Magnetic Resonance Imaging Reconstruction Research Articles

SR-Net: A sequence offset fusion net and refine net for undersampled multislice MR image reconstruction

Background and objective: The study of deep learning-based fast magnetic resonance imaging (MRI) reconstruction methods has become popular in recent years. However, there is still a challenge when MRI results undersample large acceleration factors. The objective of this study was to improve the reconstruction quality of undersampled MR images by exploring data redundancy among slices.Methods: There are two aspects of redundancy in multislice MR images including correlations inside a single slice and correlations among slices. Thus, we built two subnets for the two kinds of redundancy. For correlations among slices, we built a bidirectional recurrent convolutional neural network, named Sequence Offset Fusion Net (S-Net). In S-Net, we used a deformable convolution module to construct a neighbor slice feature extractor. For the correlation inside a single slice, we built a Refine Net (R-Net), which has 5 layers of 2D convolutions. In addition, we used a data consistency (DC) operation to maintain data fidelity in k-space. Finally, we treated the reconstruction task as a dealiasing problem in the image domain, and S-Net and R-Net are applied alternately and iteratively to generate the final reconstructions.Results: The proposed algorithm was evaluated using two online public MRI datasets. Compared with several state-of-the-art methods, the proposed method achieved better reconstruction results in terms of dealiasing and restoring tissue structure. Moreover, with over 14 slices per second reconstruction speed on 256x256 pixel images, the proposed method can meet the need for real-time processing.Conclusion: With spatial correlation among slices as additional prior information, the proposed method dramatically improves the reconstruction quality of undersampled MR images.

Effects of Nano-Sulfides on Learning and Memory Abilities and Expression of Related Genes in Cyclic Adenosine Monophosphate-cAMP Response Element Binding-Brain-Derived Neurotrophic Factor Pathway in Rats.

In recent years, with the rapid development of nano-biotechnology and biomedicine, people have provided new ideas and methods for disease diagnosis and treatment. Nano-sulfides with unique two-dimensional structures and special physicochemical properties have begun to be applied to biology and medical field. Relevant research results show that nano-sulfides have good effects in tumor photothermal treatment, in vivo multimodal imaging, antitumor drug delivery, biosensors and tissue engineering, showing their potential application value. In view of the broad application prospects of nano-sulfides in the field of nano-biomedicine, in the image reconstruction stage, before starting to use artificial intelligence algorithm models, first explore the application of iterative optimization algorithms in the process of magnetic resonance image reconstruction. Taking magnetic resonance imaging as an example, for the detected ligament trauma area, we use learned an artificial intelligence model for diagnosis of multiple ligament trauma of the knee joint and postoperative femoral nerve block.

K sparse autoencoder-based accelerated reconstruction of magnetic resonance imaging

Owing to the sequential collection of phase encoded data in k-space, magnetic resonance (MR) imaging suffers from long acquisition time. One possible measure to reduce the long acquisition time is to reconstruct MR image using a subset of k-space MR data rather than the complete set. In this work, we propose to implement a K sparse autoencoder model for reconstruction of MR image from undersampled k-space data. Autoencoder models, which have shown great ability in capturing the complex features of input data, can be used to reconstruct high-quality MR image. The reconstruction process involved solving an optimization problem whose solution was expected to satisfy the data consistency and also lie in close proximity to the output space of trained K sparse autoencoder. Observing the effect of sparsity value enforced by K sparse autoencoder on the reconstructed output, we implemented the cascaded form of reconstruction, incorporating three K sparse autoencoders with three different K values. Using MR-PD and MR-T1 images, reconstruction performance of the proposed approach was compared with those of the conventional reconstruction approaches. The quantitative as well as the qualitative analysis of the reconstructed images, obtained using the proposed approach, validates the efficiency of the proposed approach.

