Which GAN? A comparative study of generative adversarial network-based fast MRI reconstruction.

In this paper, we present a fast iterative magnetic resonance imaging (MRI) reconstruction algorithm taking advantage of the prevailing GPGPU programming paradigm. In clinical environment, MRI reconstruction is usually performed via fast Fourier transform (FFT). However, imaging artifacts (i.e. signal loss) resulting from susceptibility-induced magnetic field inhomogeneities degrade the quality of reconstructed images. These artifacts must be addressed using accurate modeling of the physics of the system coupled with iterative reconstruction. We have developed a reconstruction algorithm with improved image quality at the expense of computation time and hence an implementation on GPUs achieving significant speedup. In this work, we extend our previous work on GPU implementation by adding several new features. First, we enable Sensitivity Encoding for Fast MRI (SENSE) reconstruction (from data acquired using a multi-receiver coil array) which can reduce the acquisition time. Besides, we have implemented a GPU-based total variation regularization in our SENSE reconstruction framework. In this paper, we describe the different optimizations employed from levels of algorithm, program code structures, and specific architecture performance tuning, featuring both our MRI reconstruction algorithm and GPU hardware specifics. Results show that the current GPU implementation produces accurate image estimates while significantly accelerating the reconstruction.

DiffGAN: An adversarial diffusion model with local transformer for MRI reconstruction

Utility of fast MRIs in pediatric elbow injuries

In recent years, deep learning has demonstrated great potential in accelerating Magnetic Resonance Imaging (MRI). However, most existing works simply consider MRI reconstruction as an image-to-image task, or typically use a single and identical network for both frequency and image domain reconstruction simultaneously, without taking into consideration the data characteristics and internal interactions of the two domains, which leads to ineffective learning of the image reconstruction models. In this study, we proposed an attention-based, dual-domain reconstruction network to facilitate fast and accurate MRI reconstruction by adaptively learning different data characteristics in the frequency domain and image domain. In response to the inhomogeneous energy distribution in K-space, we designed a densely connected multi-attention network for frequency domain reconstruction. For image aliasing at low sampling rates, we developed a residual encoder-decoder network with an attention module for the image domain reconstruction. The overall network contains two parallel and interactive branches that simultaneously perform on K-space and image data, with the data fusion modules to fuse dual domain information in each reconstruction layer, and the long skip connections to transfer inter-layer information. We have evaluated our method on two datasets. A series of comparative and ablation experiments demonstrate that our method effectively reconstructs images from undersampled K-space data, achieving better image reconstruction performance and restoring significant textures of brain slices.

The deep learning method is an efficient solution for improving the quality of undersampled magnetic resonance (MR) image reconstruction while reducing lengthy data acquisition. Most deep learning methods neglect the mutual constraints between the real and imaginary components of complex-valued k-space data. In this paper, a new complex-valued convolutional neural network, namely, Dense-U-Dense Net (DUD-Net), is proposed to interpolate the undersampled k-space data and reconstruct MR images. The proposed network comprises dense layers, U-Net, and other dense layers in sequence. The dense layers are used to simulate the mutual constraints between real and imaginary components, and U-Net performs feature sparsity and interpolation estimation for k-space data. Two MRI datasets were used to evaluate the proposed method: brain magnitude-only MR images and knee complex-valued k-space data. Several operations were conducted for data preprocessing. First, the complex-valued MR images were synthesized by phase modulation on magnitude-only images. Second, a radial trajectory based on the golden angle was used for k-space undersampling, whereby a reversible normalization method was proposed to balance the distribution of positive and negative values in k-space data. The optimal performance of DUD-Net was demonstrated based on a quantitative evaluation of inter-method and intra-method comparisons. When compared with other methods, significant improvements were achieved, PSNRs were increased by 10.78 and 5.74dB, whereas RMSEs were decreased by 71.53% and 30.31% for magnitude and phase image, respectively. It is concluded that DUD-Net significantly improves the performance of MR image reconstruction.

