ACCELERATING MAGNETIC RESONANCE IMAGING VIA DEEP LEARNING

Sparse reconstruction of magnetic resonance image combined with two-step iteration and adaptive shrinkage factor

As an advanced technique, compressed sensing has been used for rapid magnetic resonance imaging in recent years, Two-step Iterative Shrinkage Thresholding Algorithm (TwIST) is a popular algorithm based on Iterative Thresholding Shrinkage Algorithm (ISTA) for fast MR image reconstruction. However TwIST algorithms cannot dynamically adjust shrinkage factor according to the degree of convergence. So it is difficult to balance speed and efficiency. In this paper, we proposed an algorithm which can dynamically adjust the shrinkage factor to rebalance the fidelity item and regular item during TwIST iterative process. The shrinkage factor adjusting is judged by the previous reconstructed results throughout the iteration cycle. It can greatly accelerate the iterative convergence while ensuring convergence accuracy. We used MR images with 2 body parts and different sampling rates to simulate, the results proved that the proposed algorithm have a faster convergence rate and better reconstruction performance. We also used 60 MR images of different body parts for further simulation, and the results proved the universal superiority of the proposed algorithm.

Deep learning for compressive sensing: a ubiquitous systems perspective

Compressive sensing (CS) is a mathematically elegant tool for reducing the sensor sampling rate, potentially bringing context-awareness to a wider range of devices. Nevertheless, practical issues with the sampling and reconstruction algorithms prevent further proliferation of CS in real world domains, especially among heterogeneous ubiquitous devices. Deep learning (DL) naturally complements CS for adapting the sampling matrix, reconstructing the signal, and learning from the compressed samples. While the CS–DL integration has received substantial research interest recently, it has not yet been thoroughly surveyed, nor has any light been shed on practical issues towards bringing the CS–DL to real world implementations in the ubiquitous computing domain. In this paper we identify main possible ways in which CS and DL can interplay, extract key ideas for making CS–DL efficient, outline major trends in the CS–DL research space, and derive guidelines for the future evolution of CS–DL within the ubiquitous computing domain.

Multimodal MRI Reconstruction Assisted With Spatial Alignment Network

In clinical practice, multi-modal magnetic resonance imaging (MRI) with different contrasts is usually acquired in a single study to assess different properties of the same region of interest in the human body. The whole acquisition process can be accelerated by having one or more modalities under-sampled in the k -space. Recent research has shown that, considering the redundancy between different modalities, a target MRI modality under-sampled in the k -space can be more efficiently reconstructed with a fully-sampled reference MRI modality. However, we find that the performance of the aforementioned multi-modal reconstruction can be negatively affected by subtle spatial misalignment between different modalities, which is actually common in clinical practice. In this paper, we improve the quality of multi-modal reconstruction by compensating for such spatial misalignment with a spatial alignment network. First, our spatial alignment network estimates the displacement between the fully-sampled reference and the under-sampled target images, and warps the reference image accordingly. Then, the aligned fully-sampled reference image joins the multi-modal reconstruction of the under-sampled target image. Also, considering the contrast difference between the target and reference images, we have designed a cross-modality-synthesis-based registration loss in combination with the reconstruction loss, to jointly train the spatial alignment network and the reconstruction network. The experiments on both clinical MRI and multi-coil k -space raw data demonstrate the superiority and robustness of the multi-modal MRI reconstruction empowered with our spatial alignment network. Our code is publicly available at https://github.com/woxuankai/SpatialAlignmentNetwork.

Evaluation of a deep learning method for the automated detection of supraspinatus tears on MRI

OBJECTIVE

To evaluate if deep learning is a feasible approach for automated detection of supraspinatus tears on MRI.

MATERIALS AND METHODS

A total of 200 shoulder MRI studies performed between 2015 and 2019 were retrospectively obtained from our institutional database using a balanced random sampling of studies containing a full-thickness tear, partial-thickness tear, or intact supraspinatus tendon. A 3-stage pipeline was developed comprised of a slice selection network based on a pre-trained residual neural network (ResNet); a segmentation network based on an encoder-decoder network (U-Net); and a custom multi-input convolutional neural network (CNN) classifier. Binary reference labels were created following review of radiologist reports and images by a radiology fellow and consensus validation by two musculoskeletal radiologists. Twenty percent of the data was reserved as a holdout test set with the remaining 80% used for training and optimization under a fivefold cross-validation strategy. Classification and segmentation accuracy were evaluated using area under the receiver operating characteristic curve (AUROC) and Dice similarity coefficient, respectively. Baseline characteristics in correctly versus incorrectly classified cases were compared using independent sample t-test and chi-squared.

RESULTS

Test sensitivity and specificity of the classifier at the optimal Youden's index were 85.0% (95% CI: 62.1-96.8%) and 85.0% (95% CI: 62.1-96.8%), respectively. AUROC was 0.943 (95% CI: 0.820-0.991). Dice segmentation accuracy was 0.814 (95% CI: 0.805-0.826). There was no significant difference in AUROC between 1.5 T and 3.0 T studies. Sub-analysis showed superior sensitivity on full-thickness (100%) versus partial-thickness (72.5%) subgroups.

DATA CONCLUSION

Deep learning is a feasible approach to detect supraspinatus tears on MRI.

Artificial intelligence in multi-parametric magnetic resonance imaging: A review

Multi-parametric magnetic resonance imaging (mpMRI) is an indispensable tool in the clinical workflow for the diagnosis and treatment planning of various diseases. Machine learning-based artificial intelligence (AI) methods, especially those adopting the deep learning technique, have been extensively employed to perform mpMRI image classification, segmentation, registration, detection, reconstruction, and super-resolution. The current availability of increasing computational power and fast-improving AI algorithms have empowered numerous computer-based systems for applying mpMRI to disease diagnosis, imaging-guided radiotherapy, patient risk and overall survival time prediction, and the development of advanced quantitative imaging technology for magnetic resonance fingerprinting. However, the wide application of these developed systems in the clinic is still limited by a number of factors, including robustness, reliability, and interpretability. This survey aims to provide an overview for new researchers in the field as well as radiologists with the hope that they can understand the general concepts, main application scenarios, and remaining challenges of AI in mpMRI. This article is protected by copyright. All rights reserved.

Dual-Domain Reconstruction Network with V-Net and K-Net for Fast MRI

PURPOSE

To introduce a dual-domain reconstruction network with V-Net and K-Net for accurate MR image reconstruction from undersampled k-space data.

METHODS

Most state-of-the-art reconstruction methods apply U-Net or cascaded U-Nets in the image domain and/or k-space domain. Nevertheless, these methods have the following problems: (1) directly applying U-Net in the k-space domain is not optimal for extracting features; (2) classical image-domain-oriented U-Net is heavyweighted and hence inefficient when cascaded many times to yield good reconstruction accuracy; (3) classical image-domain-oriented U-Net does not make full use of information of the encoder network for extracting features in the decoder network; and (4) existing methods are ineffective in simultaneously extracting and fusing features in the image domain and its dual k-space domain. To tackle these problems, we present 3 different methods: (1) V-Net, an image-domain encoder-decoder subnetwork that is more lightweight for cascading and effective in fully utilizing features in the encoder for decoding; (2) K-Net, a k-space domain subnetwork that is more suitable for extracting hierarchical features in the k-space domain, and (3) KV-Net, a dual-domain reconstruction network in which V-Nets and K-Nets are effectively combined and cascaded.

