Undersampled Magnetic Resonance Image Reconstruction Research Articles

Transformer- and joint learning-based dual-domain networks for undersampled MRI segmentation.

Recently, magnetic resonance imaging (MRI) has become a crucial medical imaging technology widely used in clinical practice. However, MRI faces challenges such as the lengthy acquisition time for k-space data and the need for time-consuming manual annotation by radiologists. Traditionally, these challenges have been addressed individually through undersampled MRI reconstruction and automatic segmentation algorithms. Whether undersampled MRI segmentation can be enhanced by treating undersampled MRI reconstruction and segmentation as an end-to-end task, trained simultaneously, rather than as serial tasks should beexplored. We introduce a novel Transformer- and Joint Learning-based Dual-domain Network (TJLD-Net) for undersampled MRIsegmentation. This method significantly enhances feature recognition in the segmentation process by fully utilizing the rich detail obtained during the image reconstruction phase. Consequently, the method can achieve precise and reliable image segmentation even with undersampled k-space data. Additionally, it incorporates an attention mechanism for feature enhancement, which improves the representation of shared features by learning the contextual information in MRimages. Simulation experiments demonstrate that the segmentation performance of TJLD-Net on three datasets is significantly higher than that of the joint model (RecSeg) and six baseline models (where reconstruction and segmentation are regarded as serial tasks). On the CHAOS dataset, the Dice scores of TJLD-Net are, on average, 9.87%, 2.17%, 1.90%, 1.80%, 9.60%, 0.80%, and 6.50% higher than those of the seven compared models. On the ATLAS challenge dataset, the average Dice scores of TJLD-Net improve by 4.23%, 5.63%, 2.30%, 1.53%, 3.57%, 0.93%, and 6.60%. Similarly, on the SKM-TEA dataset, the average Dice scores of TJLD-Net improve by 4.73%, 12.80%, 14.83%, 8.67%, 4.53%, 11.60%, and 12.10%. The novel TJLD-Net model provides a promising solution for undersampled MRI segmentation, overcoming the poor performance issues encountered by automated segmentation algorithms in low-quality acceleratedimaging.

DLGAN: Undersampled MRI reconstruction using Deep Learning based Generative Adversarial Network

Magnetic Resonance Imaging (MRI) is a crucial tool for quantitative image analysis and clinical diagnosis, providing detailed anatomical images to assist in the detection of various abnormalities. However, the widespread use of MRI is hindered by the challenges associated with long sampling periods and low-resolution image processing, prompting the development of various traditional methods to address these limitations. In recent times, advanced Deep Learning (DL) techniques have been applied to tackle the inverse problem of reconstructing MRI images from undersampled data. These DL models have demonstrated substantial improvements in terms of image reconstruction performance, cost-effectiveness, and reduced acquisition time, offering significant potential for further enhancements in this domain. This study introduces a novel DLGAN (Deep Learning Generative Adversarial Network) model comprising two sub-GAN modules tailored for specific datasets. Each module incorporates DLGAN (Generator Block, GB) and DLGAN (Discriminator Block, DB) blocks, strategically designed to regenerate MR images from K Space data. These blocks effectively leverage information from both the ground truth and KSpace characteristics, resulting in enhanced image reconstruction performance while also reducing complexity and improving overall efficiency. The DLGAN model effectively addresses common issues such as artefact removal and vanishing-gradient problems through the extraction of hierarchical features. To evaluate the model’s effectiveness, comprehensive experiments were conducted, utilizing metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The experimental findings demonstrate that the proposed DLGAN model outperforms the most recent designs in MRI image reconstruction, showcasing its potential for significant advancements in clinical diagnosis and quantitative image analysis.

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.

Perceptual contrast and residual self-attention generative adversarial network-based for highly under-sampled MRI reconstruction

ObjectiveThe study of deep learning-based fast magnetic resonance imaging (MRI) reconstruction methods has become popular in recent years. However, it is still challenging to obtain high-fidelity MRI images from undersampled data with large acceleration factors. The objective of this study was to improve the reconstruction quality of under-sampled MR images by exploring the correlation between pixels in the image and the perceptual similarities between the initial reconstructed images and the fully sampled ones. MethodsExisting reconstruction methods often suffer from aliasing artefacts and blurry texture information. We propose a novel perceptual residual self-attention generative adversarial model, SRSAGAN, to tackle this issue for fast and accurate MRI reconstruction. The proposed method involves two operation steps. In step 1, leveraging the average information and similarity weights of high-level features, we designed a novel feature enhancement module based on residual self-attention to restore fine texture details in the reconstructed image. In step 2, to improve the accuracy of network inference, we compare the perceptual similarities between the initial reconstructed images and the fully sampled ones. ResultThe proposed algorithm was evaluated using the fastMRI dataset. It demonstrates that SRSAGAN outperforms state-of-art methods and reconstructs complex image texture with only 10 % retained the k-space raw data (10-fold acceleration). The reconstruction time is only about 7.78 ms.