Denoising auto-encoding priors in undecimated wavelet domain for MR image reconstruction

Compressive sensing is an impressive approach for fast MRI. It aims at reconstructing MR image using only a few under-sampled data in k-space, enhancing the efficiency of the data acquisition. In this study, we propose to learn priors based on undecimated wavelet transform and an iterative image reconstruction algorithm. At the stage of prior learning, transformed feature images obtained by undecimated wavelet transform are stacked as an input of denoising autoencoder network (DAE). The highly redundant and multi-scale input enables the correlation of feature images at different channels, which allows a robust network-driven prior. At the iterative reconstruction, the transformed DAE prior is incorporated into the classical iterative procedure by means of proximal gradient algorithm. Experimental comparisons on different sampling trajectories and ratios validated the great potential of the presented algorithm.

Brain MR image super-resolution via a deep convolutional neural network with multi-unit upsampling learning

Image super-resolution (SR) is a preferred approach to achieving high-resolution MR images because they are typically achieved in real world at the expense of reduced signal-to-noise ratio and/or increased imaging time. A novel deep residual network (DRN) with multi-unit upsampling learning is designed for MR image SR. The multi-unit upsampling learning mechanism involves multi-unit upsampling and adaptive learning. The designed DRN performs the SR task in the LR space to accelerate the network via an upsampling strategy at the late stage of the network architecture. A multi-unit upsampling strategy is proposed to transmit lost information in each residual unit and to accumulate the upscaled feature maps achieved by different residual units. An adaptive learning strategy following multi-unit upsampling is utilized to potentially discover the contributions of these upscaled feature maps to high-resolution MR image reconstruction by adaptively assigning different significance weights to the intermediate predictions. The proposed DRN achieves a fair good reconstruction performance, which is superior to some state-of-the-art deep-learning-based methods.

High quality and fast compressed sensing MRI reconstruction via edge-enhanced dual discriminator generative adversarial network

Generative adversarial networks (GAN) are widely used for fast compressed sensing magnetic resonance imaging (CSMRI) reconstruction. However, most existing methods are difficult to make an effective trade-off between abstract global high-level features and edge features. It easily causes problems, such as significant remaining aliasing artifacts and clearly over-smoothed reconstruction details. To tackle these issues, we propose a novel edge-enhanced dual discriminator generative adversarial network architecture called EDDGAN for CSMRI reconstruction with high quality. In this model, we extract effective edge features by fusing edge information from different depths. Then, leveraging the relationship between abstract global high-level features and edge features, a three-player game is introduced to control the hallucination of details and stabilize the training process. The resulting EDDGAN can offer more focus on edge restoration and de-aliasing. Extensive experimental results demonstrate that our method consistently outperforms state-of-the-art methods and obtains reconstructed images with rich edge details. In addition, our method also shows remarkable generalization, and its time consumption for each 256 × 256 image reconstruction is approximately 8.39 ms.

Increased tibiofemoral rotation on MRI with increasing clinical severity of patellar instability.

