-and-play priors, diffusion models, and Bayesian methods. This SLR also discusses the use of loss functions and training with adversarial networks to enhance deep MRI reconstruction methods. Moreover, we explore various MRI reconstruction applications, including non-Cartesian reconstruction, super-resolution, dynamic MRI, joint learning of reconstruction with coil sensitivity and sampling, quantitative mapping, and MR fingerprinting. This paper also addresses research questions, provides insights for future directions, and emphasizes robust generalization and artifact handling. Therefore, this SLR serves as a valuable resource for advancing fast MRI, guiding research and development efforts of MRI reconstruction for better image quality and faster data acquisition.

Deep-Learning-Enabled Microwave-Induced Thermoacoustic Tomography Based on ResAttU-Net for Transcranial Brain Hemorrhage Detection

OBJECTIVE

Hemorrhagic stroke is a leading threat to human's health. The fast-developing microwave-induced thermoacoustic tomography (MITAT) technique holds potential to do brain imaging. However, transcranial brain imaging based on MITAT is still challenging due to the involved huge heterogeneity in speed of sound and acoustic attenuation of human skull. This work aims to address the adverse effect of the acoustic heterogeneity using a deep-learning-based MITAT (DL-MITAT) approach for transcranial brain hemorrhage detection.

METHODS

We establish a new network structure, a residual attention U-Net (ResAttU-Net), for the proposed DL-MITAT technique, which exhibits improved performance as compared to some traditionally used networks. We use simulation method to build training sets and take images obtained by traditional imaging algorithms as the input of the network.

RESULTS

We present ex-vivo transcranial brain hemorrhage detection as a proof-of-concept validation. By using an 8.1-mm thick bovine skull and porcine brain tissues to perform ex-vivo experiments, we demonstrate that the trained ResAttU-Net is capable of efficiently eliminating image artifacts and accurately restoring the hemorrhage spot. It is proved that the DL-MITAT method can reliably suppress false positive rate and detect a hemorrhage spot as small as 3 mm. We also study effects of several factors of the DL-MITAT technique to further reveal its robustness and limitations.

CONCLUSION

The proposed ResAttU-Net-based DL-MITAT method is promising for mitigating the acoustic inhomogeneity issue and performing transcranial brain hemorrhage detection.

SIGNIFICANCE

This work provides a novel ResAttU-Net-based DL-MITAT paradigm and paves a compelling route for transcranial brain hemorrhage detection as well as other transcranial brain imaging applications.

Accelerating High b-Value Diffusion-Weighted MRI Using a Convolutional Recurrent Neural Network (CRNN-DWI)

PURPOSE

To develop a novel convolutional recurrent neural network (CRNN-DWI) and apply it to reconstruct a highly undersampled (up to six-fold) multi-b-value, multi-direction diffusion-weighted imaging (DWI) dataset.

METHODS

A deep neural network that combines a convolutional neural network (CNN) and recurrent neural network (RNN) was first developed by using a set of diffusion images as input. The network was then used to reconstruct a DWI dataset consisting of 14 b-values, each with three diffusion directions. For comparison, the dataset was also reconstructed with zero-padding and 3D-CNN. The experiments were performed with undersampling rates (R) of 4 and 6. Standard image quality metrics (SSIM and PSNR) were employed to provide quantitative assessments of the reconstructed image quality. Additionally, an advanced non-Gaussian diffusion model was employed to fit the reconstructed images from the different approaches, thereby generating a set of diffusion parameter maps. These diffusion parameter maps from the different approaches were then compared using SSIM as a metric.

RESULTS

Both the reconstructed diffusion images and diffusion parameter maps from CRNN-DWI were better than those from zero-padding or 3D-CNN. Specifically, the average SSIM and PSNR of CRNN-DWI were 0.750 ± 0.016 and 28.32 ± 0.69 (R = 4), and 0.675 ± 0.023 and 24.16 ± 0.77 (R = 6), respectively, both of which were substantially higher than those of zero-padding or 3D-CNN reconstructions. The diffusion parameter maps from CRNN-DWI also yielded higher SSIM values for R = 4 (>0.8) and for R = 6 (>0.7) than the other two approaches (for R = 4, <0.7, and for R = 6, <0.65).

CONCLUSIONS

CRNN-DWI is a viable approach for reconstructing highly undersampled DWI data, providing opportunities to reduce the data acquisition burden.

Linear fine-tuning: a linear transformation based transfer strategy for deep MRI reconstruction

Introduction

Fine-tuning (FT) is a generally adopted transfer learning method for deep learning-based magnetic resonance imaging (MRI) reconstruction. In this approach, the reconstruction model is initialized with pre-trained weights derived from a source domain with ample data and subsequently updated with limited data from the target domain. However, the direct full-weight update strategy can pose the risk of "catastrophic forgetting" and overfitting, hindering its effectiveness. The goal of this study is to develop a zero-weight update transfer strategy to preserve pre-trained generic knowledge and reduce overfitting.

Methods

Based on the commonality between the source and target domains, we assume a linear transformation relationship of the optimal model weights from the source domain to the target domain. Accordingly, we propose a novel transfer strategy, linear fine-tuning (LFT), which introduces scaling and shifting (SS) factors into the pre-trained model. In contrast to FT, LFT only updates SS factors in the transfer phase, while the pre-trained weights remain fixed.

