Learning Joint-Sparse Codes for Calibration-Free Parallel MR Imaging

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

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

Whole brain multiparametric mapping in two minutes using a dual-flip-angle stack-of-stars blipped multi-gradient-echo acquisition

A new MRI technique is presented for three-dimensional fast simultaneous whole brain mapping of myelin water fraction (MWF), T1, proton density (PD), R2*, magnetic susceptibility (QSM), and B1 transmit field (B1+). Phantom and human (N = 9) datasets were acquired using a dual-flip-angle blipped multi-gradient-echo (DFA-mGRE) sequence with a stack-of-stars (SOS) trajectory. Images were reconstructed using a subspace-based algorithm with a locally low-rank constraint. A novel joint-sparsity-constrained multicomponent T2*-T1 spectrum estimation (JMSE) algorithm is proposed to correct for the T1 saturation effect and B1+/B1- inhomogeneities in the quantification of MWF. A tissue-prior-based B1+ estimation algorithm was adapted for B1 correction in the mapping of T1 and PD. In the phantom study, measurements obtained at an acceleration factor (R) of 12 using prospectively under-sampled SOS showed good consistency (R2 > 0.997) with Cartesian reference for R2*/T1app/M0app. In the in vivo study, results of retrospectively under-sampled SOS with R = 6, 12, 18, showed good quality (structure similarity index measure > 0.95) compared with those of fully-sampled SOS. Besides, results of prospectively under-sampled SOS with R = 12 showed good consistency (intraclass correlation coefficient > 0.91) with Cartesian reference for T1/PD/B1+/MWF/QSM/R2*, and good reproducibility (coefficient of variation < 7.0 %) in the test-retest analysis for T1/PD/B1+/MWF/R2*. This study has demonstrated the feasibility of simultaneous whole brain multiparametric mapping with a two-minute scan using the DFA-mGRE SOS sequence, which may overcome a major obstacle for neurological applications of multiparametric MRI.

AliasNet: Alias artefact suppression network for accelerated phase-encode MRI

Sparse reconstruction is an important aspect of MRI, helping to reduce acquisition time and improve spatial-temporal resolution. Popular methods are based mostly on compressed sensing (CS), which relies on the random sampling of k-space to produce incoherent (noise-like) artefacts. Due to hardware constraints, 1D Cartesian phase-encode under-sampling schemes are popular for 2D CS-MRI. However, 1D under-sampling limits 2D incoherence between measurements, yielding structured aliasing artefacts (ghosts) that may be difficult to remove assuming a 2D sparsity model. Reconstruction algorithms typically deploy direction-insensitive 2D regularisation for these direction-associated artefacts. Recognising that phase-encode artefacts can be separated into contiguous 1D signals, we develop two decoupling techniques that enable explicit 1D regularisation and leverage the excellent 1D incoherence characteristics. We also derive a combined 1D + 2D reconstruction technique that takes advantage of spatial relationships within the image. Experiments conducted on retrospectively under-sampled brain and knee data demonstrate that combination of the proposed 1D AliasNet modules with existing 2D deep learned (DL) recovery techniques leads to an improvement in image quality. We also find AliasNet enables a superior scaling of performance compared to increasing the size of the original 2D network layers. AliasNet therefore improves the regularisation of aliasing artefacts arising from phase-encode under-sampling, by tailoring the network architecture to account for their expected appearance. The proposed 1D + 2D approach is compatible with any existing 2D DL recovery technique deployed for this application.

Equilibrated Zeroth-Order Unrolled Deep Network for Parallel MR Imaging

In recent times, model-driven deep learning has evolved an iterative algorithm into a cascade network by replacing the regularizer's first-order information, such as the (sub)gradient or proximal operator, with a network module. This approach offers greater explainability and predictability compared to typical data-driven networks. However, in theory, there is no assurance that a functional regularizer exists whose first-order information matches the substituted network module. This implies that the unrolled network output may not align with the regularization models. Furthermore, there are few established theories that guarantee global convergence and robustness (regularity) of unrolled networks under practical assumptions. To address this gap, we propose a safeguarded methodology for network unrolling. Specifically, for parallel MR imaging, we unroll a zeroth-order algorithm, where the network module serves as a regularizer itself, allowing the network output to be covered by a regularization model. Additionally, inspired by deep equilibrium models, we conduct the unrolled network before backpropagation to converge to a fixed point and then demonstrate that it can tightly approximate the actual MR image. We also prove that the proposed network is robust against noisy interferences if the measurement data contain noise. Finally, numerical experiments indicate that the proposed network consistently outperforms state-of-the-art MRI reconstruction methods, including traditional regularization and unrolled deep learning techniques.