Sinogram upsampling using Primal–Dual UNet for undersampled CT and radial MRI reconstruction

Computed tomography (CT) and magnetic resonance imaging (MRI) are two widely used clinical imaging modalities for non-invasive diagnosis. However, both of these modalities come with certain problems. CT uses harmful ionising radiation, and MRI suffers from slow acquisition speed. Both problems can be tackled by undersampling, such as sparse sampling. However, such undersampled data leads to lower resolution and introduces artefacts. Several techniques, including deep learning based methods, have been proposed to reconstruct such data. However, the undersampled reconstruction problem for these two modalities was always considered as two different problems and tackled separately by different research works. This paper proposes a unified solution for both sparse CT and undersampled radial MRI reconstruction, achieved by applying Fourier transform-based pre-processing on the radial MRI and then finally reconstructing both modalities using sinogram upsampling combined with filtered back-projection. The Primal–Dual network is a deep learning based method for reconstructing sparsely-sampled CT data. This paper introduces Primal–Dual UNet, which improves the Primal–Dual network in terms of accuracy and reconstruction speed. The proposed method resulted in an average SSIM of 0.932±0.021 while performing sparse CT reconstruction for fan-beam geometry with a sparsity level of 16, achieving a statistically significant improvement over the previous model, which resulted in 0.919±0.016. Furthermore, the proposed model resulted in 0.903±0.019 and 0.957±0.023 average SSIM while reconstructing undersampled brain and abdominal MRI data with an acceleration factor of 16, respectively - statistically significant improvements over the original model, which resulted in 0.867±0.025 and 0.949±0.025. Finally, this paper shows that the proposed network not only improves the overall image quality, but also improves the image quality for the regions-of-interest: liver, kidneys, and spleen; as well as generalises better than the baselines in presence the of a needle.

Modeling human observer detection in undersampled magnetic resonance imaging reconstruction with total variation and wavelet sparsity regularization.

Task-based assessment of image quality in undersampled magnetic resonance imaging provides a way of evaluating the impact of regularization on task performance. In this work, we evaluated the effect of total variation (TV) and wavelet regularization on human detection of signals with a varying background and validated a model observer in predicting human performance. Human observer studies used two-alternative forced choice (2-AFC) trials with a small signal known exactly task but with varying backgrounds for fluid-attenuated inversion recovery images reconstructed from undersampled multi-coil data. We used a 3.48 undersampling factor with TV and a wavelet sparsity constraints. The sparse difference-of-Gaussians (S-DOG) observer with internal noise was used to model human observer detection. The internal noise for the S-DOG was chosen to match the average percent correct (PC) in 2-AFC studies for four observers using no regularization. That S-DOG model was used to predict the PC of human observers for a range of regularization parameters. We observed a trend that the human observer detection performance remained fairly constant for a broad range of values in the regularization parameter before decreasing at large values. A similar result was found for the normalized ensemble root mean squared error. Without changing the internal noise, the model observer tracked the performance of the human observers as the regularization was increased but overestimated the PC for large amounts of regularization for TV and wavelet sparsity, as well as the combination of both parameters. For the task we studied, the S-DOG observer was able to reasonably predict human performance with both TV and wavelet sparsity regularizers over a broad range of regularization parameters. We observed a trend that task performance remained fairly constant for a range of regularization parameters before decreasing for large amounts of regularization.