RESULTS

Extensive experimental results on the fastMRI dataset demonstrate that the proposed KV-Net can reconstruct high-quality images and outperform state-of-the-art approaches with fewer parameters.

CONCLUSIONS

To reconstruct images effectively and efficiently from incomplete k-space data, we have presented a dual-domain KV-Net to combine K-Nets and V-Nets. The KV-Net achieves better results with 9% and 5% parameters than comparable methods (XPD-Net and i-RIM).

Multiple B-Value Model-Based Residual Network (MORN) for Accelerated High-Resolution Diffusion-Weighted Imaging

Single-Shot Echo Planar Imaging (SSEPI) based Diffusion Weighted Imaging (DWI) has shortcomings such as low resolution and severe distortions. In contrast, Multi-Shot EPI (MSEPI) provides optimal spatial resolution but increases scan time. This study proposed a Multiple b-value mOdel-based Residual Network (MORN) model to reconstruct multiple b-value high-resolution DWI from undersampled k-space data simultaneously. We incorporated Parallel Imaging (PI) into a residual U-net to reconstruct multiple b-value multi-coil data with the supervision of MUltiplexed Sensitivity-Encoding (MUSE) reconstructed Multi-Shot DWI (MSDWI). Moreover, asymmetric concatenations among different b-values and the combined loss to back propagate helped the feature transfer. After training and validation of the MORN in a dataset of 32 healthy cases, additional assessments were performed on 6 patients with different tumor types. The experimental results demonstrated that the MORN model outperformed conventional PI reconstruction (i.e. SENSE) and two state-of-the-art deep learning methods (SENSE-GAN and VSNet) in terms of PSNR (Peak Signal-to-Noise Ratio), SSIM (Structual SIMilarity) and apparent diffusion coefficient maps. In addition, using the pre-trained model under DWI, the MORN achieved consistent fractional anisotrophy and mean diffusivity reconstructed from multiple diffusion directions. Hence, the proposed method shows potential in clinical application according to the observations on tumor patients as well as images of multiple diffusion directions.

Multi-Coil MRI Reconstruction Challenge-Assessing Brain MRI Reconstruction Models and Their Generalizability to Varying Coil Configurations

Deep-learning-based brain magnetic resonance imaging (MRI) reconstruction methods have the potential to accelerate the MRI acquisition process. Nevertheless, the scientific community lacks appropriate benchmarks to assess the MRI reconstruction quality of high-resolution brain images, and evaluate how these proposed algorithms will behave in the presence of small, but expected data distribution shifts. The multi-coil MRI (MC-MRI) reconstruction challenge provides a benchmark that aims at addressing these issues, using a large dataset of high-resolution, three-dimensional, T1-weighted MRI scans. The challenge has two primary goals: (1) to compare different MRI reconstruction models on this dataset and (2) to assess the generalizability of these models to data acquired with a different number of receiver coils. In this paper, we describe the challenge experimental design and summarize the results of a set of baseline and state-of-the-art brain MRI reconstruction models. We provide relevant comparative information on the current MRI reconstruction state-of-the-art and highlight the challenges of obtaining generalizable models that are required prior to broader clinical adoption. The MC-MRI benchmark data, evaluation code, and current challenge leaderboard are publicly available. They provide an objective performance assessment for future developments in the field of brain MRI reconstruction.

Fast MRI Reconstruction: How Powerful Transformers Are?

Magnetic resonance imaging (MRI) is a widely used non-radiative and non-invasive method for clinical interro-gation of organ structures and metabolism, with an inherently long scanning time. Methods by k-space undersampling and deep learning based reconstruction have been popularised to accelerate the scanning process. This work focuses on investigating how powerful transformers are for fast MRI by exploiting and comparing different novel network architectures. In particular, a generative adversarial network (GAN) based Swin transformer (ST-GAN) was introduced for the fast MRI reconstruction. To further preserve the edge and texture information, edge enhanced GAN based Swin transformer (EES-GAN) and texture enhanced GAN based Swin transformer (TES-GAN) were also developed, where a dual-discriminator GAN structure was applied. We compared our proposed GAN based transformers, standalone Swin transformer and other convolutional neural networks based GAN model in terms of the evaluation metrics PSNR, SSIM and FID. We showed that transformers work well for the MRI reconstruction from different undersampling conditions. The utilisation of GAN's adversarial structure improves the quality of images reconstructed when undersampled for 30% or higher. The code is publicly available at https://github.comJayanglab/SwinGANMR.

Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers

Supervised reconstruction models are characteristically trained on matched pairs of undersampled and fully-sampled data to capture an MRI prior, along with supervision regarding the imaging operator to enforce data consistency. To reduce supervision requirements, the recent deep image prior framework instead conjoins untrained MRI priors with the imaging operator during inference. Yet, canonical convolutional architectures are suboptimal in capturing long-range relationships, and priors based on randomly initialized networks may yield suboptimal performance. To address these limitations, here we introduce a novel unsupervised MRI reconstruction method based on zero-Shot Learned Adversarial TransformERs (SLATER). SLATER embodies a deep adversarial network with cross-attention transformers to map noise and latent variables onto coil-combined MR images. During pre-training, this unconditional network learns a high-quality MRI prior in an unsupervised generative modeling task. During inference, a zero-shot reconstruction is then performed by incorporating the imaging operator and optimizing the prior to maximize consistency to undersampled data. Comprehensive experiments on brain MRI datasets clearly demonstrate the superior performance of SLATER against state-of-the-art unsupervised methods.

EPI phase error correction with deep learning (PEC-DL) at 7 T

PURPOSE

The phase mismatch between odd and even echoes in EPI causes Nyquist ghost artifacts. Existing ghost correction methods often suffer from severe residual artifacts and are ineffective with k-space undersampling data. This study proposed a deep learning-based method (PEC-DL) to correct phase errors for DWI at 7 Tesla.

METHODS

The acquired k-space data were divided into 2 independent undersampled datasets according to their readout polarities. Then the proposed PEC-DL network reconstructed 2 ghost-free images using the undersampled data without calibration and navigator data. The network was trained with fully sampled images and applied to two- and fourfold accelerated data. Healthy volunteers and patients with Moyamoya disease were recruited to validate the efficacy of the PEC-DL method.

RESULTS

The PEC-DL method was capable to mitigate the ghost artifacts in DWI in healthy volunteers as well as patients with Moyamoya disease. The fourfold accelerated results showed much less distortion in the lesions of the Moyamoya patient using high b-value DWI and the corresponding ADC maps. The ghost-to-signal ratios were significantly lower in PEC-DL images compared to conventional linear phase corrections, mini-entropy, and PEC-GRAPPA algorithms.

CONCLUSION

The proposed method can effectively eliminate ghost artifacts for full sampled and up to fourfold accelerated EPI data without calibration and navigator data.

Simultaneously optimizing sampling pattern for joint acceleration of multi-contrast MRI using model-based deep learning

BACKGROUND

Acceleration of MR imaging (MRI) is a popular research area, and usage of deep learning for acceleration has become highly widespread in the MR community. Joint acceleration of multiple-acquisition MRI was proven to be effective over a single-acquisition approach. Also, optimization in the sampling pattern demonstrated its advantage over conventional undersampling pattern. However, optimizing the sampling patterns for joint acceleration of multiple-acquisition MRI has not been investigated well.