Tibiofemoral rotation through the knee joint, specifically relative external tibial rotation, has been identified as a potential contributing factor to patellar instability. The purpose of this study is to investigate the relationship between severity of instability with degree of tibiofemoral rotation in three clinical cohorts: fixed or obligatory dislocators (in which the patella either is constantly laterally dislocated or laterally dislocates with every instance of knee flexion, respectively), standard traumatic instability patients, and normal controls. A retrospective study was performed with three cohorts from April 2009 to February 2019: fixed or obligatory dislocators, standard traumatic instability patients, and controls with normal magnetic resonance imaging (MRI) of the knee. All fixed or obligatory dislocation patients from the study time frame were analyzed; controls and standard traumatic instability patients were randomly selected. Inclusion criteria were age under 18years and qualifying diagnosis; exclusion criteria were outside institution MRI and previous MPFL reconstruction or tibial tubercle osteotomy. Tibiofemoral rotation was measured blindly on initial axial MRI using the posterior femoral and tibial condylar lines. Tibial tubercle to trochlear groove distance (TT-TG) was measured. Intraclass correlation coefficient (ICC) was calculated among four measurers. A total of 100 patients were included, 20 fixed or obligatory dislocators, 40 standard traumatic instability patients, and 40 controls. Median age was 13.2years (range 10-17years), with 55 females. Age was significantly higher in the standard traumatic instability group than both the control (p < 0.001) and fixed or obligatory dislocator groups (p = 0.003). ICC for TT-TG and tibiofemoral rotation were 0.92 and 0.96, respectively. Fixed or obligatory dislocator patients averaged 8.5° external tibiofemoral rotation, standard traumatic instability patients 1.6° external tibiofemoral rotation, and controls 3.8° internal tibiofemoral rotation. Both tibiofemoral rotation and TT-TG were highest in the fixed or obligatory dislocator cohort, followed by the standard traumatic instability cohort, and lowest in the controls (p < 0.0001 for tibiofemoral rotation and TT-TG). Multivariate analysis showed no correlation between age and tibiofemoral rotation. Measurement of tibiofemoral rotation was reproducible with excellent interrater reliability. The degree of tibiofemoral rotation is correlated with severity of patellar instability, with the greatest external tibiofemoral rotation in fixed or obligatory dislocator patients, followed by standard traumatic instability patients, and slight internal tibiofemoral rotation in controls. High external tibiofemoral rotation may be an important pathoanatomic factor in fixed or obligatory dislocators, and with further understanding may become a prognostic factor or surgical target. III.

PIC-GAN: A Parallel Imaging Coupled Generative Adversarial Network for Accelerated Multi-Channel MRI Reconstruction.

In this study, we proposed a model combing parallel imaging (PI) with generative adversarial network (GAN) architecture (PIC-GAN) for accelerated multi-channel magnetic resonance imaging (MRI) reconstruction. This model integrated data fidelity and regularization terms into the generator to benefit from multi-coils information and provide an “end-to-end” reconstruction. Besides, to better preserve image details during reconstruction, we combined the adversarial loss with pixel-wise loss in both image and frequency domains. The proposed PIC-GAN framework was evaluated on abdominal and knee MRI images using 2, 4 and 6-fold accelerations with different undersampling patterns. The performance of the PIC-GAN was compared to the sparsity-based parallel imaging (L1-ESPIRiT), the variational network (VN), and conventional GAN with single-channel images as input (zero-filled (ZF)-GAN). Experimental results show that our PIC-GAN can effectively reconstruct multi-channel MR images at a low noise level and improved structure similarity of the reconstructed images. PIC-GAN has yielded the lowest Normalized Mean Square Error (in ) (PIC-GAN: 0.58 ± 0.37, ZF-GAN: 1.93 ± 1.41, VN: 1.87 ± 1.28, L1-ESPIRiT: 2.49 ± 1.04 for abdominal MRI data and PIC-GAN: 0.80 ± 0.26, ZF-GAN: 0.93 ± 0.29, VN:1.18 ± 0.31, L1-ESPIRiT: 1.28 ± 0.24 for knee MRI data) and the highest Peak Signal to Noise Ratio (PIC-GAN: 34.43 ± 1.92, ZF-GAN: 31.45 ± 4.0, VN: 29.26 ± 2.98, L1-ESPIRiT: 25.40 ± 1.88 for abdominal MRI data and PIC-GAN: 34.10 ± 1.09, ZF-GAN: 31.47 ± 1.05, VN: 30.01 ± 1.01, L1-ESPIRiT: 28.01 ± 0.98 for knee MRI data) compared to ZF-GAN, VN and L1-ESPIRiT with an under-sampling factor of 6. The proposed PIC-GAN framework has shown superior reconstruction performance in terms of reducing aliasing artifacts and restoring tissue structures as compared to other conventional and state-of-the-art reconstruction methods.

