Reconstructing high-fidelity MR images from undersampled k-space data remains a challenging problem in MRI. While Mamba variants for vision tasks offer promising long-range modeling capabilities with linear-time complexity, their direct application to MRI reconstruction inherits two key limitations: (1) insensitivity to high-frequency anatomical details; and (2) reliance on redundant multi-directional scanning. To address these limitations, we introduce High-Fidelity Mamba (HiFi-Mamba), a novel dual-stream Mamba-based architecture comprising stacked ?-Laplacian (WL) and HiFi-Mamba blocks. Specifically, the WL block performs fidelity-preserving spectral decoupling, producing complementary low- and high-frequency streams. This separation enables the HiFi-Mamba block to focus on low-frequency structures, enhancing global feature modeling. Concurrently, the HiFi-Mamba block selectively integrates high-frequency features through adaptive state-space modulation, preserving comprehensive spectral details. To eliminate the scanning redundancy, the HiFi-Mamba block adopts a streamlined unidirectional traversal strategy that preserves long-range modeling capability with improved computational efficiency. Extensive experiments on standard MRI reconstruction benchmarks demonstrate that HiFi-Mamba consistently outperforms state-of-the-art CNN-based, Transformer-based, and other Mamba-based models in reconstruction accuracy while maintaining a compact and efficient model design.

Incoherent k-space undersampling and deep learning-based reconstruction methods have shown great success in accelerating MRI. However, the performance of most previous methods will degrade dramatically under high acceleration factors, e.g., $8\times $ or higher. Recently, denoising diffusion models (DM) have demonstrated promising results in solving this issue; however, one major drawback of the DM methods is the long inference time due to a dramatic number of iterative reverse posterior sampling steps. In this work, a Single Step Diffusion Model-based reconstruction framework, namely SSDM-MRI, is proposed for restoring MRI images from highly undersampled k-space. The proposed method achieves one-step reconstruction by first training a conditional DM and then iteratively distilling this model four times using an iterative selective distillation algorithm, which works synergistically with a shortcut reverse sampling strategy for model inference. Comprehensive experiments were carried out on both publicly available fastMRI brain and knee images, as well as an in-house multi-echo GRE (QSM) subject. Overall, the results showed that SSDM-MRI outperformed other methods in terms of numerical metrics (e.g., PSNR and SSIM), error maps, image fine details, and latent susceptibility information hidden in MRI phase images. In addition, the reconstruction time for a ${320}\times {320}$ brain slice of SSDM-MRI is only 0.45 second, which is only comparable to that of a simple U-net, making it a highly effective solution for MRI reconstruction tasks.

Quantitative susceptibility mapping (QSM) is a post-processing technique for deriving tissue magnetic susceptibility distribution from MRI phase measurements. Deep learning (DL) algorithms hold great potential for solving the ill-posed QSM reconstruction problem. However, a significant challenge facing current DL-QSM approaches is their limited adaptability to magnetic dipole field orientation variations during training and testing. In this work, we propose a novel Orientation-Adaptive Latent Feature Editing (OA-LFE) module to learn the encoding of acquisition orientation vectors and seamlessly integrate them into the latent features of deep networks. Importantly, it can be directly Plug-and-Play (PnP) into various existing DL-QSM architectures, enabling reconstructions of QSM from arbitrary magnetic dipole orientations. Its effectiveness is demonstrated by combining the OA-LFE module into our previously proposed phase-to-susceptibility single-step instant QSM (iQSM) network, which was initially tailored for pure-axial acquisitions. The proposed OA-LFE-empowered iQSM, which we refer to as iQSM+, is trained in a simulated-supervised manner on a specially-designed simulation brain dataset. Comprehensive experiments are conducted on simulated and in vivo human brain datasets, encompassing subjects ranging from healthy individuals to those with pathological conditions. These experiments involve various MRI platforms (3T and 7T) and aim to compare our proposed iQSM+ against several established QSM reconstruction frameworks, including the original iQSM. The iQSM+ yields QSM images with significantly improved accuracies and mitigates artifacts, surpassing other state-of-the-art DL-QSM algorithms. The PnP OA-LFE module’s versatility was further demonstrated by its successful application to xQSM, a distinct DL-QSM network for dipole inversion. In conclusion, this work introduces a new DL paradigm, allowing researchers to develop innovative QSM methods without requiring a complete overhaul of their existing architectures.

Image compressed sensing (ICS) has been extensively applied in various imaging domains due to its capability to sample and reconstruct images at subNyquist sampling rates. The current predominant approaches in ICS, specifically pure convolutional networks (ConvNets)-based ICS methods, have demonstrated their effectiveness in capturing local features for image recovery. Simultaneously, the Transformer architecture has gained significant attention due to its capability to model global correlations among image features. Motivated by these insights, we propose a novel hybrid network for ICS, named MTC-CSNet, which effectively combines the strengths of both ConvNets and Transformer architectures in capturing local and global image features to achieve high-quality image recovery. Particularly, MTC-CSNet is a dual-path framework that consists of a ConvNets-based recovery branch and a Transformer-based recovery branch. Along the ConvNets-based recovery branch, we design a lightweight scheme to capture the local features in natural images. Meanwhile, we implement a Transformer-based recovery branch to iteratively model the global dependencies among image patches. Ultimately, the ConvNets-based and Transformer-based recovery branches collaborate through a bridging unit, facilitating the adaptive transmission and fusion of informative features for image reconstruction. Extensive experimental results demonstrate that our proposed MTC-CSNet surpasses the state-of-the-art methods on various public datasets. The code and models are publicly available at MTC-CSNet.