PURPOSE

To develop a model-based deep learning scheme to optimize sampling patterns for a joint acceleration of multi-contrast MRI.

METHODS

The proposed scheme combines sampling pattern optimization and multi-contrast MRI reconstruction. It was extended from the physics-guided method of the joint model-based deep learning (J-MoDL) scheme to optimize the separate sampling pattern for each of multiple contrasts simultaneously for their joint reconstruction. Tests were performed with three contrasts of T2-weighted, FLAIR, and T1-weighted images. The proposed multi-contrast method was compared to (i) single-contrast method with sampling optimization (baseline J-MoDL), (ii) multi-contrast method without sampling optimization, and (iii) multi-contrast method with single common sampling optimization for all contrasts. The optimized sampling patterns were analyzed for sampling location overlap across contrasts. The scheme was also tested in a data-driven scenario, where the inversion between input and label was learned from the under-sampled data directly and tested on knee datasets for generalization test.

RESULTS

The proposed scheme demonstrated a quantitative and qualitative advantage over the single-contrast scheme with sampling pattern optimization and the multi-contrast scheme without sampling pattern optimization. Optimizing the separate sampling pattern for each of the multi-contrasts was superior to optimizing only one common sampling pattern for all contrasts. The proposed scheme showed less overlap in sampling locations than the single-contrast scheme. The main hypothesis was also held in the data-driven situation as well. The brain-trained model worked well on the knee images, demonstrating its generalizability.

CONCLUSION

Our study introduced an effective scheme that combines the sampling optimization and the multi-contrast acceleration. The seamless combination resulted in superior performance over the other existing methods.

Accelerating multi-echo chemical shift encoded water-fat MRI using model-guided deep learning

PURPOSE

To accelerate chemical shift encoded (CSE) water-fat imaging by applying a model-guided deep learning water-fat separation (MGDL-WF) framework to the undersampled k-space data.

METHODS

A model-guided deep learning water-fat separation framework is proposed for the acceleration using Cartesian/radial undersampling data. The proposed MGDL-WF combines the power of CSE water-fat imaging model and data-driven deep learning by jointly using a multi-peak fat model and a modified residual U-net network. The model is used to guide the image reconstruction, and the network is used to capture the artifacts induced by the undersampling. A data consistency layer is used in MGDL-WF to ensure the output images to be consistent with the k-space measurements. A Gauss-Newton iteration algorithm is adapted for the gradient updating of the networks.

RESULTS

Compared with the compressed sensing water-fat separation (CS-WF) algorithm/2-step procedure algorithm, the MGDL-WF increased peak signal-to-noise ratio (PSNR) by 5.31/5.23, 6.11/4.54, and 4.75 dB/1.88 dB with Cartesian sampling, and by 4.13/6.53, 2.90/4.68, and 1.68 dB/3.48 dB with radial sampling, at acceleration rates (R) of 4, 6, and 8, respectively. By using MGDL-WF, radial sampling increased the PSNR by 2.07 dB at R = 8, compared with Cartesian sampling.

CONCLUSIONS

The proposed MGDL-WF enables exploiting features of the water images and fat images from the undersampled multi-echo data, leading to improved performance in the accelerated CSE water-fat imaging. By using MGDL-WF, radial sampling can further improve the image quality with comparable scan time in comparison with Cartesian sampling.

Parallel MR image reconstruction based on triple cycle optimization

The self-calibration parallel imaging (SC-SENSE) method reconstructs the image by estimating the coil sensitivity matrix. In order to obtain the sensitivity matrix, it is necessary to take a small amount of automatic calibration signal lines (ACSL) in the center of k-space. This method uses the data of the central region to obtain the sensitivity matrix, and then the reconstructed image is obtained. This paper proposed the triple cycle optimization (TCO) method to continuously optimize reconstructed images. The proposed TCO method takes the sensitivity matrix obtained by ACSL and substituted the reconstructed image as the initial data generation into the loop, and estimates the k-space data repeatedly. A new sensitivity matrix is obtained by using k-space data and the reconstructed image, and a stable triple cycle is obtained. In the cycle, all data are optimized to a certain extent, including the reconstructed image. Experimental results show that under the same sampling density, images reconstructed by using the triple cycle optimization method have lower noise and artifacts than those of the traditional method. When combined with the variable density sampling method, the effect is remarkable with a much low sampling rate.

Arterial spin labeling MR image denoising and reconstruction using unsupervised deep learning

Arterial spin labeling (ASL) imaging is a powerful magnetic resonance imaging technique that allows to quantitatively measure blood perfusion non-invasively, which has great potential for assessing tissue viability in various clinical settings. However, the clinical applications of ASL are currently limited by its low signal-to-noise ratio (SNR), limited spatial resolution, and long imaging time. In this work, we propose an unsupervised deep learning-based image denoising and reconstruction framework to improve the SNR and accelerate the imaging speed of high resolution ASL imaging. The unique feature of the proposed framework is that it does not require any prior training pairs but only the subject's own anatomical prior, such as T1-weighted images, as network input. The neural network was trained from scratch in the denoising or reconstruction process, with noisy images or sparely sampled k-space data as training labels. Performance of the proposed method was evaluated using in vivo experiment data obtained from 3 healthy subjects on a 3T MR scanner, using ASL images acquired with 44-min acquisition time as the ground truth. Both qualitative and quantitative analyses demonstrate the superior performance of the proposed txtc framework over the reference methods. In summary, our proposed unsupervised deep learning-based denoising and reconstruction framework can improve the image quality and accelerate the imaging speed of ASL imaging.

DIMENSION: Dynamic MR imaging with both k-space and spatial prior knowledge obtained via multi-supervised network training

Dynamic MR image reconstruction from incomplete k-space data has generated great research interest due to its capability in reducing scan time. Nevertheless, the reconstruction problem is still challenging due to its ill-posed nature. Most existing methods either suffer from long iterative reconstruction time or explore limited prior knowledge. This paper proposes a dynamic MR imaging method with both k-space and spatial prior knowledge integrated via multi-supervised network training, dubbed as DIMENSION. Specifically, the DIMENSION architecture consists of a frequential prior network for updating the k-space with its network prediction and a spatial prior network for capturing image structures and details. Furthermore, a multi-supervised network training technique is developed to constrain the frequency domain information and the spatial domain information. The comparisons with classical k-t FOCUSS, k-t SLR, L+S and the state-of-the-art CNN-based method on in vivo datasets show our method can achieve improved reconstruction results in shorter time.

Multi-level pooling encoder-decoder convolution neural network for MRI reconstruction

MRI reconstruction is one of the critical processes of MRI machines, along with the acquisition. Due to a slow processing time of signal acquiring, parallel imaging and reconstruction techniques are applied for acceleration. To accelerate the acquisition process, fewer raw data are sampled simultaneously with all RF coils acquisition. Then, the reconstruction uses under-sampled data from all RF coils to restore the final MR image that resembles the fully sampled MR image. These processes have been a traditional procedure inside the MRI system since the invention of the multi-coils MRI machine. This paper proposes the deep learning technique with a lightweight network. The deep neural network is capable of generating the high-quality reconstructed MR image with a high peak signal-to-noise ratio (PSNR). This also opens a high acceleration factor for MR data acquisition. The lightweight network is called Multi-Level Pooling Encoder-Decoder Net (MLPED Net). The proposed network outperforms the traditional encoder-decoder networks on 4-fold acceleration with a significant margin on every evaluation metric. The network can be trained end-to-end, and it is a lightweight structure that can reduce training time significantly. Experimental results are based on a publicly available MRI Knee dataset from the fastMRI competition.