One-Shot Generative Prior in Hankel-k-Space for Parallel Imaging Reconstruction

Magnetic resonance imaging serves as an essential tool for clinical diagnosis. However, it suffers from a long acquisition time. The utilization of deep learning, especially the deep generative models, offers aggressive acceleration and better reconstruction in magnetic resonance imaging. Nevertheless, learning the data distribution as prior knowledge and reconstructing the image from limited data remains challenging. In this work, we propose a novel Hankel-k-space generative model (HKGM), which can generate samples from a training set of as little as one k-space. At the prior learning stage, we first construct a large Hankel matrix from k-space data, then extract multiple structured k-space patches from the Hankel matrix to capture the internal distribution among different patches. Extracting patches from a Hankel matrix enables the generative model to be learned from the redundant and low-rank data space. At the iterative reconstruction stage, the desired solution obeys the learned prior knowledge. The intermediate reconstruction solution is updated by taking it as the input of the generative model. The updated result is then alternatively operated by imposing low-rank penalty on its Hankel matrix and data consistency constraint on the measurement data. Experimental results confirmed that the internal statistics of patches within single k-space data carry enough information for learning a powerful generative model and providing state-of-the-art reconstruction.

WKGM: weighted k-space generative model for parallel imaging reconstruction

Deep learning based parallel imaging (PI) has made great progress in recent years to accelerate MRI. Nevertheless, it still has some limitations: for example, the robustness and flexibility of existing methods are greatly deficient. In this work, we propose a method to explore the k-space domain learning via robust generative modeling for flexible calibrationless PI reconstruction, coined the weighted k-space generative model (WKGM). Specifically, WKGM is a generalized k-space domain model, where the k-space weighting technology and high-dimensional space augmentation design are efficiently incorporated for score-based generative model training, resulting in good and robust reconstructions. In addition, WKGM is flexible and thus can be synergistically combined with various traditional k-space PI models, which can make full use of the correlation between multi-coil data and realize calibrationless PI. Even though our model was trained on only 500 images, experimental results with varying sampling patterns and acceleration factors demonstrate that WKGM can attain state-of-the-art reconstruction results with the well learned k-space generative prior.

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

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

K-space and image domain collaborative energy-based model for parallel MRI reconstruction

Decreasing magnetic resonance (MR) image acquisition times can potentially make MR examinations more accessible. Prior arts including the deep learning models have been devoted to solving the problem of long MRI imaging time. Recently, deep generative models have exhibited great potentials in algorithm robustness and usage flexibility. Nevertheless, none of existing schemes can be learned from or employed to the k-space measurement directly. Furthermore, how do the deep generative models work well in hybrid domain is also worth being investigated. In this work, by taking advantage of the deep energy-based models, we propose a k-space and image domain collaborative generative model to comprehensively estimate the MR data from under-sampled measurement. Equipped with parallel and sequential orders, experimental comparisons with the state-of-the-arts demonstrated that they involve less error in reconstruction accuracy and are more stable under different acceleration factors.

Medical image super-resolution reconstruction algorithms based on deep learning: A survey

BACKGROUND AND OBJECTIVE

With the high-resolution (HR) requirements of medical images in clinical practice, super-resolution (SR) reconstruction algorithms based on low-resolution (LR) medical images have become a research hotspot. This type of method can significantly improve image SR without improving hardware equipment, so it is of great significance to review it.

METHODS

Aiming at the unique SR reconstruction algorithms in the field of medical images, based on subdivided medical fields such as magnetic resonance (MR) images, computed tomography (CT) images, and ultrasound images. Firstly, we deeply analyzed the research progress of SR reconstruction algorithms, and summarized and compared the different types of algorithms. Secondly, we introduced the evaluation indicators corresponding to the SR reconstruction algorithms. Finally, we prospected the development trend of SR reconstruction technology in the medical field.