RNLFNet: Residual non-local Fourier network for undersampled MRI reconstruction

Magnetic Resonance Imaging (MRI) has been widely applied in medical clinical diagnosis. Generally, obtaining a high spatial resolution MR image takes up to tens of minutes long. Reconstructing MR images from the undersampled k-space data has been playing a crucial role to accelerate MRI. Especially, the deep Convolutional Neural Networks (CNNs) have shown potential to significantly accelerate MRI. However, the receptive field size of CNNs is relatively small and it fails to capture the long-range dependencies. Nowadays, the non-local attention has been successfully applied in vision tasks due to the advantages in capturing long-range dependencies. However, the existing non-local attention generally learns long-range interactions among spatial locations in the spatial domain. It rarely involves in the frequency domain, which are likely to lead to beneficial outcomes. Recently, there are investigations that start to combine Fourier Transform with deep neural networks. In this work, we consider to learn the long-range interactions from the perspective of frequency. Specifically, we design a novel Non-Local Fourier Attention (NLFA) that combines the self-attention mechanism with Fourier Transform to capture the long-range spatial dependencies in the frequency domain. Furthermore, a new deep Residual Non-Local Fourier Network (RNLFNet) constructed with the Non-Local Fourier Attention and Residual Blocks is proposed for accelerated MRI. Such framework focuses on learning the information from both the spatial and frequency domain, which enjoys benefits from modelling both local details and global context between the degraded MR image and ground truth image pairs. The proposed model is evaluated on the MICCAI grand challenge datasets and fastMRI datasets, which significantly boosts the MR image reconstruction performance.

A Generally Regularized Inversion for NMR Applications and Beyond

NMR (Nuclear Magnetic Resonance) technique presents a powerful analytical tool in the fields of chemistry, biology, and material science. The performance of the NMR technique highly relies on post-data processing methods, which are diverse according to different applications. In this paper, we propose a general processing method that can cover a wide range of applications from molecular dynamics study to biomedical engineering. We analyze the computation performance of the method by comparing it to other well-known algorithms and demonstrate its application in various NMR data processing problems, i.e., diffusion-ordered spectroscopy processing, under-sampled MRI (Magnetic Resonance Imaging) reconstruction, Laplace NMR inversion, and spectrum denoising. The results corroborate that the method performs effectively and efficiently compared to state-of-the-art methods. Moreover, we construct the method as a light toolbox, with which the users can perform various kinds of data processing tasks conveniently via graphic interfaces.

Undersampled magnetic resonance image reconstruction based on support prior and deep image prior without pre-training

Magnetic resonance imaging (MRI) method based on deep learning needs large-quantity and high-quality patient-based datasets for pre-training. However, this is a challenge to the clinical applications because it is difficult to obtain a sufficient quantity of patient-based MR datasets due to the limitation of equipment and patient privacy concerns. In this paper, we propose a novel undersampled MRI reconstruction method based on deep learning. This method does not require any pre-training procedures and does not depend on training datasets. The proposed method is inspired by the traditional deep image prior (DIP) framework, and integrates the structure prior and support prior of the target MR image to improve the efficiency of learning. Based on the similarity between the reference image and the target image, the high-resolution reference image obtained in advance is used as the network input, thereby incorporating the structural prior information into network. By taking the coefficient index set of the reference image with large amplitude in the wavelet domain as the known support of the target image, the regularization constraint term is constructed, and the network training is transformed into the optimization process of network parameters. Experimental results show that the proposed method can obtain more accurate reconstructions from undersampled <i>k</i>-space data, and has obvious advantages in preserving tissue features and detailed texture.

Undersampled Magnetic Resonance Image Reconstruction based on Support Prior and Deep Image Prior without Pre-Training

基于深度学习的磁共振成像（Magnetic Resonance Imaging，简称MRI）方法需要大规模、高质量的病患数据样本集进行预训练。然而，由于病患隐私及设备等因素限制，获取大规模、高质量的磁共振数据集在实际临床应用中面临挑战。本文提出一种新的基于深度学习的欠采样磁共振图像重建方法，该方法无需预训练、不依赖训练数据集。本文方法充分利用待重建的目标MR图像的结构先验和支撑先验，并将其引入深度图像先验（Deep Image Prior，简称DIP）框架，从而削减对训练数据集的依赖，提升学习效率。基于参考图像与目标图像的相似性，采用高分辨率参考图像作为深度网络输入，将结构先验信息引入网络；将参考图像在小波域中幅值大的系数索引集作为目标图像的已知支撑集，构造正则化约束项，将网络训练转化为网络参数的最优化求解过程。实验结果表明，本文方法可由欠采样k空间数据重建得到更精确的磁共振图像，且在保留组织特征、细节纹理方面具有明显优势。

SARA-GAN: Self-Attention and Relative Average Discriminator Based Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction.

Research on undersampled magnetic resonance image (MRI) reconstruction can increase the speed of MRI imaging and reduce patient suffering. In this paper, an undersampled MRI reconstruction method based on Generative Adversarial Networks with the Self-Attention mechanism and the Relative Average discriminator (SARA-GAN) is proposed. In our SARA-GAN, the relative average discriminator theory is applied to make full use of the prior knowledge, in which half of the input data of the discriminator is true and half is fake. At the same time, a self-attention mechanism is incorporated into the high-layer of the generator to build long-range dependence of the image, which can overcome the problem of limited convolution kernel size. Besides, spectral normalization is employed to stabilize the training process. Compared with three widely used GAN-based MRI reconstruction methods, i.e., DAGAN, DAWGAN, and DAWGAN-GP, the proposed method can obtain a higher peak signal-to-noise ratio (PSNR) and structural similarity index measure(SSIM), and the details of the reconstructed image are more abundant and more realistic for further clinical scrutinization and diagnostic tasks.