Implicit data crimes: Machine learning bias arising from misuse of public data

SignificancePublic databases are an important resource for machine learning research, but their growing availability sometimes leads to "off-label" usage, where data published for one task are used for another. This work reveals that such off-label usage could lead to biased, overly optimistic results of machine-learning algorithms. The underlying cause is that public data are processed with hidden processing pipelines that alter the data features. Here we study three well-known algorithms developed for image reconstruction from magnetic resonance imaging measurements and show they could produce biased results with up to 48% artificial improvement when applied to public databases. We relate to the publication of such results as implicit "data crimes" to raise community awareness of this growing big data problem.

Accelerating MR Parameter Mapping Using Nonlinear Compressive Manifold Learning and Regularized Pre-Imaging

In this study, we presented a novel method to reconstruct the MR parametric maps from highly undersampled k-space data. Specifically, we utilized a nonlinear model to sparsely represent the unknown MR parameter-weighted images in high-dimensional feature space. Each image at a specific time point is assumed to belong to a low-dimensional manifold which is learned from training images created based on the parametric model. The final reconstruction is carried out by venturing the sparse representation of the images in the feature space back to the input space, using the pre-imaging technique. Particularly, among an infinite number of solutions that satisfy the data consistency, the one that is closest to the manifold is selected as the desired solution. The underlying optimization problem is solved using kernel trick, sparse coding, and split Bregman iteration algorithm. In addition, both spatial and temporal regularizations were utilized to further improve the reconstruction quality. The proposed method was validated on both phantom and in vivo human brain T2 mapping data. Results showed the proposed method was superior to the conventional linear model-based reconstruction methods, in terms of artifact removal and quantitative estimate accuracy. The proposed method could be potentially beneficial for quantitative MR applications.

Data-Consistent non-Cartesian deep subspace learning for efficient dynamic MR image reconstruction

Non-Cartesian sampling with subspace-constrained image reconstruction is a popular approach to dynamic MRI, but slow iterative reconstruction limits its clinical application. Data-consistent (DC) deep learning can accelerate reconstruction with good image quality, but has not been formulated for non-Cartesian subspace imaging. In this study, we propose a DC non-Cartesian deep subspace learning framework for fast, accurate dynamic MR image reconstruction. Four novel DC formulations are developed and evaluated: two gradient decent approaches, a directly solved approach, and a conjugate gradient approach. We applied a U-Net model with and without DC layers to reconstruct T1-weighted images for cardiac MR Multitasking (an advanced multidimensional imaging method), comparing our results to the iteratively reconstructed reference. Experimental results show that the proposed framework significantly improves reconstruction accuracy over the U-Net model without DC, while significantly accelerating the reconstruction over conventional iterative reconstruction.

Technical Background for 4D Flow MR Imaging

Recently, the hemodynamic assessments with 3D cine phase-contrast (PC) MRI (4D flow MRI) have attracted considerable attention from clinicians. Unlike 2D cine PC MRI, the technique allows for cardiac phase-resolved data acquisitions of flow velocity vectors within the entire FOV during a clinically viable period. Thus, the method has enabled retrospective flowmetry in the spatial and temporal axes, which are essential to derive hemodynamic parameters related to vascular homeostasis and those to the progression of the pathologies. Accelerations in imaging are critical for this technology to be clinically viable; however, a high SNR or velocity-to-noise ratio (VNR) is also vital for accurate flow measurements. In this chapter, the technologies enabling this difficult balance are discussed.

A review and experimental evaluation of deep learning methods for MRI reconstruction

Following the success of deep learning in a wide range of applications, neural network-based machine-learning techniques have received significant interest for accelerating magnetic resonance imaging (MRI) acquisition and reconstruction strategies. A number of ideas inspired by deep learning techniques for computer vision and image processing have been successfully applied to nonlinear image reconstruction in the spirit of compressed sensing for accelerated MRI. Given the rapidly growing nature of the field, it is imperative to consolidate and summarize the large number of deep learning methods that have been reported in the literature, to obtain a better understanding of the field in general. This article provides an overview of the recent developments in neural-network based approaches that have been proposed specifically for improving parallel imaging. A general background and introduction to parallel MRI is also given from a classical view of k-space based reconstruction methods. Image domain based techniques that introduce improved regularizers are covered along with k-space based methods which focus on better interpolation strategies using neural networks. While the field is rapidly evolving with plenty of papers published each year, in this review, we attempt to cover broad categories of methods that have shown good performance on publicly available data sets. Limitations and open problems are also discussed and recent efforts for producing open data sets and benchmarks for the community are examined.

A multi-sequences MRI deep framework study applied to glioma classfication

Glioma is one of the most important central nervous system tumors, ranked 15th in the most common cancer for men and women. Magnetic Resonance Imaging (MRI) represents a common tool for medical experts to the diagnosis of glioma. A set of multi-sequences from an MRI is selected according to the severity of the pathology. Our proposed approach aims moreto create a computer-aided system that is capable of helping morethe expert diagnose the brain gliomas. moreWe propose a supervised learning regime based on a convolutional neural network based framework and transfer learning techniques. Our research morefocuses on the performance of different pre-trained deep learning models with respect to different MRI sequences. We highlight the best combinations of such model-MRI sequence couple for our specific task of classifying healthy brain against brain with glioma. moreWe also propose to visually analyze the extracted deep features for studying the existing relation of the MRI sequences and models. This interpretability analysis gives some hints for medical expert to understand the diagnosis made by the models. Our study is based on the well-known BraTS datasets including multi-sequence images and expert diagnosis.

Contrast-Enhanced Fluid-Attenuated Inversion Recovery in Neuroimaging: A Narrative Review on Clinical Applications and Technical Advances

While contrast-enhanced fluid-attenuated inversion recovery (FLAIR) has long been regarded as an adjunct sequence to evaluate leptomeningeal disease in addition to contrast-enhanced T1-weighted imaging, it is gradually being used for more diverse pathologies beyond leptomeningeal disease. Contrast-enhanced FLAIR is known to be highly sensitive to low concentrations of gadolinium within the fluid. Accordingly, recent research has suggested the potential utility of contrast-enhanced FLAIR in various kinds of disease, such as Meniere's disease, seizure, stroke, traumatic brain injury, and brain metastasis, in addition to being used for visualizing glymphatic dysfunction. However, its potential applications have been reported sporadically in an unorganized manner. Furthermore, the exact mechanism for its superior sensitivity to low concentrations of gadolinium has not been fully understood. Rapidly developing magnetic resonance technology and unoptimized parameters for FLAIR may challenge its accurate application in clinical practice. This review provides the fundamental mechanism of contrast-enhanced FLAIR, systematically describes its current and potential clinical application, and elaborates on technical considerations for its optimization. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 5.

AI musculoskeletal clinical applications: how can AI increase my day-to-day efficiency?