Radial encoding is often performed for fast data acquisition in magnetic resonance imaging (MRI). Therefore, the gridding method, which is a kind of algorithm for Fast Fourier Transform, is widely used in fast MRI reconstruction. In this paper, an improved gridding method has been utilized to 2D MRI reconstruction, which precomputes an 1D finely sampled table of a high-accuracy interpolator and then uses separable bilinear interpolation by look-up table. Experimental comparisons are made by assessing the performance of the direct reconstruction, the conventional KB gridding and the proposed method. The experimental results show that the proposed method provides high accuracy, fast computation, and dramatic memory saving.

Deep learning-based magnetic resonance imaging (MRI) reconstruction obtains extremely high reconstruction performance by training with large amounts of data. However, the acquisition of fully sampled MRI data is expensive and time-consuming, making it difficult to obtain large amounts of fully sampled data. This not only poses a challenge for models that require more fully sampled data for training but also limits the generalization ability of network models. To address the above problems, we propose a semi-supervised MRI reconstruction algorithm based on migration learning by analyzing the characteristics of under-sampled MRI reconstruction. To address the lack of data scarcity and generalization in the reconstruction process. The model fuses shallow features extracted from the convolutional layer and deep features obtained from the Swin Transformer Block (STB) to greatly improve the reconstruction capability of the network. However, the process of distillation cannot predict the goodness of the knowledge transferred, which hinders the performance of the semi-supervised algorithm. We further propose the use of privilege loss as a way to improve the distillation of useful knowledge. Experimental results show that student networks trained by this algorithm are able to rival supervised teacher networks and outperform unsupervised network models in brain data reconstruction.KeywordsMagnetic resonance imagingSwin transformerKnowledge distillationPrivileged information

Single image super-resolution (SISR) reconstruction for magnetic resonance imaging (MRI) has generated significant interest because of its potential to not only speed up imaging but to improve quantitative processing and analysis of available image data. Generative Adversarial Networks (GAN) have proven to perform well in image recovery tasks. In this work, we followed the GAN framework and developed a generator coupled with discriminator to tackle the task of 3D SISR on T1 brain MRI images. We developed a novel 3D memory-efficient residual-dense block generator (MRDG) that achieves state-of-the-art performance in terms of SSIM (Structural Similarity), PSNR (Peak Signal to Noise Ratio) and NRMSE (Normalized Root Mean Squared Error) metrics. We also designed a pyramid pooling discriminator (PPD) to recover details on different size scales simultaneously. Finally, we introduced model blending, a simple and computational efficient method to balance between image and texture quality in the final output, to the task of SISR on 3D images.

Compressive sensing magnetic resonance (MR) imaging is aimed at achieving high-quality MR image reconstruction by undersampling K-space data. It is crucial to explore prior information since compressive sensing MR imaging relies heavily on some prior assumptions, such as signal's sparse property. In this study, in order to explore the prior information fully, an improved MR image reconstruction model based on compressive sensing theory is proposed, named reference image MR imaging with adaptive tight frame. In the proposed model, an adaptive tight frame is involved to explore the sparse prior information adapt to MR images and the similarity prior information to the target image. Meanwhile, improved adaptive weighting parameters are used to trade off the sparsity between the regions with much similarity and that of little similarity. In addition, the smoothing-based fast iterative shrinkage-threshold algorithm is utilised to tackle the optimisation problem so as to speed up imaging. The experimental results demonstrate that the proposed MR image reconstruction method outperforms some state-of-the-art methods in terms of quantitative results.

In recent years, brain health has received increasing attention, but conventional acquisition of brain MRI (magnetic resonance imaging) images still suffer from issues such as missing data, artifacts, and high costs, which hinders research and diagnosis. With the application of deep learning in medical image synthesis, low-cost, efficient, and high-quality medical MRI synthesis techniques have become a prominent research focus and have gradually matured. However, traditional methods for synthesizing magnetic resonance imaging (MRI) mostly rely on generative adversarial networks, which require fine-tuning of parameters and learning rates to achieve stringent Nash equilibrium conditions, leading to problems such as gradient explosions and mode collapse. Building upon the latest research in synthetic models DDPM (denoising diffusion probabilistic model), we propose a novel approach for 2D brain MRI image synthesis based on a lightweight denoising diffusion probabilistic model. This method improves the attention module in the denoising diffusion probabilistic model to make it more lightweight. Additionally, we adopt the smooth L1 loss function as a replacement for the traditional mean absolute error (L1 loss) by comparing the error between the 2D brain MRI images with added noise and the real noise for training the model. Finally, we validate the proposed model on the MRI Brain Tumor Classification dataset, demonstrating that it achieves high-quality synthesis results while significantly reducing the parameter count of the DDPM model.