Triple-D network for efficient undersampled magnetic resonance images reconstruction

Compressed sensing (CS) theory can help accelerate magnetic resonance imaging (MRI) by sampling partial k-space measurements. However, conventional optimization-based CS-MRI methods are often time-consuming and are based on fixed transform or shallow image dictionaries, which limits modeling capabilities. Recently, deep learning models have been used to solve the CS-MRI problem. However, recent researches have focused on modeling in image domain, and the potential of k-space modeling capability has not been utilized seriously. In this paper, we propose a deep model called Dual Domain Dense network (Triple-D network), which consisted of some k-space and image domain sub-network. These sub-networks are connected with dense connections, which can utilize feature maps at different levels to enhance performance. To further promote model capabilities, we use two strategies: multi-supervision strategies, which can avoid loss of supervision information; channel-wise attention layer (CA layer), which can adaptively adjust the weight of the feature map. Experimental results show that the proposed Triple-D network provides promising performance in CS-MRI, and it can effectively work on different sampling trajectories and noisy settings.

IKWI-net: A cross-domain convolutional neural network for undersampled magnetic resonance image reconstruction

Magnetic resonance imaging (MRI) is widely used to get the information of anatomical structure and physiological function with the advantages of high resolution and non-invasive scanning. But the long acquisition time limits its application. To reduce the time consumption of MRI, compressed sensing (CS) theory has been proposed to reconstruct MRI images from undersampled k-space data. But conventional CS methods mostly use iterative methods that take lots of time. Recently, deep learning methods are proposed to achieve faster reconstruction, but most of them only pay attention to a single domain, such as the image domain or k-space. To take advantage of the feature representation in different domains, we propose a cross-domain method based on deep learning, which first uses convolutional neural networks (CNNs) in the image domain, k-space and wavelet domain simultaneously. The combined order of the three domains is also first studied in this work, which has a significant effect on reconstruction. The proposed IKWI-net achieves the best performance in various combinations, which utilizes CNNs in the image domain, k-space, wavelet domain and image domain sequentially. Compared with several deep learning methods, experiments show it also achieves mean improvements of 0.91 dB in peak signal-to-noise ratio (PSNR) and 0.005 in structural similarity (SSIM).

High-dimensional embedding network derived prior for compressive sensing MRI reconstruction.

Although recent deep learning methodology has shown promising performance in fast imaging, the network needs to be retrained for specific sampling patterns and ratios. Therefore, how to explore the network as a general prior and leverage it into the observation constraint flexibly is urgent. In this work, we present a multi-channel enhanced Deep Mean-Shift Prior (MEDMSP) to address the highly under-sampled magnetic resonance imaging reconstruction problem. By extending the naive DMSP via integration of multi-model aggregation and multi-channel network learning, a high-dimensional embedding network derived prior is formed. Then, we apply the learned prior to single-channel image reconstruction via variable augmentation technique. The resulting model is tackled by proximal gradient descent and alternative iteration. Experimental results under various sampling trajectories and acceleration factors consistently demonstrated the superiority of the proposed prior.

Region-of-interest undersampled MRI reconstruction: A deep convolutional neural network approach

Compressive sensing enables fast magnetic resonance imaging (MRI) reconstruction with undersampled k-space data. However, in most existing MRI reconstruction models, the whole MR image is targeted and reconstructed without taking specific tissue regions into consideration. This may fails to emphasize the reconstruction accuracy on important and region-of-interest (ROI) tissues for diagnosis. In some ROI-based MRI reconstruction models, the ROI mask is extracted by human experts in advance, which is laborious when the MRI datasets are too large. In this paper, we propose a deep neural network architecture for ROI MRI reconstruction called ROIRecNet to improve reconstruction accuracy of the ROI regions in under-sampled MRI. In the model, we obtain the ROI masks by feeding an initially reconstructed MRI from a pre-trained MRI reconstruction network (RecNet) to a pre-trained MRI segmentation network (ROINet). Then we fine-tune the RecNet with a binary weighted ℓ2 loss function using the produced ROI mask. The resulting ROIRecNet can offer more focus on the ROI. We test the model on the MRBrainS13 dataset with different brain tissues being ROIs. The experiment shows the proposed ROIRecNet can significantly improve the reconstruction quality of the region of interest.