Deep compressive sensing (CS) has become a prevalent technique for image acquisition and reconstruction. However, existing deep learning (DL)-based CS methods often encounter challenges such as block artifacts and information loss during iterative reconstruction, particularly at low sampling rates, resulting in a reduction of reconstructed details. To address these issues, we propose NesTD-Net, an unfolding-based architecture inspired by the NESTA algorithm, designed for image CS. NesTD-Net integrates DL modules into NESTA iterations, forming a deep network that continuously iterates to minimize the ℓ1-norm CS problem, ensuring high-quality image CS. Utilizing a learned sampling matrix for measurements and an initialization module for initial estimate, NesTD-Net then introduces Iteration Sub-Modules derived from the NESTA algorithm (i.e., Yk, Zk, and Xk) during reconstruction stages to iteratively solve the ℓ1-norm CS reconstruction. Additionally, NesTD-Net incorporates a Dual-Path Deblocking Structure (DPDS) to facilitate feature information flow and mitigate block artifacts, enhancing image detail reconstruction. Furthermore, DPDS exhibits remarkable versatility and demonstrates seamless integration with other unfolding-based methods, offering the potential to enhance their performance in image reconstruction. Experimental results demonstrate that our proposed NesTD-Net achieves better performance compared to other state-of-the-art methods in terms of image quality metrics such as SSIM and PSNR, as well as visual perception on several public benchmark datasets. Our code is available at NesTD-Net.

Block compressive sensing (CS) is a well-known signal acquisition and reconstruction paradigm with widespread application prospects in science, engineering, and cybernetic systems. However, state-of-the-art block-based image CS (BCS) methods generally suffer from two issues. The sparsifying domain and the sensing matrices widely used for image acquisition are not data driven and, thus, both the features of the image and the relationships among subblock images are ignored. Moreover, it requires to address a high-dimensional optimization problem with extensive computational complexity for image reconstruction. In this article, we provide a deep learning (DL) strategy for BCS, called AutoBCS, which automatically takes the prior knowledge of images into account in the acquisition step and establishes a reconstruction model for performing fast image reconstruction. More precisely, we present a learning-based sensing matrix to accomplish image acquisition, thereby capturing and preserving more image characteristics than those captured by the existing methods. In addition, we build a noniterative reconstruction network, which provides an end-to-end BCS reconstruction framework to maximize image reconstruction efficiency. Furthermore, we investigate comprehensive comparison studies with both traditional BCS approaches and newly developed DL methods. Compared with these approaches, our proposed AutoBCS can not only provide superior performance in terms of image quality metrics (SSIM and PSNR) and visual perception but also automatically benefit reconstruction speed.

Fuzzy message detection is a novel cryptographic primitive in which the remote storage cloud can help the client carry out fuzzy detections with some false-positive rate. This primitive protects the privacy of clients and does not reveal exactly the matching messages to the untrusted cloud. However, the existing public-key-based schemes require many public keys to generate a single flag ciphertext. This introduces heavy costs in terms of public-key certificate management. In this paper, we propose an efficient identity-based fuzzy message detection method based on a novel identity-based online/offline encryption scheme. All heavy cost computation operations are carried out in the offline phase without the knowledge of the identities for each message, and the single flag ciphertext can be generated quickly with the message’s identities since only light cost computations are required in the online phase. We apply our scheme to the blockchain-based fuzzy message detection systems. Additionally, we design a new history indexing scheme based on Dodis’ verifiable random function and Schnorr’s signature. The transactions history and order of accessing storage cloud (storing and detecting messages) are indexed, and signed by each client. We provide the analysis of privacy guarantees and differential privacy requirements for our online/offline ID-FMD scheme, and implement our FMD system over the Fibos platform and the Huawei Elastic Cloud.

Abstract Software-defined networking (SDN), a novel network paradigm, separates the control plane and data plane into different network equipment to realize the flexible control of network traffic. Its excellent programmability and global view present many new opportunities. DDoS detection under the SDN context is an important and challenging research field. Some previous works attempted to collect and analyze statistics related to flows, usually recorded in switches, to address DDoS threats. In contrast, other works applied machine learning-based solutions to identify DDoS and achieved promising results. Generally, most previous works need to periodically request flow rules or packets to obtain flow statistics or features to detect stealthy exceptions. Nevertheless, the request for flow rules is very time-consuming and CPU-consuming; moreover may congest the communication channel between the controller and the switches. Therefore, we present FORT, a lightweight DDoS detection scheme, which spreads the rule-based detection algorithm at edge switches and determines whether to start it by periodically retrieving the ports state. A time-series algorithm, ARIMA, is utilized to determine the port statistics adaptively, and an SVM algorithm is applied to detect whether a DDoS attack does occur. Representative experiments demonstrate that FORT can significantly reduce the controller load and provide a reliable detection accuracy. Referring to the false alarm rate of 1.24% in the comparison scheme, the false alarm rate of this scheme is only 0.039%, which significantly reduces the probability of false alarm. Besides, by introducing the alarm mechanism, this scheme can reduce the load of the southbound channel by more than 60% in the normal state.