EVOLVE: Learning volume-adaptive phases for fast 3D magnetic resonance scan and image reconstruction

This paper introduces an efficient algorithm for magnetic resonance (MR) image reconstruction. The proposed method minimizes a linear combination of nonlocal total variation and least-square data-fitting term to reconstruct the MR images from undersampled k-space data. The nonlocal total variation is taken as the L 1-regularization functional and solved using Split Bregman iteration. The proposed algorithm is compared with previous methods in terms of the reconstruction accuracy and computational complexity. The comparison results demonstrate the superiority of the proposed algorithm for compressed MR image reconstruction.

Medical image reconstruction is typically an ill-posed inverse problem. In order to address such ill-posed problems, the prior distribution of the sought after object property is usually incorporated by means of some sparsity-promoting regularization. Recently, prior distributions for images estimated using generative adversarial networks (GANs) have shown great promise in regularizing some of these image reconstruction problems. In this work, we apply an image-adaptive GAN-based reconstruction method (IAGAN) to reconstruct high fidelity images from incomplete medical imaging data. It is observed that the IAGAN method can potentially recover fine structures in the object that are relevant for medical diagnosis but may be oversmoothed in reconstructions with traditional sparsity-promoting regularization.

Magnetic Resonance Imaging (MRI) is one of the most commonly used modalities in medical imaging, and one of the main limitations is its slow scanning and reconstruction speed. Recently, deep learning used for compressed sensing (CS) methods have been proposed to accelerate the acquisition by undersampling in the K-space and reconstruct images with neural networks. However, there are still some challenges remained: First, directly training networks based on L1/L2 distance to the target fully sampled images may lead to fuzzy reconstruction images because L1/L2 loss only enforces the overall image or patch similarity, but does not consider the local details such as anatomical sharpness. Second, Generative Adversarial Networks (GAN) can partially solve this problem. The undersampling image gets the latent space through the encoder, and the image is reconstructed by the decoder based on GAN loss, but it may generate unrealistic details by lacking of constraints in K-space domain. Third, most of the networks after training are fixed and have limited adaptation capability in the inference time, and the patient-specific information cannot be effectively used. To resolve these challenges, we proposed a new compressed sensing GAN reconstruction method, and there are two main contributions: (1) We proposed a encoder-decoder structure, which guided GAN optimization strategy data-consistency in latent space to improve the reconstruction quality such as preserving more local details and improving the anatomical sharpness while constraining GAN to follow the data distribution in the K-space to prevent the unrealistic details. (2) An online update strategy is used to find the best representation in the latent space for the underlying patient, and the reconstruct result can be further improved by incorporating the patient-specific information. Extensive experimental results show the effectiveness of our method. KeywordsMRI reconstructionData-consistencyLatent spaceOnline update

An approach to Magnetic Resonance (MR) image reconstruction from undersampled data is proposed. Undersampling artifacts are removed using an iterative thresholding algorithm applied to nonlinearly transformed image block arrays. Each block array is transformed using kernel principal component analysis where the contribution of each image block to the transform depends in a nonlinear fashion on the distance to other image blocks. Elimination of undersampling artifacts is achieved by conventional principal component analysis in the nonlinear transform domain, projection onto the main components and back-mapping into the image domain. Iterative image reconstruction is performed by interleaving the proposed undersampling artifact removal step and gradient updates enforcing consistency with acquired k-space data. The algorithm is evaluated using retrospectively undersampled MR cardiac cine data and compared to k-t SPARSE-SENSE, block matching with spatial Fourier filtering and k-t ℓ1-SPIRiT reconstruction. Evaluation of image quality and root-mean-squared-error (RMSE) reveal improved image reconstruction for up to 8-fold undersampled data with the proposed approach relative to k-t SPARSE-SENSE, block matching with spatial Fourier filtering and k-t ℓ1-SPIRiT. In conclusion, block matching and kernel methods can be used for effective removal of undersampling artifacts in MR image reconstruction and outperform methods using standard compressed sensing and ℓ1-regularized parallel imaging methods.