RESULTS

The medical image SR reconstruction technology based on deep learning can provide more abundant lesion information, relieve the expert's diagnosis pressure, and improve the diagnosis efficiency and accuracy.

CONCLUSION

The medical image SR reconstruction technology based on deep learning helps to improve the quality of medicine, provides help for the diagnosis of experts, and lays a solid foundation for the subsequent analysis and identification tasks of the computer, which is of great significance for improving the diagnosis efficiency of experts and realizing intelligent medical care.

Magnetic resonance imaging reconstruction using a deep energy-based model

Although recent deep energy-based generative models (EBMs) have shown encouraging results in many image-generation tasks, how to take advantage of self-adversarial cogitation in deep EBMs to boost the performance of magnetic resonance imaging (MRI) reconstruction is still desired. With the successful application of deep learning in a wide range of MRI reconstructions, a line of emerging research involves formulating an optimization-based reconstruction method in the space of a generative model. Leveraging this, a novel regularization strategy is introduced in this article that takes advantage of self-adversarial cogitation of the deep energy-based model. More precisely, we advocate alternating learning by a more powerful energy-based model with maximum likelihood estimation to obtain the deep energy-based information, represented as a prior image. Simultaneously, implicit inference with Langevin dynamics is a unique property of reconstruction. In contrast to other generative models for reconstruction, the proposed method utilizes deep energy-based information as the image prior in reconstruction to improve the quality of image. Experimental results imply the proposed technique can obtain remarkable performance in terms of high reconstruction accuracy that is competitive with state-of-the-art methods, and which does not suffer from mode collapse. Algorithmically, an iterative approach is presented to strengthen EBM training with the gradient of energy network. The robustness and reproducibility of the algorithm were also experimentally validated. More importantly, the proposed reconstruction framework can be generalized for most MRI reconstruction scenarios.

aiWave: Volumetric Image Compression With 3-D Trained Affine Wavelet-Like Transform

Volumetric image compression has become an urgent task to effectively transmit and store images produced in biological research and clinical practice. At present, the most commonly used volumetric image compression methods are based on wavelet transform, such as JP3D. However, JP3D employs an ideal, separable, global, and fixed wavelet basis to convert input images from pixel domain to frequency domain, which seriously limits its performance. In this paper, we first design a 3-D trained wavelet-like transform to enable signal-dependent and non-separable transform. Then, an affine wavelet basis is introduced to capture the various local correlations in different regions of volumetric images. Furthermore, we embed the proposed wavelet-like transform to an end-to-end compression framework called aiWave to enable an adaptive compression scheme for various datasets. Last but not least, we introduce the weight sharing strategies of the affine wavelet-like transform according to the volumetric data characteristics in the axial direction to reduce the number of parameters. The experimental results show that: 1) when cooperating our trained 3-D affine wavelet-like transform with a simple factorized entropy coding module, aiWave performs better than JP3D and is comparable in terms of encoding and decoding complexities; 2) when adding a context module to remove signal redundancy further, aiWave can achieve a much better performance than HEVC.

Development and Application of a Standardized Testset for an Artificial Intelligence Medical Device Intended for the Computer-Aided Diagnosis of Diabetic Retinopathy

Objective

To explore a centralized approach to build test sets and assess the performance of an artificial intelligence medical device (AIMD) which is intended for computer-aided diagnosis of diabetic retinopathy (DR).

Method

A framework was proposed to conduct data collection, data curation, and annotation. Deidentified colour fundus photographs were collected from 11 partner hospitals with raw labels. Photographs with sensitive information or authenticity issues were excluded during vetting. A team of annotators was recruited through qualification examinations and trained. The annotation process included three steps: initial annotation, review, and arbitration. The annotated data then composed a standardized test set, which was further imported to algorithms under test (AUT) from different developers. The algorithm outputs were compared with the final annotation results (reference standard).