Results

To evaluate the proposed LFT, we designed three different transfer scenarios and conducted a comparative analysis of FT, LFT, and other methods at various sampling rates and data volumes. In the transfer scenario between different contrasts, LFT outperforms typical transfer strategies at various sampling rates and considerably reduces artifacts on reconstructed images. In transfer scenarios between different slice directions or anatomical structures, LFT surpasses the FT method, particularly when the target domain contains a decreasing number of training images, with a maximum improvement of up to 2.06 dB (5.89%) in peak signal-to-noise ratio.

Discussion

The LFT strategy shows great potential to address the issues of "catastrophic forgetting" and overfitting in transfer scenarios for MRI reconstruction, while reducing the reliance on the amount of data in the target domain. Linear fine-tuning is expected to shorten the development cycle of reconstruction models for adapting complicated clinical scenarios, thereby enhancing the clinical applicability of deep MRI reconstruction.

Adaptive diffusion priors for accelerated MRI reconstruction

Deep MRI reconstruction is commonly performed with conditional models that de-alias undersampled acquisitions to recover images consistent with fully-sampled data. Since conditional models are trained with knowledge of the imaging operator, they can show poor generalization across variable operators. Unconditional models instead learn generative image priors decoupled from the operator to improve reliability against domain shifts related to the imaging operator. Recent diffusion models are particularly promising given their high sample fidelity. Nevertheless, inference with a static image prior can perform suboptimally. Here we propose the first adaptive diffusion prior for MRI reconstruction, AdaDiff, to improve performance and reliability against domain shifts. AdaDiff leverages an efficient diffusion prior trained via adversarial mapping over large reverse diffusion steps. A two-phase reconstruction is executed following training: a rapid-diffusion phase that produces an initial reconstruction with the trained prior, and an adaptation phase that further refines the result by updating the prior to minimize data-consistency loss. Demonstrations on multi-contrast brain MRI clearly indicate that AdaDiff outperforms competing conditional and unconditional methods under domain shifts, and achieves superior or on par within-domain performance.

Improving accelerated MRI by deep learning with sparsified complex data

PURPOSE

To obtain high-quality accelerated MR images with complex-valued reconstruction from undersampled k-space data.

METHODS

The MRI scans from human subjects were retrospectively undersampled with a regular pattern using skipped phase encoding, leading to ghosts in zero-filling reconstruction. A complex difference transform along the phase-encoding direction was applied in image domain to yield sparsified complex-valued edge maps. These sparse edge maps were used to train a complex-valued U-type convolutional neural network (SCU-Net) for deghosting. A k-space inverse filtering was performed on the predicted deghosted complex edge maps from SCU-Net to obtain final complex images. The SCU-Net was compared with other algorithms including zero-filling, GRAPPA, RAKI, finite difference complex U-type convolutional neural network (FDCU-Net), and CU-Net, both qualitatively and quantitatively, using such metrics as structural similarity index, peak SNR, and normalized mean square error.

RESULTS

The SCU-Net was found to be effective in deghosting aliased edge maps even at high acceleration factors. High-quality complex images were obtained by performing an inverse filtering on deghosted edge maps. The SCU-Net compared favorably with other algorithms.

CONCLUSION

Using sparsified complex data, SCU-Net offers higher reconstruction quality for regularly undersampled k-space data. The proposed method is especially useful for phase-sensitive MRI applications.

Uncertainty-aware physics-driven deep learning network for free-breathing liver fat and R2 * quantification using self-gated stack-of-radial MRI

PURPOSE

To develop a deep learning-based method for rapid liver proton-density fat fraction (PDFF) and R2 * quantification with built-in uncertainty estimation using self-gated free-breathing stack-of-radial MRI.

METHODS

This work developed an uncertainty-aware physics-driven deep learning network (UP-Net) to (1) suppress radial streaking artifacts because of undersampling after self-gating, (2) calculate accurate quantitative maps, and (3) provide pixel-wise uncertainty maps. UP-Net incorporated a phase augmentation strategy, generative adversarial network architecture, and an MRI physics loss term based on a fat-water and R2 * signal model. UP-Net was trained and tested using free-breathing multi-echo stack-of-radial MRI data from 105 subjects. UP-Net uncertainty scores were calibrated in a validation dataset and used to predict quantification errors for liver PDFF and R2 * in a testing dataset.

RESULTS

Compared with images reconstructed using compressed sensing (CS), UP-Net achieved structural similarity index >0.87 and normalized root mean squared error <0.18. Compared with reference quantitative maps generated using CS and graph-cut (GC) algorithms, UP-Net achieved low mean differences (MD) for liver PDFF (-0.36%) and R2 * (-0.37 s-1 ). Compared with breath-holding Cartesian MRI results, UP-Net achieved low MD for liver PDFF (0.53%) and R2 * (6.75 s-1 ). UP-Net uncertainty scores predicted absolute liver PDFF and R2 * errors with low MD of 0.27% and 0.12 s-1 compared to CS + GC results. The computational time for UP-Net was 79 ms/slice, whereas CS + GC required 3.2 min/slice.

CONCLUSION

UP-Net rapidly calculates accurate liver PDFF and R2 * maps from self-gated free-breathing stack-of-radial MRI. The pixel-wise uncertainty maps from UP-Net predict quantification errors in the liver.