Segmented Multistage Reconstruction of Magnetic Resonance Images

Segmented Multistage Reconstruction of Magnetic Resonance Images

Model Adaptation for Inverse Problems in Imaging

Deep neural networks have been applied successfully to a wide variety of inverse problems arising in computational imaging. These networks are typically trained using a forward model that describes the measurement process to be inverted, which is often incorporated directly into the network itself. However, these approaches are sensitive to changes in the forward model: if at test time the forward model varies (even slightly) from the one the network was trained for, the reconstruction performance can degrade substantially. Given a network trained to solve an initial inverse problem with a known forward model, we propose two novel procedures that adapt the network to a change in the forward model, even without full knowledge of the change. Our approaches do not require access to more labeled data (i.e., ground truth images). We show these simple model adaptation approaches achieve empirical success in a variety of inverse problems, including deblurring, super-resolution, and undersampled image reconstruction in magnetic resonance imaging.

Parallel magnetic resonance imaging acceleration with a hybrid sensing approach.

In magnetic resonance imaging (MRI), the scan time for acquiring an image is relatively long, resulting in patient uncomfortable and error artifacts. Fortunately, the compressed sensing (CS) and parallel magnetic resonance imaging (pMRI) can reduce the scan time of the MRI without significantly compromising the quality of the images. It has been found that the combination of pMRI and CS can better improve the image reconstruction, which will accelerate the speed of MRI acquisition because the number of measurements is much smaller than that by pMRI. In this paper, we propose combining a combined CS method and pMRI for better accelerating the MRI acquisition. In the combined CS method, the under-sampled data of the K-space is performed by taking both regular sampling and traditional random under-sampling approaches. MRI image reconstruction is then performed by using nonlinear conjugate gradient optimization. The performance of the proposed method is simulated and evaluated using the reconstruction error measure, the universal image quality Q-index, and the peak signal-to-noise ratio (PSNR). The numerical simulations confirmed that, the average error, the Q index, and the PSNR ratio of the appointed scheme are remarkably improved up to 59, 63, and 39% respectively as compared to the traditional scheme. For the first time, instead of using highly computational approaches, a simple and efficient combination of CS and pMRI is proposed for the better MRI reconstruction. These findings are very meaningful for reducing the imaging time of MRI systems.

Learning-based Algorithms for Inverse Problems in MR Image Reconstruction and Quantitative Perfusion Imaging

Learning-based Algorithms for Inverse Problems in MR Image Reconstruction and Quantitative Perfusion Imaging

Denoising Medical Images Using Deep Learning in IoT Environment

Medical Resonance Imaging (MRI) is a noninvasive, nonradioactive, and meticulous diagnostic modality capability in the field of medical imaging. However, the efficiency of MR image reconstruction is affected by its bulky image sets and slow process implementation. Therefore, to obtain a high-quality reconstructed image we presented a sparse aware noise removal technique that uses convolution neural network (SANR_CNN) for eliminating noise and improving the MR image reconstruction quality. The proposed noise removal or denoising technique adopts a fast CNN architecture that aids in training larger datasets with improved quality, and SARN algorithm is used for building a dictionary learning technique for denoising large image datasets. The proposed SANR_CNN model also preserves the details and edges in the image during reconstruction. An experiment was conducted to analyze the performance of SANR_CNN in a few existing models in regard with peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mean squared error (MSE). The proposed SANR_CNN model achieved higher PSNR, SSIM, and MSE efficiency than the other noise removal techniques. The proposed architecture also provides transmission of these denoised medical images through secured IoT architecture.