Result

The test set consists of 6327 digital colour fundus photographs. The final labels include 5 stages of DR and non-DR, as well as other ocular diseases and photographs with unacceptable quality. The Fleiss Kappa was 0.75 among the annotators. The Cohen's kappa between raw labels and final labels is 0.5. Using this test set, five AUTs were tested and compared quantitatively. The metrics include accuracy, sensitivity, and specificity. The AUTs showed inhomogeneous capabilities to classify different types of fundus photographs.

Conclusions

This article demonstrated a workflow to build standardized test sets and conduct algorithm testing of the AIMD for computer-aided diagnosis of diabetic retinopathy. It may provide a reference to develop technical standards that promote product verification and quality control, improving the comparability of products.

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.

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.

A Coarse-to-Fine Deformable Transformation Framework for Unsupervised Multi-Contrast MR Image Registration with Dual Consistency Constraint

Multi-contrast magnetic resonance (MR) image registration is useful in the clinic to achieve fast and accurate imaging-based disease diagnosis and treatment planning. Nevertheless, the efficiency and performance of the existing registration algorithms can still be improved. In this paper, we propose a novel unsupervised learning-based framework to achieve accurate and efficient multi-contrast MR image registration. Specifically, an end-to-end coarse-to-fine network architecture consisting of affine and deformable transformations is designed to improve the robustness and achieve end-to-end registration. Furthermore, a dual consistency constraint and a new prior knowledge-based loss function are developed to enhance the registration performances. The proposed method has been evaluated on a clinical dataset containing 555 cases, and encouraging performances have been achieved. Compared to the commonly utilized registration methods, including VoxelMorph, SyN, and LT-Net, the proposed method achieves better registration performance with a Dice score of 0.8397± 0.0756 in identifying stroke lesions. With regards to the registration speed, our method is about 10 times faster than the most competitive method of SyN (Affine) when testing on a CPU. Moreover, we prove that our method can still perform well on more challenging tasks with lacking scanning information data, showing the high robustness for the clinical application.

FA-GAN: Fused attentive generative adversarial networks for MRI image super-resolution

High-resolution magnetic resonance images can provide fine-grained anatomical information, but acquiring such data requires a long scanning time. In this paper, a framework called the Fused Attentive Generative Adversarial Networks(FA-GAN) is proposed to generate the super- resolution MR image from low-resolution magnetic resonance images, which can reduce the scanning time effectively but with high resolution MR images. In the framework of the FA-GAN, the local fusion feature block, consisting of different three-pass networks by using different convolution kernels, is proposed to extract image features at different scales. And the global feature fusion module, including the channel attention module, the self-attention module, and the fusion operation, is designed to enhance the important features of the MR image. Moreover, the spectral normalization process is introduced to make the discriminator network stable. 40 sets of 3D magnetic resonance images (each set of images contains 256 slices) are used to train the network, and 10 sets of images are used to test the proposed method. The experimental results show that the PSNR and SSIM values of the super-resolution magnetic resonance image generated by the proposed FA-GAN method are higher than the state-of-the-art reconstruction methods.

Optimizing multicontrast MRI reconstruction with shareable feature aggregation and selection

This paper proposes a new method for optimizing feature sharing in deep neural network-based, rapid, multicontrast magnetic resonance imaging (MC-MRI). Using the shareable information of MC images for accelerated MC-MRI reconstruction, current algorithms stack the MC images or features without optimizing the sharing protocols, leading to suboptimal reconstruction results. In this paper, we propose a novel feature aggregation and selection scheme in a deep neural network to better leverage the MC features and improve the reconstruction results. First, we propose to extract and use the shareable information by mapping the MC images into multiresolution feature maps with multilevel layers of the neural network. In this way, the extracted features capture complementary image properties, including local patterns from the shallow layers and semantic information from the deep layers. Then, an explicit selection module is designed to compile the extracted features optimally. That is, larger weights are learned to incorporate the constructive, shareable features; and smaller weights are assigned to the unshareable information. We conduct comparative studies on publicly available T2-weighted and T2-weighted fluid attenuated inversion recovery brain images, and the results show that the proposed network consistently outperforms existing algorithms. In addition, the proposed method can recover the images with high fidelity under 16 times acceleration. The ablation studies are conducted to evaluate the effectiveness of the proposed feature aggregation and selection mechanism. The results and the visualization of the weighted features show that the proposed method does effectively improve the usage of the useful features and suppress useless information, leading to overall enhanced reconstruction results. Additionally, the selection module can zero-out repeated and redundant features and improve network efficiency.