One of the main challenges in ultra-high field whole body MRI relates to the uniformity and efficiency of the radiofrequency field. Although recent advances in the design of RF coils have demonstrated that dipole antennas have a current distribution ideally suited to 7T MRI, they are limited by low isolation and poor robustness to loading changes. Multi-layered and self-decoupled loop coils have demonstrated improved RF performance in these areas at lower field MRI but have not been adapted to dipole designs. In this work, we introduce a novel type of RF antenna consisting of integrated multi-modal antenna with coupled radiating structures (I-MARS), which use layered conductors and dielectric substrates to allow dipole and transmission line modes to co-exist on the same compact dipole-shaped structure. The proposed antenna was optimally designed for 7T MRI and compared with existing dipole antennas using numerical simulations, which showed that I-MARS had similar B1over specific absorption rate efficiency and superior isolation and stability. Subsequently, a prototype pTx coil array was built and testedin vivoon healthy volunteers at 7T. The articulated, modular construction of the I-MARS coil array allowed it to be readily conformed across multiple body regions (hip, knee, shoulder, lumbar spine and prostate), without requiring modification of the tuning and matching of the antennas. Using RF shimming, uniform and efficient excitation was successfully achieved in the acquisition of high-resolution MR images.

Many integral equation (IE)-based magnetic resonance electrical property tomography (MR-EPT) methods use unloaded incident radio-frequency (RF) fields from simulations that may not fully reflect the real situation and thus lead to reconstruction errors. To improve the accuracy of IE-based MR-EPT methods, a novel approach that enables the calculation of loaded coil current distributions and avoids the explicit use of incident RF fields is presented in this paper. In the proposed method, a hybrid source composed of the current source from the coil and the contrast source from the subject are introduced in the integral equations. Because the loaded coil current distributions can be extracted from the reconstructed hybrid source, the simulated incident RF fields are eliminated from the problem formulations. To improve the convergence performance, a modified conjugate gradient (CG) scheme was used where the gradients of the current source and contrast source were balanced through using different weighting parameters. The proposed method was verified through full-wave simulations at 9.4 and 7 T involving a heterogeneous ball and an anatomical head phantom. The numerical results indicated that by using the proposed method, an accurate coil current distributions and EPs profiles can be reconstructed and the desirable robustness against noise can also be achieved.

Compressed sensing magnetic resonance imaging (CS‐MRI) is an effective way of reducing the sampling data in the k ‐space and shortening the scanning time. Motivated by the high performance of directional tensor product complex tight framelets (TPCTFs) for the image denoising problem, the authors proposed a novel framework that integrated TPCTF for sparse representation and projected fast iterative soft‐thresholding algorithm (pFISTA) for CS‐MRI reconstruction. Furthermore, to take advantage of the cross‐scale relations in the wavelet tree of frame coefficients, the bivariate shrinkage (BS) function with local variance estimation is proposed to shrink thresholding. Such TPCTFs can provide sparse directional representations very well for MR image. When compared with other the state‐of‐the‐art CS‐MRI algorithms in numerical experiments, the proposed TPCTF‐BS method achieves a higher reconstruction quality with respect to image edge preservation and the artefact suppression.

Recently, we have developed a tensor-decomposition based compressed sensing (CS) method for dynamic magnetic resonance imaging (dMRI) [1]. The proposed CS-dMRI method exploits the sparsity of the multi-dimensional MRI signal using Higher-order singular value decomposition (HOSVD). Our preliminary study indicates that, compared with conventional approaches, the proposed CS method offers further acceleration in acquisition and also improves image quality. To further enhance the algorithm efficiency, in this work, we present a parallelized implementation of the HOSVD-based CS reconstructions using a graphics processing unit (GPU). The cine cardiac MRI study indicated the efficiency and accuracy of the GPU-accelerated high-dimensional CS-dMRI method.

Volume selective excitation has a variety of uses in clinical magnetic resonance imaging, but can suffer from insufficient excitation accuracy and impractically long pulse duration in ultra-high field applications. Based on recently-developed parallel transmission techniques, an optimized 3D tailored radio-frequency RF (TRF) pulse, designed with a novel 3D adaptive trajectory, is proposed to improve and accelerate volume selective excitation. The trajectory is designed to be regular-shaped and adaptively stretched according to the size of a 3D k-space "trajectory container." The container is designed to hold most of the RF energy deposition responsible for the desired pattern in the excitation k-space in the use of the blurring patterns caused by the multichannel sensitivity maps. The proposed method can also be used to reduce both global and peak RF energy required during excitation. The feasibility of this method is confirmed by simulations of ultra-high field cases.