Self-Organized Maps and High-Frequency Image Detail for MRI Image Enhancement

Magnetic resonance imaging (MRI) is a medical technology that uses powerful magnets, radio waves, and a computer to produce images of the body’s internal organs. The patient should be quiet and motionless during the scanning period, as unavoidable movements, such as breathing and heart rate, cause motion artifacts in the image, which cause contrast instability and low-resolution MRI images. Imaging in the clinical setting is performed at low resolution because the scanning time for high-resolution MR imaging would be very long and cumbersome, and imaging is also very expensive. Learning-based image superresolution methods can reconstruct MR images with optimal quality and resolution. However, these methods have problems such as the inability to find the intrinsic relationship between low- and high-resolution image patches in the training dictionary, specification of the proper amount of error in the training and testing stage due to variability in MR image contrast, inability to reconstruct objects by smoothed edges, and use of the backpropagation method in updating their weight vectors. In this paper, we propose a new superresolution method according to competitive learning-based approaches to overcome the problems of previous superresolution methods, which do not have the problems and complexities of those methods. The proposed method includes self-organizing maps as a preprocessor, the nearest neighbor algorithm as a classifier, and a high-frequency filter as a high-frequency image detail extractor. We constructed a single external dictionary from a combination of low-resolution and high-resolution feature patches and trained our SOM network. Next, we reconstruct the high-resolution image by converting the low-resolution input image into feature patch vectors, and for each vector, we find all corresponding neurons in the network and retrieve all their training feature vectors. Next, we train the nearest neighbor algorithm with the recovered vectors plus the input vector and find the best similarity vector to the input vector. After finding all the best similarity vectors to the input vectors, we reconstruct our high superresolution image. The proposed image superresolution method in practical experiments was trained, tested, and evaluated by the Div2k dataset and compared with other traditional and state-of-the-art image enhancement methods on various datasets, such as SET5, SET14, BSDS100, and URBAN100, and presented better results with higher accuracy and quality than traditional and state-of-the-art methods, both visually compared to each other by human and computational benchmarks, such as the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), to compare image superresolution algorithms. This method is best for reconstructing high-resolution magnetic resonance images that require high-frequency details and sharp edges with a smooth slope of the imaging objects in their structures. The execution time of the proposed algorithm is slower than that of the other algorithms, so we use GPU hardware and parallel programming techniques to increase the algorithm speed.

Super-resolution reconstruction of brain magnetic resonance images via lightweight autoencoder

Magnetic Resonance Imaging (MRI) is useful to provide detailed anatomical information such as images of tissues and organs within the body that are vital for quantitative image analysis. However, typically the MR images acquired lacks adequate resolution because of the constraints such as patients’ comfort and long sampling duration. Processing the low resolution MRI may lead to an incorrect diagnosis. Therefore, there is a need for super resolution techniques to obtain high resolution MRI images. Single image super resolution (SR) is one of the popular techniques to enhance image quality. Reconstruction based SR technique is a category of single image SR that can reconstruct the low resolution MRI images to high resolution images. Inspired by the advanced deep learning based SR techniques, in this paper we propose an autoencoder based MRI image super resolution technique that performs reconstruction of the high resolution MRI images from low resolution MRI images. Experimental results on synthetic and real brain MRI images show that our autoencoder based SR technique surpasses other state-of-the-art techniques in terms of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), Information Fidelity Criterion (IFC), and computational time.

Research of Sensitivity Encoding Reconstruction for MRI with Non-Cartesian K-Space Trajectories

The Sensitivity Encoding (SENSE) parallel reconstruction scheme for magnetic resonance imaging (MRI) is implemented with non-cartesian sampled k-space trajectories in this paper. SENSE has the special capability to reduce the scanning time for MRI experiments while maintaining the image resolution with under-sampling data sets. In this manner, it has become an increasingly popular technique for multiple MRI data acquisition and image reconstruction schemes. The gridding algorithm is also implemented with SENSE due to its ability in evaluating forward and adjoin operator with non-cartesian sampled data. In this paper, the sensitivity map profile, field map information and the spiral k-space data collected from an array of receiver coils are used to reconstruct unaliased images from under-sampled data. The performance of SENSE with real data set identifies the computational issues to be improved for researched.