D-UNet: A Dimension-Fusion U Shape Network for Chronic Stroke Lesion Segmentation

Assessing the location and extent of lesions caused by chronic stroke is critical for medical diagnosis, surgical planning, and prognosis. In recent years, with the rapid development of 2D and 3D convolutional neural networks (CNN), the encoder-decoder structure has shown great potential in the field of medical image segmentation. However, the 2D CNN ignores the 3D information of medical images, while the 3D CNN suffers from high computational resource demands. This paper proposes a new architecture called dimension-fusion-UNet (D-UNet), which combines 2D and 3D convolution innovatively in the encoding stage. The proposed architecture achieves a better segmentation performance than 2D networks, while requiring significantly less computation time in comparison to 3D networks. Furthermore, to alleviate the data imbalance issue between positive and negative samples for the network training, we propose a new loss function called Enhance Mixing Loss (EML). This function adds a weighted focal coefficient and combines two traditional loss functions. The proposed method has been tested on the ATLAS dataset and compared to three state-of-the-art methods. The results demonstrate that the proposed method achieves the best quality performance in terms of DSC = 0.5349 ± 0.2763 and precision = 0.6331 ± 0.295).

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.

A guaranteed convergence analysis for the projected fast iterative soft-thresholding algorithm in parallel MRI

Sparse sampling and parallel imaging techniques are two effective approaches to alleviate the lengthy magnetic resonance imaging (MRI) data acquisition problem. Promising data recoveries can be obtained from a few MRI samples with the help of sparse reconstruction models. To solve the optimization models, proper algorithms are indispensable. The pFISTA, a simple and efficient algorithm, has been successfully extended to parallel imaging. However, its convergence criterion is still an open question. Besides, the existing convergence criterion of single-coil pFISTA cannot be applied to the parallel imaging pFISTA, which, therefore, imposes confusions and difficulties on users about determining the only parameter - step size. In this work, we provide the guaranteed convergence analysis of the parallel imaging version pFISTA to solve the two well-known parallel imaging reconstruction models, SENSE and SPIRiT. Along with the convergence analysis, we provide recommended step size values for SENSE and SPIRiT reconstructions to obtain fast and promising reconstructions. Experiments on in vivo brain images demonstrate the validity of the convergence criterion.

Penalized-likelihood PET Image Reconstruction Using 3D Structural Convolutional Sparse Coding

Positron emission tomography (PET) is widely used for clinical diagnosis. As PET suffers from low resolution and high noise, numerous efforts try to incorporate anatomical priors into PET image reconstruction, especially with the development of hybrid PET/CT and PET/MRI systems. In this work, we proposed a cube-based 3D structural convolutional sparse coding (CSC) concept for penalized-likelihood PET image reconstruction, named 3D PET-CSC. The proposed 3D PET-CSC takes advantage of the convolutional operation and manages to incorporate anatomical priors without the need of registration or supervised training. As 3D PET-CSC codes the whole 3D PET image, instead of patches, it alleviates the staircase artifacts commonly presented in traditional patch-based sparse coding methods. Compared with traditional coding methods in Fourier domain, the proposed method extends the 3D CSC to a straightforward approach based on the pursuit of localized cubes. Moreover, we developed the residual-image and order-subset mechanisms to further reduce the computational cost and accelerate the convergence for the proposed 3D PET-CSC method. Experiments based on computer simulations and clinical datasets demonstrate the superiority of 3D PET-CSC compared with other reference methods.

A Modified Phase Cycling Method for Complex-Valued MRI Reconstruction

The phase cycling method is a state-of-the-art method to reconstruct complex-valued MR image. However, when it follows practical two-dimensional (2D) subsampling Cartesian acquisition which is only enforcing random sampling in the phase-encoding direction, a number of artifacts in magnitude appear. A modified approach is proposed to remove these artifacts under practical MRI subsampling, by adding one-dimensional total variation (TV) regularization into the phase cycling method to "pre-process" the magnitude component before its update. Furthermore, an operation used in SFISTA is employed to update the magnitude and phase images for better solutions. The results of the experiments show the ability of the proposed method to eliminate the ring artifacts and improve the magnitude reconstruction.