Artificial intelligence (AI) is expected to bring greater efficiency in radiology by performing tasks that would otherwise require human intelligence, also at a much faster rate than human performance. In recent years, milestone deep learning models with unprecedented low error rates and high computational efficiency have shown remarkable performance for lesion detection, classification, and segmentation tasks. However, the growing field of AI has significant implications for radiology that are not limited to visual tasks. These are essential applications for optimizing imaging workflows and improving noninterpretive tasks. This article offers an overview of the recent literature on AI, focusing on the musculoskeletal imaging chain, including initial patient scheduling, optimized protocoling, magnetic resonance imaging reconstruction, image enhancement, medical image-to-image translation, and AI-aided image interpretation. The substantial developments of advanced algorithms, the emergence of massive quantities of medical data, and the interest of researchers and clinicians reveal the potential for the growing applications of AI to augment the day-to-day efficiency of musculoskeletal radiologists.

Studying osteoarthritis with artificial intelligence applied to magnetic resonance imaging

The 3D nature and soft-tissue contrast of MRI makes it an invaluable tool for osteoarthritis research, by facilitating the elucidation of disease pathogenesis and progression. The recent increasing employment of MRI has certainly been stimulated by major advances that are due to considerable investment in research, particularly related to artificial intelligence (AI). These AI-related advances are revolutionizing the use of MRI in clinical research by augmenting activities ranging from image acquisition to post-processing. Automation is key to reducing the long acquisition times of MRI, conducting large-scale longitudinal studies and quantitatively defining morphometric and other important clinical features of both soft and hard tissues in various anatomical joints. Deep learning methods have been used recently for multiple applications in the musculoskeletal field to improve understanding of osteoarthritis. Compared with labour-intensive human efforts, AI-based methods have advantages and potential in all stages of imaging, as well as post-processing steps, including aiding diagnosis and prognosis. However, AI-based methods also have limitations, including the arguably limited interpretability of AI models. Given that the AI community is highly invested in uncovering uncertainties associated with model predictions and improving their interpretability, we envision future clinical translation and progressive increase in the use of AI algorithms to support clinicians in optimizing patient care.

Illumination angle correction during image acquisition in light-sheet fluorescence microscopy using deep learning

Light-sheet fluorescence microscopy (LSFM) is a high-speed imaging technique that provides optical sectioning with reduced photodamage. LSFM is routinely used in life sciences for live cell imaging and for capturing large volumes of cleared tissues. LSFM has a unique configuration, in which the illumination and detection paths are separated and perpendicular to each other. As such, the image quality, especially at high resolution, largely depends on the degree of overlap between the detection focal plane and the illuminating beam. However, spatial heterogeneity within the sample, curved specimen boundaries, and mismatch of refractive index between tissues and immersion media can refract the well-aligned illumination beam. This refraction can cause extensive blur and non-uniform image quality over the imaged field-of-view. To address these issues, we tested a deep learning-based approach to estimate the angular error of the illumination beam relative to the detection focal plane. The illumination beam was then corrected using a pair of galvo scanners, and the correction significantly improved the image quality across the entire field-of-view. The angular estimation was based on calculating the defocus level on a pixel level within the image using two defocused images. Overall, our study provides a framework that can correct the angle of the light-sheet and improve the overall image quality in high-resolution LSFM 3D image acquisition.

Edge-enhanced dual discriminator generative adversarial network for fast MRI with parallel imaging using multi-view information

In clinical medicine, magnetic resonance imaging (MRI) is one of the most important tools for diagnosis, triage, prognosis, and treatment planning. However, MRI suffers from an inherent slow data acquisition process because data is collected sequentially in k-space. In recent years, most MRI reconstruction methods proposed in the literature focus on holistic image reconstruction rather than enhancing the edge information. This work steps aside this general trend by elaborating on the enhancement of edge information. Specifically, we introduce a novel parallel imaging coupled dual discriminator generative adversarial network (PIDD-GAN) for fast multi-channel MRI reconstruction by incorporating multi-view information. The dual discriminator design aims to improve the edge information in MRI reconstruction. One discriminator is used for holistic image reconstruction, whereas the other one is responsible for enhancing edge information. An improved U-Net with local and global residual learning is proposed for the generator. Frequency channel attention blocks (FCA Blocks) are embedded in the generator for incorporating attention mechanisms. Content loss is introduced to train the generator for better reconstruction quality. We performed comprehensive experiments on Calgary-Campinas public brain MR dataset and compared our method with state-of-the-art MRI reconstruction methods. Ablation studies of residual learning were conducted on the MICCAI13 dataset to validate the proposed modules. Results show that our PIDD-GAN provides high-quality reconstructed MR images, with well-preserved edge information. The time of single-image reconstruction is below 5ms, which meets the demand of faster processing.

Deep neural networks for magnetic resonance elastography acceleration in thermal ablation monitoring

PURPOSE

To develop a deep neural network for accelerating magnetic resonance elastography (MRE) acquisition, to validate the ability to generate reliable MRE results with the down-sampled k-space data, and to demonstrate the feasibility of the proposed method in monitoring the stiffness changes during thermal ablation in a phantom study.

MATERIALS AND METHODS

MRE scans were performed with 60 Hz excitation on porcine ex-vivo liver gel phantoms in a 0.36T MRI scanner to generate the training dataset. The acquisition protocol was based on a spin-echo MRE pulse sequence with tailored motion-sensitive gradients to reduce echo time (TE). A U-Net based deep neural network was developed and trained to interpolate the missing data from down-sampled k-space. We calculated the errors of 80 sets magnitude/phase images reconstructed from the zero-filled, compressive sensing (CS) and deep learning (DL) method for comparison. The peak signal-to-noise rate (PSNR) and structural similarity (SSIM) of the magnitude/phase images were also calculated for comparison. The stiffness changes were recorded before, during, and after ablation. The mean stiffness values over the region of interest (ROI) were compared between the elastograms reconstructed from the fully-sampled k-space and interpolated k-space after thermal ablation.

RESULTS

The mean absolute error (MAE), PSNR, and SSIM of the proposed deep learning approach were significantly better than the results from the zero-filled method (p<0.0001) and CS (p<0.0001). The stiffness changes before and after thermal ablation assessed by the proposed approach (before: 7.7±1.1 kPa, after: 11.9±4.0 kPa, 4.2-kPa increase) gave close agreement with the values calculated from the fully-sampled data (before: 8.0±1.0 kPa, after: 12.6±4.2 kPa, 4.6-kPa increase). In contrast, the stiffness changes computed from the zero-filled method (before: 4.9±1.4 kPa, after: 5.6±2.8 kPa, 0.7-kPa increase) were substantially underestimated.

CONCLUSION

This study demonstrated the capability of the proposed deep learning method for rapid MRE acquisition and provided a promising solution for monitoring the MRI-guided thermal ablation. This article is protected by copyright. All rights reserved.

Undersampled Multi-contrast MRI Reconstruction Based on Double-domain Generative Adversarial Network

Multi-contrast magnetic resonance imaging can provide comprehensive information for clinical diagnosis. However, multi-contrast imaging suffers from long acquisition time, which makes it inhibitive for daily clinical practice. Subsampling k-space is one of the main methods to speed up scan time. Missing k-space samples will lead to inevitable serious artifacts and noise. Considering the assumption that different contrast modalities share some mutual information, it may be possible to exploit this redundancy to accelerate multi-contrast imaging acquisition. Recently, generative adversarial network shows superior performance in image reconstruction and synthesis. Some studies based on k-space reconstruction also exhibit superior performance over conventional state-of-art method. In this study, we propose a cross-domain two-stage generative adversarial network for multi-contrast images reconstruction based on prior full-sampled contrast and undersampled information. The new approach integrates reconstruction and synthesis, which estimates and completes the missing k-space and then refines in image space. It takes one fully-sampled contrast modality data and highly undersampled data from several other modalities as input, and outputs high quality images for each contrast simultaneously. The network is trained and tested on a public brain dataset from healthy subjects. Quantitative comparisons against baseline clearly indicate that the proposed method can effectively reconstruct undersampled images. Even under high acceleration, the network still can recover texture details and reduce artifacts.

