Cardiac magnetic resonance (CMR) imaging is widely used to characterize cardiac morphology and function. To accelerate CMR imaging, various methods have been proposed to recover high-quality spatiotemporal CMR images from highly undersampled k-t space data. However, current CMR reconstruction techniques either fail to achieve satisfactory image quality or are restricted by the scarcity of ground truth data, leading to limited applicability in clinical scenarios. In this work, we proposed MoCo‑INR, a new unsupervised method that integrates implicit neural representations (INR) with the conventional motion‑compensated (MoCo) framework. Using the explicit motion modeling and the continuous prior of INRs, our MoCo-INR can produce accurate cardiac motion decomposition and high-quality CMR reconstruction. Moreover, we present a new INR network architecture tailored to the CMR problem, which can greatly stabilize model optimization. Experiments on retrospective (i.e., simulated) datasets demonstrate the superiority of MoCo‑INR over state‑of‑the‑art methods, achieving fast convergence and fine‑detailed reconstructions at ultra‑high acceleration factors (e.g., 20x in VISTA sampling). In addition, evaluations on prospective (i.e., real-acquired) free‑breathing CMR scans highlight its clinical practicality for real‑time imaging. Several ablation studies also confirm the effectiveness of critical components of MoCo-INR.

Emerging unsupervised implicit neural representation (INR) methods, such as NeRP, NeAT, and SCOPE, have shown great potential in addressing sparse-view computed tomography (SVCT) inverse problems. While these INR-based methods perform well on relatively dense SVCT reconstructions, they struggle to achieve comparable performance with supervised methods in sparser SVCT scenarios and are prone to being affected by noise, limiting their applicability in real clinical settings. Additionally, current methods have not fully explored the use of image domain priors for solving SVCT inverse problems. In this work, we demonstrate that imperfect reconstruction results can provide effective image domain priors for INRs to enhance performance. To leverage this, we introduce Self-prior embedding neural representation (Spener), a novel unsupervised method for SVCT reconstruction that integrates iterative reconstruction algorithms. During each iteration, Spener extracts local image prior features from the previous iteration and embeds them to constrain the solution space. Experimental results on multiple CT datasets show that our unsupervised Spener method achieves performance comparable to supervised state-of-the-art (SOTA) methods on in-domain data while outperforming them on out-of-domain datasets. Moreover, Spener significantly improves the performance of INR-based methods in handling SVCT with noisy sinograms.

High-quality 3D fetal brain MRI reconstruction from motion-corrupted 2D slices is crucial for precise clinical diagnosis and advancing our understanding of fetal brain development. This necessitates reliable slice-to-volume registration (SVR) for motion correction and super-resolution reconstruction (SRR) techniques. Traditional approaches have their limitations, but deep learning (DL) offers the potential in enhancing SVR and SRR. However, most of DL methods require large-scale external 3D high-resolution (HR) training datasets, which is challenging in clinical fetal MRI. To address this issue, we propose an unsupervised iterative joint SVR and SRR DL framework for 3D isotropic HR volume reconstruction. Specifically, our method conceptualizes SVR as a function that maps a 2D slice and a 3D target volume to a rigid transformation matrix, aligning the slice to the underlying location within the target volume. This function is parameterized by a convolutional neural network, which is trained by minimizing the difference between the volume slicing at the predicted position and the actual input slice. For SRR, a decoding network embedded within a deep image prior framework, coupled with a comprehensive image degradation model, is used to produce the HR volume. The deep image prior framework offers a local consistency prior to guide the reconstruction of HR volumes. By performing a forward degradation model, the HR volume is optimized by minimizing the loss between the predicted slices and the acquired slices. Experiments on both large-magnitude motion-corrupted simulation data and clinical data have shown that our proposed method outperforms current state-of-the-art fetal brain reconstruction methods.

Supervised Deep-Learning (DL)-based reconstruction algorithms have shown state-of-the-art results for highly-undersampled dynamic Magnetic Resonance Imaging (MRI) reconstruction. However, the requirement of excessive high-quality ground-truth data hinders their applications due to the generalization problem. Recently, Implicit Neural Representation (INR) has emerged as a powerful DL-based tool for solving the inverse problem by characterizing the attributes of a signal as a continuous function of corresponding coordinates in an unsupervised manner. In this work, we proposed an INR-based method to improve dynamic MRI reconstruction from highly undersampled $\boldsymbol {k}$ -space data, which only takes spatiotemporal coordinates as inputs and does not require any training on external datasets or transfer-learning from prior images. Specifically, the proposed method encodes the dynamic MRI images into neural networks as an implicit function, and the weights of the network are learned from sparsely-acquired ( $\boldsymbol {k}$ , t)-space data itself only. Benefiting from the strong implicit continuity regularization of INR together with explicit regularization for low-rankness and sparsity, our proposed method outperforms the compared state-of-the-art methods at various acceleration factors. E.g., experiments on retrospective cardiac cine datasets show an improvement of 0.6-2.0 dB in PSNR for high accelerations (up to $40.8\times $ ). The high-quality and inner continuity of the images provided by INR exhibit great potential to further improve the spatiotemporal resolution of dynamic MRI. The code is available at: https://github.com/AMRI-Lab/INR_for_DynamicMRI.