Adaptive sparsity level and dictionary size estimation for image reconstruction in accelerated 2D radial cine MRI

PURPOSE

In the past, dictionary learning (DL) and sparse coding (SC) have been proposed for the regularization of image reconstruction problems. The regularization is given by a sparse approximation of all image patches using a learned dictionary, that is, an overcomplete set of basis functions learned from data. Despite its competitiveness, DL and SC require the tuning of two essential hyperparameters: the sparsity level S - the number of basis functions of the dictionary, called atoms, which are used to approximate each patch, and K - the overall number of such atoms in the dictionary. These two hyperparameters usually have to be chosen a priori and are determined by repetitive and computationally expensive experiments. Furthermore, the final reported values vary depending on the specific situation. As a result, the clinical application of the method is limited, as standardized reconstruction protocols have to be used.

METHODS

In this work, we use adaptive DL and propose a novel adaptive sparse coding algorithm for two-dimensional (2D) radial cine MR image reconstruction. Using adaptive DL and adaptive SC, the optimal dictionary size K as well as the optimal sparsity level S are chosen dependent on the considered data.

RESULTS

Our three main results are the following: First, adaptive DL and adaptive SC deliver results which are comparable or better than the most widely used nonadaptive version of DL and SC. Second, the time needed for the regularization is accelerated due to the fact that the sparsity level S is never overestimated. Finally, the a priori choice of S and K is no longer needed but is optimally chosen dependent on the data under consideration.

CONCLUSIONS

Adaptive DL and adaptive SC can highly facilitate the application of DL- and SC-based regularization methods. While in this work we focused on 2D radial cine MR image reconstruction, we expect the method to be applicable to different imaging modalities as well.

Towards a general framework for fast and feasible k-space trajectories for MRI based on projection methods

The design of feasible trajectories to traverse the k-space for sampling in magnetic resonance imaging (MRI) is important while considering ways to reduce the scan time. Over the recent years, non-Cartesian trajectories have been observed to result in benign artifacts and being less sensitive to motion. In this paper, we propose a generalized framework that encompasses projection-based methods to generate feasible non-Cartesian k-space trajectories. This framework allows to construct feasible trajectories from both random or structured initial trajectories, e.g., based on the traveling salesman problem (TSP). We evaluate the performance of the proposed methods by simulating the reconstruction of 128 × 128 and 256 × 256 phantom and brain MRI images in terms of structural similarity (SSIM) index and peak signal-to-noise ratio (PSNR) using compressed sensing techniques. It is observed that the TSP-based trajectories from the proposed projection method with constant acceleration parameterization (CAP) result in better reconstruction compared to the projection method with constant velocity parameterization (CVP) and this for a similar read-out time. Further, random-like trajectories are observed to be better than TSP-based trajectories as they reduce the read-out time while providing better reconstruction quality. A reduction in read-out time by upto 67% is achieved using the proposed projection with permutation (PP) method.

A Network-Driven Prior Induced Bregman Model for Parallel MR Imaging

Compressed sensing based parallel imaging (CS-PI) has attracted great attention in fast magnetic resonance imaging (MRI) community. In particular, Bregman iterative model has shown encouraging performance in solving this problem. However, its regularization term still has large room for improvement. In this work, we propose a network-driven prior induced Bregman model, dubbed as Breg-EDAEP, for CS-PI task. In the present model, the implicit property among different channel MR images is preliminarily explored by the network to obtain more structure details in iterative reconstruction procedure. Experiments on various acceleration factors and sampling patterns have shown that the proposed method outperforms the state-of-the-art algorithms. Breg-EDAEP possesses strong capability to restore image details and preserves well structure information.