A simultaneous multi-slice T2 mapping framework based on overlapping-echo detachment planar imaging and deep learning reconstruction

PURPOSE

Quantitative MRI (qMRI) is of great importance to clinical medicine and scientific research. However, most qMRI techniques are time-consuming and sensitive to motion, especially when a large 3D volume is imaged. To accelerate the acquisition, a framework is proposed to realize reliable simultaneous multi-slice T₂ mapping.

METHODS

The simultaneous multi-slice T₂ mapping framework is based on overlapping-echo detachment (OLED) planar imaging (dubbed SMS-OLED). Multi-slice overlapping-echo signals were generated by multiple excitation pulses together with echo-shifting gradients. The signals were excited and acquired with a single-channel coil. U-Net was used to reconstruct T₂ maps from the acquired overlapping-echo image.

RESULTS

Single-shot double-slice and two-shot triple-slice SMS-OLED scan schemes were designed according to the framework for evaluation. Simulations, water phantom, and in vivo rat brain experiments were carried out. Overlapping-echo signals were acquired, and T₂ maps were reconstructed and compared with references. The results demonstrate the superior performance of our method.

CONCLUSION

Two slices of T₂ maps can be obtained in a single shot within hundreds of milliseconds. Higher quality multi-slice T₂ maps can be obtained via multiple shots. SMS-OLED provides a lower specific absorption rate scheme compared with conventional SMS methods with a coil with only a single receiver channel. The new method is of potential in dynamic qMRI and functional qMRI where temporal resolution is vital.

An artificial intelligence-accelerated 2-minute multi-shot echo planar imaging protocol for comprehensive high-quality clinical brain imaging

PURPOSE

We introduce and validate an artificial intelligence (AI)-accelerated multi-shot echo-planar imaging (msEPI)-based method that provides T1w, T2w, T 2 ∗ , T2-FLAIR, and DWI images with high SNR, high tissue contrast, low specific absorption rates (SAR), and minimal distortion in 2 minutes.

METHODS

The rapid imaging technique combines a novel machine learning (ML) scheme to limit g-factor noise amplification and improve SNR, a magnetization transfer preparation module to provide clinically desirable contrast, and high per-shot EPI undersampling factors to reduce distortion. The ML training and image reconstruction incorporates a tunable parameter for controlling the level of denoising/smoothness. The performance of the reconstruction method is evaluated across various acceleration factors, contrasts, and SNR conditions. The 2-minute protocol is directly compared to a 10-minute clinical reference protocol through deployment in a clinical setting, where five representative cases with pathology are examined.

RESULTS

Optimization of custom msEPI sequences and protocols was performed to balance acquisition efficiency and image quality compared to the five-fold longer clinical reference. Training data from 16 healthy subjects across multiple contrasts and orientations were used to produce ML networks at various acceleration levels. The flexibility of the ML reconstruction was demonstrated across SNR levels, and an optimized regularization was determined through radiological review. Network generalization toward novel pathology, unobserved during training, was illustrated in five clinical case studies with clinical reference images provided for comparison.

CONCLUSION

The rapid 2-minute msEPI-based protocol with tunable ML reconstruction allows for advantageous trade-offs between acquisition speed, SNR, and tissue contrast when compared to the five-fold slower standard clinical reference exam.

Evaluation on the generalization of a learned convolutional neural network for MRI reconstruction

Recently, deep learning approaches with various network architectures have drawn significant attention from the magnetic resonance imaging (MRI) community because of their great potential for image reconstruction from undersampled k-space data in fast MRI. However, the robustness of a trained network when applied to test data deviated from training data is still an important open question. In this work, we focus on quantitatively evaluating the influence of image contrast, human anatomy, sampling pattern, undersampling factor, and noise level on the generalization of a trained network composed by a cascade of several CNNs and a data consistency layer, called a deep cascade of convolutional neural network (DC-CNN). The DC-CNN is trained from datasets with different image contrast, human anatomy, sampling pattern, undersampling factor, and noise level, and then applied to test datasets consistent or inconsistent with the training datasets to assess the generalizability of the learned DC-CNN network. The results of our experiments show that reconstruction quality from the DC-CNN network is highly sensitive to sampling pattern, undersampling factor, and noise level, which are closely related to signal-to-noise ratio (SNR), and is relatively less sensitive to the image contrast. We also show that a deviation of human anatomy between training and test data leads to a substantial reduction of image quality for the brain dataset, whereas comparable performance for the chest and knee dataset having fewer anatomy details than brain images. This work further provides some empirical understanding of the generalizability of trained networks when there are deviations between training and test data. It also demonstrates the potential of transfer learning for image reconstruction from datasets different from those used in training the network.

A review on deep learning MRI reconstruction without fully sampled k-space

BACKGROUND

Magnetic resonance imaging (MRI) is an effective auxiliary diagnostic method in clinical medicine, but it has always suffered from the problem of long acquisition time. Compressed sensing and parallel imaging are two common techniques to accelerate MRI reconstruction. Recently, deep learning provides a new direction for MRI, while most of them require a large number of data pairs for training. However, there are many scenarios where fully sampled k-space data cannot be obtained, which will seriously hinder the application of supervised learning. Therefore, deep learning without fully sampled data is indispensable.

MAIN TEXT

In this review, we first introduce the forward model of MRI as a classic inverse problem, and briefly discuss the connection of traditional iterative methods to deep learning. Next, we will explain how to train reconstruction network without fully sampled data from the perspective of obtaining prior information.

CONCLUSION

Although the reviewed methods are used for MRI reconstruction, they can also be extended to other areas where ground-truth is not available. Furthermore, we may anticipate that the combination of traditional methods and deep learning will produce better reconstruction results.

Compressed Sensing in Sodium Magnetic Resonance Imaging: Techniques, Applications, and Future Prospects

Sodium (²³ Na) yields the second strongest nuclear magnetic resonance (NMR) signal in biological tissues and plays a vital role in cell physiology. Sodium magnetic resonance imaging (MRI) can provide insights into cell integrity and tissue viability relative to pathologies without significant anatomical alternations, and thus it is considered to be a potential surrogate biomarker that provides complementary information for standard hydrogen (¹ H) MRI in a noninvasive and quantitative manner. However, sodium MRI suffers from a relatively low signal-to-noise ratio and long acquisition times due to its relatively low NMR sensitivity. Compressed sensing-based (CS-based) methods have been shown to accelerate sodium imaging and/or improve sodium image quality significantly. In this manuscript, the basic concepts of CS and how CS might be applied to improve sodium MRI are described, and the historical milestones of CS-based sodium MRI are briefly presented. Representative advanced techniques and evaluation methods are discussed in detail, followed by an expose of clinical applications in multiple anatomical regions and diseases as well as thoughts and suggestions on potential future research prospects of CS in sodium MRI. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: Stage 1.