Deep learning for undersampled MRI reconstruction

This paper presents a deep learning method for faster magnetic resonance imaging (MRI) by reducing k-space data with sub-Nyquist sampling strategies and provides a rationale for why the proposed approach works well. Uniform subsampling is used in the time-consuming phase-encoding direction to capture high-resolution image information, while permitting the image-folding problem dictated by the Poisson summation formula. To deal with the localization uncertainty due to image folding, a small number of low-frequency k-space data are added. Training the deep learning net involves input and output images that are pairs of the Fourier transforms of the subsampled and fully sampled k-space data. Our experiments show the remarkable performance of the proposed method; only 29 of the k-space data can generate images of high quality as effectively as standard MRI reconstruction with the fully sampled data.

Gradient-Based Low Rank Method for Highly Undersampled Magnetic Resonance Imaging Reconstruction

Recently, exploiting low rank property of the data accomplished by the non-convex optimization has shown great potential to decrease measurements for compressed sensing. In this paper, the low rank regularization is adopted to gradient similarity minimization, and applied for highly undersampled magnetic resonance imaging (MRI) reconstruction, termed gradient-based low rank MRI reconstruction (GLRMRI). In the proposed method, by incorporating the spatially adaptive iterative singular-value thresholding (SAIST) to optimize our gradient scheme, the deterministic annealing iterates the procedure efficiently and superior reconstruction performance is achieved. Extensive experimental results have consistently demonstrated that GLRMRI recovers both realvalued MR images and complex-valued MR data accurately, especially in the edge preserving perspective, and outperforms the current state-of-the-art approaches in terms of higher peak signal to noise ratio (PSNR) and lower high-frequency error norm (HFEN) values.

Fast Compressed Sensing MRI Based on Complex Double-Density Dual-Tree Discrete Wavelet Transform.

Compressed sensing (CS) has been applied to accelerate magnetic resonance imaging (MRI) for many years. Due to the lack of translation invariance of the wavelet basis, undersampled MRI reconstruction based on discrete wavelet transform may result in serious artifacts. In this paper, we propose a CS-based reconstruction scheme, which combines complex double-density dual-tree discrete wavelet transform (CDDDT-DWT) with fast iterative shrinkage/soft thresholding algorithm (FISTA) to efficiently reduce such visual artifacts. The CDDDT-DWT has the characteristics of shift invariance, high degree, and a good directional selectivity. In addition, FISTA has an excellent convergence rate, and the design of FISTA is simple. Compared with conventional CS-based reconstruction methods, the experimental results demonstrate that this novel approach achieves higher peak signal-to-noise ratio (PSNR), larger signal-to-noise ratio (SNR), better structural similarity index (SSIM), and lower relative error.

Highly undersampled MR image reconstruction using an improved dual-dictionary learning method with self-adaptive dictionaries.

Dual-dictionary learning (Dual-DL) method utilizes both a low-resolution dictionary and a high-resolution dictionary, which are co-trained for sparse coding and image updating, respectively. It can effectively exploit a priori knowledge regarding the typical structures, specific features, and local details of training sets images. The prior knowledge helps to improve the reconstruction quality greatly. This method has been successfully applied in magnetic resonance (MR) image reconstruction. However, it relies heavily on the training sets, and dictionaries are fixed and nonadaptive. In this research, we improve Dual-DL by using self-adaptive dictionaries. The low- and high-resolution dictionaries are updated correspondingly along with the image updating stage to ensure their self-adaptivity. The updated dictionaries incorporate both the prior information of the training sets and the test image directly. Both dictionaries feature improved adaptability. Experimental results demonstrate that the proposed method can efficiently and significantly improve the quality and robustness of MR image reconstruction.

Two-level Bregman method for MRI reconstruction with graph regularized sparse coding

In this paper, a two-level Bregman method is presented with graph regularized sparse coding for highly undersampled magnetic resonance image reconstruction. The graph regularized sparse coding is incorporated with the two-level Bregman iterative procedure which enforces the sampled data constraints in the outer level and updates dictionary and sparse representation in the inner level. Graph regularized sparse coding and simple dictionary updating applied in the inner minimization make the proposed algorithm converge with a relatively small number of iterations. Experimental results demonstrate that the proposed algorithm can consistently reconstruct both simulated MR images and real MR data efficiently, and outperforms the current state-of-the-art approaches in terms of visual comparisons and quantitative measures.