Optimization Methods for Magnetic Resonance Image Reconstruction: Key Models and Optimization Algorithms

The development of compressed sensing methods for magnetic resonance (MR) image reconstruction led to an explosion of research on models and optimization algorithms for MR imaging (MRI). Roughly 10 years after such methods first appeared in the MRI literature, the U.S. Food and Drug Administration (FDA) approved certain compressed sensing methods for commercial use, making compressed sensing a clinical success story for MRI. This review paper summarizes several key models and optimization algorithms for MR image reconstruction, including both the type of methods that have FDA approval for clinical use, as well as more recent methods being considered in the research community that use data-adaptive regularizers. Many algorithms have been devised that exploit the structure of the system model and regularizers used in MRI; this paper strives to collect such algorithms in a single survey.

Broad Learning Enhanced 1H-MRS for Early Diagnosis of Neuropsychiatric Systemic Lupus Erythematosus

In this paper, we explore the potential of using the multivoxel proton magnetic resonance spectroscopy (¹H-MRS) to diagnose neuropsychiatric systemic lupus erythematosus (NPSLE) with the assistance of a support vector machine broad learning system (BL-SVM). We retrospectively analysed 23 confirmed patients and 16 healthy controls, who underwent a 3.0 T magnetic resonance imaging (MRI) sequence with multivoxel ¹H-MRS in our hospitals. One hundred and seventeen metabolic features were extracted from the multivoxel ¹H-MRS image. Thirty-three metabolic features selected by the Mann-Whitney U test were considered to have a statistically significant difference (p < 0.05). However, the best accuracy achieved by conventional statistical methods using these 33 metabolic features was only 77%. We turned to develop a support vector machine broad learning system (BL-SVM) to quantitatively analyse the metabolic features from ¹H-MRS. Although not all the individual features manifested statistics significantly, the BL-SVM could still learn to distinguish the NPSLE from the healthy controls. The area under the receiver operating characteristic curve (AUC), the sensitivity, and the specificity of our BL-SVM in predicting NPSLE were 95%, 95.8%, and 93%, respectively, by 3-fold cross-validation. We consequently conclude that the proposed system effectively and efficiently working on limited and noisy samples may brighten a noinvasive in vivo instrument for early diagnosis of NPSLE.

Directionality guided non linear diffusion compressed sensing MR image reconstruction

PURPOSE

Address the shortcomings of edge-preserving filters to preserve the complex nature of edges, by adapting the direction of diffusion to the local variations in intensity function on a subpixel level, thereby achieving a reconstruction accuracy superior to that of data-driven learning-based approaches.

THEORY AND METHODS

Rate of diffusion for edges is found to vary in accordance with their gradient direction. Therefore, the edge preservation is strongly dependent on the direction in which the gradient is computed. Since the directionality of edges varies at different regions of the image, the proposed technique computes the gradients in all possible angular directions and uses a spatial-frequency-based deviation measure to choose the most reliable edges from the images diffused along different directions.

RESULTS

The proposed method is compared with the state-of-the-art data-driven learning-based techniques of block matching and 3D filtering (BM3D), patch-based nonlocal operator (PANO), and dictionary learning MRI (DLMRI). Best results are obtained when directionality of edges is estimated from a prior optimized k-space and shows an improvement in peak signal-to-noise ratio (PSNR) measures by a factor of 2.36 dB, 1.92 dB, and 1.59 dB over BM3D, PANO, and dictionary learning MRI, respectively.

CONCLUSION

The proposed technique prevents the emphasis of false edges and better captures the structural details by a locally varying directionality-guided diffusion to make the error lower than that of the state-of-the-art reconstruction techniques. In addition, a highly parallelizable form of the proposed model promises a significant gain in the reconstruction speed for practical implementations.

Common Information Enhanced Reconstruction for Accelerated High-resolution Multi-shot Diffusion Imaging

PURPOSE

Multi-shot technique can effectively achieve high-resolution diffusion weighted images, but the acquisition time of multi-shot technique is prolonged, especially for multiple direction diffusion encoding. Thus, increasing acquisition efficiency is highly desirable for high-resolution diffusion tensor imaging (DTI). In this study, based on the assumption that different diffusion directions share the common information, image ratio constrained reconstruction (IRCR) combined with iterative self-consistent parallel imaging reconstruction (SPIRiT) is proposed to improve data sampling efficiency and image reconstruction fidelity for high-resolution DTI.