Emerging neural reconstruction techniques based on tomography (e.g., NeRF, NeAT, and NeRP) have started showing unique capabilities in medical imaging. In this work, we present a novel Polychromatic neural representation (Polyner) to tackle the challenging problem of CT imaging when metallic implants exist within the human body. CT metal artifacts arise from the drastic variation of metal's attenuation coefficients at various energy levels of the X-ray spectrum, leading to a nonlinear metal effect in CT measurements. Recovering CT images from metal-affected measurements hence poses a complicated nonlinear inverse problem where empirical models adopted in previous metal artifact reduction (MAR) approaches lead to signal loss and strongly aliased reconstructions. Polyner instead models the MAR problem from a nonlinear inverse problem perspective. Specifically, we first derive a polychromatic forward model to accurately simulate the nonlinear CT acquisition process. Then, we incorporate our forward model into the implicit neural representation to accomplish reconstruction. Lastly, we adopt a regularizer to preserve the physical properties of the CT images across different energy levels while effectively constraining the solution space. Our Polyner is an unsupervised method and does not require any external training data. Experimenting with multiple datasets shows that our Polyner achieves comparable or better performance than supervised methods on in-domain datasets while demonstrating significant performance improvements on out-of-domain datasets. To the best of our knowledge, our Polyner is the first unsupervised MAR method that outperforms its supervised counterparts. The code for this work is available at: https://github.com/iwuqing/Polyner.

With the popularity of cloud computing services, an increasing number of users begin to use subscription-based services. Due to the semi-trusted cloud servers that may access the outsourced data, and malicious senders who may publish unauthorized data or junk data, access control encryption (ACE) schemes have been studied recently to enforce secure data write control as well as read control. However, their access control policies are specified by the authority or publishers, which do not apply to the subscriptions. In this paper, we propose DSFlow, a secure and fine-grained flow control system for subscription-based data services. DSFlow is designed in the cloud-edge computing architecture, which employs edge nodes to control the communications between publishers and cloud servers by sanitizing the original ciphertexts to resist malicious publishers, and allows any valid subscriber to decrypt the sanitized ciphertexts in cloud. We introduce a receiver-policy attribute-based ACE (RA-ACE) scheme for DSFlow, which embeds the fine-grained access control policy within the receiver's decryption key. We give a concrete construction of RA-ACE from key-policy attribute-based encryption, structure-preserving signature and non-interactive zero-knowledge proof, and formally prove the no-read rule and no-write rule of RA-ACE. The experiments demonstrate the efficiency of DSFlow compared with existing schemes.

With the rapid development of bioinformatics and the availability of genetic sequencing technologies, genomic data has been used to facilitate personalized medicine. Cloud computing, features as low cost, rich storage and rapid processing can precisely respond to the challenges brought by the emergence of massive genomic data. Considering the security of cloud platform and the privacy of genomic data, we first introduce P2GT which utilizes key-policy attribute-based encryption to realize genomic data access control with unbounded attributes, and employs equality test algorithm to achieve personalized medicine test by matching digitized single nucleotide polymorphisms (SNPs) directly on the users' ciphertext without encrypting multiple times. We then propose an enhanced scheme P2GT+, which adopts identity-based encryption with equality test supporting flexible joint authorization to realize privacy-preserving paternity test, genetic compatibility test and disease susceptibility test over the encrypted SNPs with P2GT. We prove the security of proposed schemes and conduct extensive experiments with the 1,000 Genomes dataset. The results show that P2GT and P2GT+ are practical and scalable enough to meet the privacy-preserving and authorized genetic testing requirements in cloud computing.

Nowadays, the rapid development of edge computing is accelerating the data sharing between cloud computing platforms and mobile users. These data often contain sensitive information, which faces severe leakage risks not only from the semi-trusted cloud servers but also from the malicious senders in the organizations. Fortunately, access control encryption (ACE) has been utilized to secure the data with access control policies, in which a sanitizer (e.g., the edge node) is employed to check all the communications between the sender and receiver, and drop illegal ciphertexts according to the access control policy. However, previous schemes have some limitations in mobile edge cloud, e.g., the sender's attributes are not strictly authenticated in the attribute-based access control policy, or the sanitization time is the bottleneck of fast data sharing. To this end, we introduce PSFlow, a parallel secure flow control framework for private data sharing in mobile edge cloud. First, we propose an attribute-based outsourced ACE (AOACE) scheme, which achieves secure fine-grained data read and write control, and reduces the computational cost of the sender and receiver with outsourced computations in edge nodes. Then, we propose a concrete construction of PSFlow from AOACE, and accelerate the sanitization process with parallel computing. Specifically, PSFlow parallelizes the sanitization operations with a multi-server model in each edge node, and optimizes the sanitization efficiency in each edge server by constructing a shared pool from the attribute universe. The experimental results show that PSFlow is more efficient and practical than previous schemes in mobile edge cloud.