Sensitivity Encoding Reconstruction for MRI with Gridding Algorithm

The Sensitivity Encoding (SENSE) parallel reconstruction scheme for magnetic resonance imaging (MRI) is studied and implemented with gridding algorithm in this paper. In this paper, the sensitivity map profile, field map information and the spiral k-space data collected from an array of receiver coils are used to reconstruct un-aliased images from under-sampled data. The gridding algorithm is implemented with SENSE due to its ability in evaluating forward and adjoins operators with non-Cartesian sampled data. This paper also analyzes the performance of SENSE with real data set and identifies the computational issues that need to be improved for further research.

Over-and-Under Complete Convolutional RNN for MRI Reconstruction.

Reconstructing magnetic resonance (MR) images from under-sampled data is a challenging problem due to various artifacts introduced by the under-sampling operation. Recent deep learning-based methods for MR image reconstruction usually leverage a generic auto-encoder architecture which captures low-level features at the initial layers and high-level features at the deeper layers. Such networks focus much on global features which may not be optimal to reconstruct the fully-sampled image. In this paper, we propose an Over-and-Under Complete Convolutional Recurrent Neural Network (OUCR), which consists of an overcomplete and an undercomplete Convolutional Recurrent Neural Network (CRNN). The overcomplete branch gives special attention in learning local structures by restraining the receptive field of the network. Combining it with the undercomplete branch leads to a network which focuses more on low-level features without losing out on the global structures. Extensive experiments on two datasets demonstrate that the proposed method achieves significant improvements over the compressed sensing and popular deep learning-based methods with less number of trainable parameters.

High-Resolution Pelvic MRI Reconstruction Using a Generative Adversarial Network With Attention and Cyclic Loss

Magnetic resonance imaging (MRI) is an important medical imaging modality, but its acquisition speed is quite slow due to the physiological limitations. Recently, super-resolution methods have shown excellent performance in accelerating MRI. In some circumstances, it is difficult to obtain high-resolution images even with prolonged scan time. Therefore, we proposed a novel super-resolution method that uses a generative adversarial network with cyclic loss and attention mechanism to generate high-resolution MR images from low-resolution MR images by upsampling factors of 2× and 4×. We implemented our model on pelvic images from healthy subjects as training and validation data, while those data from patients were used for testing. The MR dataset was obtained using different imaging sequences, including T2, T2W SPAIR, and mDIXON-W. Four methods, i.e., BICUBIC, SRCNN, SRGAN, and EDSR were used for comparison. Structural similarity, peak signal to noise ratio, root mean square error, and variance inflation factor were used as calculation indicators to evaluate the performances of the proposed method. Various experimental results showed that our method can better restore the details of the high-resolution MR image as compared to the other methods. In addition, the reconstructed high-resolution MR image can provide better lesion textures in the tumor patients, which is promising to be used in clinical diagnosis.

Compressed Sensing-Based Simultaneous Recovery of Magnitude and Phase MR Images via Dual Trigonometric Sparsity

Complex-valued Magnetic Resonance Imaging (MRI) is widely used in clinical diagnosis. The magnitude images are mainly used for structure visualization, and the phase images reveal tissue properties, such as magnetic susceptibility and fluid flow information. While MRI is slow, compressed sensing (CS) can be used to reconstruct the accelerated acquisitions. Current CS-based MRI reconstruction algorithms mostly focus on magnitude image recovery, with less attention to the recovery of phase images. In this paper, we propose a novel CS algorithm to simultaneously recover the magnitude and phase MR images based on the sparsity of the trigonometric function. The CS method requires a sparse representation of the original images, and it is observed the trigonometric functions of phase images in the Wavelet domain promote sparsity. Therefore, rather than transforming the phase images directly into the Wavelet domain, we calculate the sine and cosine of the phase images whose Wavelet transforms are set as the L1-norm regularization term. The combination of the dual trigonometric functions captures a unique, faithful four-quadrant phase information, which also improves the reconstructed magnitude images through an alternating optimization procedure. Reconstructions of simulated images and in vivo images are studied, and both show the superiority of the proposed method over compared phase recovery algorithms.