Review and Prospect: Artificial Intelligence in Advanced Medical Imaging

Artificial intelligence (AI) as an emerging technology is gaining momentum in medical imaging. Recently, deep learning-based AI techniques have been actively investigated in medical imaging, and its potential applications range from data acquisition and image reconstruction to image analysis and understanding. In this review, we focus on the use of deep learning in image reconstruction for advanced medical imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET). Particularly, recent deep learning-based methods for image reconstruction will be emphasized, in accordance with their methodology designs and performances in handling volumetric imaging data. It is expected that this review can help relevant researchers understand how to adapt AI for medical imaging and which advantages can be achieved with the assistance of AI.

Time-Dependent Deep Image Prior for Dynamic MRI

We propose a novel unsupervised deep-learning-based algorithm for dynamic magnetic resonance imaging (MRI) reconstruction. Dynamic MRI requires rapid data acquisition for the study of moving organs such as the heart. We introduce a generalized version of the deep-image-prior approach, which optimizes the weights of a reconstruction network to fit a sequence of sparsely acquired dynamic MRI measurements. Our method needs neither prior training nor additional data. In particular, for cardiac images, it does not require the marking of heartbeats or the reordering of spokes. The key ingredients of our method are threefold: 1) a fixed low-dimensional manifold that encodes the temporal variations of images; 2) a network that maps the manifold into a more expressive latent space; and 3) a convolutional neural network that generates a dynamic series of MRI images from the latent variables and that favors their consistency with the measurements in k -space. Our method outperforms the state-of-the-art methods quantitatively and qualitatively in both retrospective and real fetal cardiac datasets. To the best of our knowledge, this is the first unsupervised deep-learning-based method that can reconstruct the continuous variation of dynamic MRI sequences with high spatial resolution.

Homotopic Gradients of Generative Density Priors for MR Image Reconstruction

Deep learning, particularly the generative model, has demonstrated tremendous potential to significantly speed up image reconstruction with reduced measurements recently. Rather than the existing generative models that often optimize the density priors, in this work, by taking advantage of the denoising score matching, homotopic gradients of generative density priors (HGGDP) are exploited for magnetic resonance imaging (MRI) reconstruction. More precisely, to tackle the low-dimensional manifold and low data density region issues in generative density prior, we estimate the target gradients in higher-dimensional space. We train a more powerful noise conditional score network by forming high-dimensional tensor as the network input at the training phase. More artificial noise is also injected in the embedding space. At the reconstruction stage, a homotopy method is employed to pursue the density prior, such as to boost the reconstruction performance. Experiment results implied the remarkable performance of HGGDP in terms of high reconstruction accuracy. Only 10% of the k-space data can still generate image of high quality as effectively as standard MRI reconstructions with the fully sampled data.

DeepSENSE: Learning coil sensitivity functions for SENSE reconstruction using deep learning

PURPOSE

To improve the estimation of coil sensitivity functions from limited auto-calibration signals (ACS) in SENSE-based reconstruction for brain imaging.

METHODS

We propose to use deep learning to estimate coil sensitivity functions by leveraging information from previous scans obtained using the same RF receiver system. Specifically, deep convolutional neural networks were designed to learn an end-to-end mapping from the initial sensitivity to the high-resolution counterpart. Sensitivity alignment was further proposed to reduce the geometric variation caused by different subject positions and imaging FOVs. Cross-validation with a small set of datasets was performed to validate the learned neural network. Iterative SENSE reconstruction was adopted to evaluate the utility of the sensitivity functions from the proposed and conventional methods.

RESULTS

The proposed method produced improved sensitivity estimates and SENSE reconstructions compared to the conventional methods in terms of aliasing and noise suppression with very limited ACS data. Cross-validation with a small set of data demonstrated the feasibility of learning coil sensitivity functions for brain imaging. The network learned on the spoiled GRE data can be applied to predict sensitivity functions for spin-echo and MPRAGE datasets.

CONCLUSION

A deep learning-based method has been proposed for improving the estimation of coil sensitivity functions. Experimental results have demonstrated the feasibility and potential of the proposed method for improving SENSE-based reconstructions especially when the ACS data are limited.

Learning a preconditioner to accelerate compressed sensing reconstructions in MRI

Purpose

To learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions.

Methods

A convolutional neural network (CNN) with residual connections was used to train a preconditioning operator. Training and validation data were simulated using 50% brain images and 50% white Gaussian noise images. Each multichannel training example contains a simulated sampling mask, complex coil sensitivity maps, and two regularization parameter maps. The trained model was integrated in the preconditioned conjugate gradient (PCG) method as part of the split Bregman CS method. The acceleration performance was compared with that of a circulant PI‐CS preconditioner for varying undersampling factors, number of coil elements and anatomies.

Results

The learned preconditioner reduces the number of PCG iterations by a factor of 4, yielding a similar acceleration as an efficient circulant preconditioner. The method generalizes well to different sampling schemes, coil configurations and anatomies.

Conclusion

It is possible to learn adaptable preconditioners for PI and CS reconstructions that meet the performance of state‐of‐the‐art preconditioners. Further acceleration could be achieved by optimizing the network architecture and the training set. Such a preconditioner could also be integrated in fully learned reconstruction methods to accelerate the training process of unrolled networks.

Dynamic Imaging Using a Deep Generative SToRM (Gen-SToRM) Model

We introduce a generative smoothness regularization on manifolds (SToRM) model for the recovery of dynamic image data from highly undersampled measurements. The model assumes that the images in the dataset are non-linear mappings of low-dimensional latent vectors. We use the deep convolutional neural network (CNN) to represent the non-linear transformation. The parameters of the generator as well as the low-dimensional latent vectors are jointly estimated only from the undersampled measurements. This approach is different from traditional CNN approaches that require extensive fully sampled training data. We penalize the norm of the gradients of the non-linear mapping to constrain the manifold to be smooth, while temporal gradients of the latent vectors are penalized to obtain a smoothly varying time-series. The proposed scheme brings in the spatial regularization provided by the convolutional network. The main benefit of the proposed scheme is the improvement in image quality and the orders-of-magnitude reduction in memory demand compared to traditional manifold models. To minimize the computational complexity of the algorithm, we introduce an efficient progressive training-in-time approach and an approximate cost function. These approaches speed up the image reconstructions and offers better reconstruction performance.

Compressed Sensing MRI with ℓ1-Wavelet Reconstruction Revisited Using Modern Data Science Tools

Deep learning (DL) has emerged as a powerful tool for improving the reconstruction quality of accelerated MRI. These methods usually show enhanced performance compared to conventional methods, such as compressed sensing (CS) and parallel imaging. However, in most scenarios, CS is implemented with two or three empirically-tuned hyperparameters, while a plethora of advanced data science tools are used in DL. In this work, we revisit ℓ1 -wavelet CS for accelerated MRI using modern data science tools. By using tools like algorithm unrolling and end-to-end training with stochastic gradient descent over large databases that DL algorithms utilize, and combining these with conventional concepts like wavelet sub-band processing and reweighted ℓ1 minimization, we show that ℓ1-wavelet CS can be fine-tuned to a level comparable to DL methods. While DL uses hundreds of thousands of parameters, the proposed optimized ℓ1-wavelet CS with sub-band training and reweighting uses only 128 parameters, and employs a fully-explainable convex reconstruction model.