THEORY AND METHODS

The proposed reconstruction framework is named Common Information Enhanced Reconstruction (CIER). Inter-image correlation among different direction diffusion-weighted images is used through common information, which is an isotropic component and structure, for improving the performance of reconstruction. The framework consists of three steps. (i) Pre-processing: three intermediate multi-shot images, low-resolution composite image, high-resolution composite image and low-resolution diffusion weighted image, are generated based on the SPIRiT method. (ii) IRCR: the initial high-resolution diffusion weighted image is calculated from the images in step (i) based on that the ratio map between high-resolution images is approximated by the ratio map between the corresponding low-resolution images. (iii) Final SPIRiT reconstruction: the final image is generated with the image from IRCR as initialization by considering data consistency only in the SPIRiT calculation. A specific implementation based on multishot variable density spiral (VDS) DTI is used to demonstrate the method.

RESULTS

The proposed CIER method was compared with the traditional reconstruction methods, conjugate gradient SENSE (CG-SENSE), L1-regularized SPIRiT (L1-SPIRiT), and anisotropic-sparsity SPIRiT (AS-SPIRiT) in brain DTI at acceleration factors of 3 to 7. CIER provided better diffusion image quality than other methods shown by both qualitative and quantitative results, especially at higher undersampling acceleration factors.

CONCLUSION

CIER offers better diffusion image quality at higher undersampling acceleration factors for high-resolution DTI. Both qualitative and quantitative results prove that common information can be used to improve sampling efficiency and maintain the image quality of diffusion-weighted images.

3D Morphological Processing for Wheat Spike Phenotypes Using Computed Tomography Images

Wheat is the main food crop today world-wide. In order to improve its yields, researchers are committed to understand the relationships between wheat genotypes and phenotypes. Compared to progressive technology of wheat gene section identification, wheat trait measurement is mostly done manually in a destructive, labor-intensive and time-consuming way. Therefore, this study will be greatly accelerated and promoted if we can automatically discover wheat phenotype in a nondestructive and fast manner. In this paper, we propose a novel pipeline based on 3D morphological processing to detect wheat spike grains and stem nodes from 3D X-ray micro computed tomography (CT) images. We also introduce a set of newly defined 3D phenotypes, including grain aspect ratio, porosity, Grain-to-Grain distance, and grain angle, which are very difficult to be manually measured. The analysis of the associations among these traits would be very helpful for wheat breeding. Experimental results show that our method is able to count grains more accurately than normal human performance. By analyzing the relationships between traits and environment conditions, we find that the Grain-to-Grain distance, aspect ratio and porosity are more likely affected by the genome than environment (only tested temperature and water conditions). We also find that close grains will inhibit grain volume growth and that the aspect ratio 3.5 may be the best for higher yield in wheat breeding.

Highly and Adaptively Undersampling Pattern for Pulmonary Hyperpolarized 129Xe Dynamic MRI

Hyperpolarized (HP) gas (e.g., ³He or ¹²⁹Xe) dynamic MRI could visualize the lung ventilation process, which provides characteristics regarding lung physiology and pathophysiology. Compressed sensing (CS) is generally used to increase the temporal resolution of such dynamic MRI. Nevertheless, the acceleration factor of CS is constant, which results in difficulties in precisely observing and/or measuring dynamic ventilation process due to bifurcating network structure of the lung. Here, an adaptive strategy is proposed to highly undersample pulmonary HP dynamic k-space data, according to the characteristics of both lung structure and gas motion. After that, a valid reconstruction algorithm is developed to reconstruct dynamic MR images, considering the low-rank, global sparsity, gas-inflow effects, and joint sparsity. Both the simulation and the in vivo results verify that the proposed approach outperforms the state-of-the-art methods both in qualitative and quantitative comparisons. In particular, the proposed method acquires 33 frames within 6.67 s (more than double the temporal resolution of the recently proposed strategy), and achieves high-image quality [the improvements are 29.63%, 3.19%, 2.08%, and 13.03% regarding the mean absolute error (MAE), structural similarity index (SSIM), quality index based on local variance (QILV), and contrast-to-noise ratio (CNR) comparisons]. This provides accurate structural and functional information for early detection of obstructive lung diseases.