Deep Convolutional Neural Network for Compressive Sensing of Magnetic Resonance Images

Compressive Sensing for Magnetic Resonance Imaging (CS-MRI) aims to reconstruct Magnetic Resonance (MR) images from under-sampled raw data. There are two challenges to improve CS-MRI methods, i.e. designing an under-sampling algorithm to achieve optimal sampling, as well as designing fast and small deep neural networks to obtain reconstructed MR images with superior quality. To improve the reconstruction quality of MR images, we propose a novel deep convolutional neural network architecture for CS-MRI named MRCSNet. The MRCSNet consists of three sub-networks, a compressive sensing sampling sub-network, an initial reconstruction sub-network, and a refined reconstruction sub-network. Experimental results demonstrate that MRCSNet generates high-quality reconstructed MR images at various under-sampling ratios, and also meets the requirements of real-time CS-MRI applications. Compared to state-of-the-art CS-MRI approaches, MRCSNet offers a significant improvement in reconstruction accuracies, such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM). Besides, it reduces the reconstruction error evaluated by the Normalized Root-Mean-Square Error (NRMSE). The source codes are available at https://github.com/TaihuLight/MRCSNet .

Simultaneous image reconstruction and lesion segmentation in accelerated MRI using multitasking learning

PURPOSE

Magnetic resonance imaging (MRI) serves as an important medical imaging modality for a variety of clinical applications. However, the problem of long imaging time limited its wide usage. In addition, prolonged scan time will cause discomfort to the patient, leading to severe image artifacts. On the other hand, manually lesion segmentation is time consuming. Algorithm-based automatic lesion segmentation is still challenging, especially for accelerated imaging with low quality.

METHODS

In this paper, we proposed a multitask learning-based method to perform image reconstruction and lesion segmentation simultaneously, called "RecSeg". Our hypothesis is that both tasks can benefit from the usage of the proposed combined model. In the experiment, we validated the proposed multitask model on MR k-space data with different acceleration factors (2×, 4×, and 6×). Two connected U-nets were used for the tasks of liver and renal image reconstruction and segmentation. A total of 50 healthy subjects and 100 patients with hepatocellular carcinoma were included for training and testing. For the segmentation part, we use healthy subjects to verify organ segmentation, and hepatocellular carcinoma patients to verify lesion segmentation. The organs and lesions were manually contoured by an experienced radiologist.

RESULTS

Experimental results show that the proposed RecSeg yielded the highest PSNR (RecSeg: 32.39 ± 1.64 vs. KSVD: 29.53 ± 2.74 and single U-net: 31.18 ± 1.68, respectively, p < 0.05) and highest structural similarity index measure (SSIM) (RecSeg: 0.93 ± 0.01 vs. KSVD: 0.88 ± 0.02 and single U-net: 0.90 ± 0.01, respectively, p < 0.05) under 6× acceleration. Moreover, in the task of lesion segmentation, it is proposed that RecSeg produced the highest Dice score (RecSeg: 0.86 ± 0.01 vs. KSVD: 0.82 ± 0.01 and single U-net: 0.84 ± 0.01, respectively, p < 0.05).

CONCLUSIONS

This study focused on the simultaneous reconstruction of medical images and the segmentation of organs and lesions. It is observed that the multitask learning-based method can improve performances of both image reconstruction and lesion segmentation.

Anatomically aided PET image reconstruction using deep neural networks

PURPOSE

The developments of PET/CT and PET/MR scanners provide opportunities for improving PET image quality by using anatomical information. In this paper, we propose a novel co-learning three-dimensional (3D) convolutional neural network (CNN) to extract modality-specific features from PET/CT image pairs and integrate complementary features into an iterative reconstruction framework to improve PET image reconstruction.

METHODS

We used a pretrained deep neural network to represent PET images. The network was trained using low-count PET and CT image pairs as inputs and high-count PET images as labels. This network was then incorporated into a constrained maximum likelihood framework to regularize PET image reconstruction. Two different network structures were investigated for the integration of anatomical information from CT images. One was a multichannel CNN, which treated PET and CT volumes as separate channels of the input. The other one was multibranch CNN, which implemented separate encoders for PET and CT images to extract latent features and fed the combined latent features into a decoder. Using computer-based Monte Carlo simulations and two real patient datasets, the proposed method has been compared with existing methods, including the maximum likelihood expectation maximization (MLEM) reconstruction, a kernel-based reconstruction and a CNN-based deep penalty method with and without anatomical guidance.

RESULTS

Reconstructed images showed that the proposed constrained ML reconstruction approach produced higher quality images than the competing methods. The tumors in the lung region have higher contrast in the proposed constrained ML reconstruction than in the CNN-based deep penalty reconstruction. The image quality was further improved by incorporating the anatomical information. Moreover, the liver standard deviation was lower in the proposed approach than all the competing methods at a matched lesion contrast.

CONCLUSIONS

The supervised co-learning strategy can improve the performance of constrained maximum likelihood reconstruction. Compared with existing techniques, the proposed method produced a better lesion contrast versus background standard deviation trade-off curve, which can potentially improve lesion detection.

Feasibility and Implementation of a Deep Learning MR Reconstruction for TSE Sequences in Musculoskeletal Imaging

Magnetic Resonance Imaging (MRI) of the musculoskeletal system is one of the most common examinations in clinical routine. The application of Deep Learning (DL) reconstruction for MRI is increasingly gaining attention due to its potential to improve the image quality and reduce the acquisition time simultaneously. However, the technology has not yet been implemented in clinical routine for turbo spin echo (TSE) sequences in musculoskeletal imaging. The aim of this study was therefore to assess the technical feasibility and evaluate the image quality. Sixty examinations of knee, hip, ankle, shoulder, hand, and lumbar spine in healthy volunteers at 3 T were included in this prospective, internal-review-board-approved study. Conventional (TSE_S) and DL-based TSE sequences (TSE_DL) were compared regarding image quality, anatomical structures, and diagnostic confidence. Overall image quality was rated to be excellent, with a significant improvement in edge sharpness and reduced noise compared to TSE_S (p < 0.001). No difference was found concerning the extent of artifacts, the delineation of anatomical structures, and the diagnostic confidence comparing TSE_S and TSE_DL (p > 0.05). Therefore, DL image reconstruction for TSE sequences in MSK imaging is feasible, enabling a remarkable time saving (up to 75%), whilst maintaining excellent image quality and diagnostic confidence.

Domain knowledge augmentation of parallel MR image reconstruction using deep learning

A deep learning (DL) method for accelerated magnetic resonance (MR) imaging is presented that incorporates domain knowledge of parallel MR imaging to augment the DL networks for accurate and stable image reconstruction. The proposed DL method employs a novel loss function consisting of a combination of mean absolute error, structural similarity, and sobel edge loss. The DL model takes both original measurements and images reconstructed by the parallel imaging method as inputs to the network. The accuracy of the proposed method was evaluated using two anatomical regions and six MRI contrasts and was compared with state-of-the-art parallel imaging and deep learning methods. The proposed method significantly outperformed the other methods for all the six different contrasts in terms of structural similarity, peak signal to noise ratio, and normalized mean squared error. The out-of-sample performance of the proposed method was assessed for a truly "unseen" case in a volunteer scan. The method produced images without any artificial features, often occurring in the DL image reconstruction methods. A stability analysis was performed by adding perturbations to the input, which demonstrated that the proposed method is robust and stable with respect to small structural changes, and different undersampling ratios. Comprehensive validation on large datasets demonstrated that incorporation of domain knowledge sufficiently regularizes the DL based image reconstruction and produces accurate and stable image enhancement.