Enforce Data Consistency Research Articles

DEQ-MPI: A Deep Equilibrium Reconstruction With Learned Consistency for Magnetic Particle Imaging.

Magnetic particle imaging (MPI) offers unparalleled contrast and resolution for tracing magnetic nanoparticles. A common imaging procedure calibrates a system matrix (SM) that is used to reconstruct data from subsequent scans. The ill-posed reconstruction problem can be solved by simultaneously enforcing data consistency based on the SM and regularizing the solution based on an image prior. Traditional hand-crafted priors cannot capture the complex attributes of MPI images, whereas recent MPI methods based on learned priors can suffer from extensive inference times or limited generalization performance. Here, we introduce a novel physics-driven method for MPI reconstruction based on a deep equilibrium model with learned data consistency (DEQ-MPI). DEQ-MPI reconstructs images by augmenting neural networks into an iterative optimization, as inspired by unrolling methods in deep learning. Yet, conventional unrolling methods are computationally restricted to few iterations resulting in non-convergent solutions, and they use hand-crafted consistency measures that can yield suboptimal capture of the data distribution. DEQ-MPI instead trains an implicit mapping to maximize the quality of a convergent solution, and it incorporates a learned consistency measure to better account for the data distribution. Demonstrations on simulated and experimental data indicate that DEQ-MPI achieves superior image quality and competitive inference time to state-of-the-art MPI reconstruction methods.

Diffusion Modeling with Domain-conditioned Prior Guidance for Accelerated MRI and qMRI Reconstruction.

This study introduces a novel image reconstruction technique based on a diffusion model that is conditioned on the native data domain. Our method is applied to multi-coil MRI and quantitative MRI (qMRI) reconstruction, leveraging the domain-conditioned diffusion model within the frequency and parameter domains. The prior MRI physics are used as embeddings in the diffusion model, enforcing data consistency to guide the training and sampling process, characterizing MRI k-space encoding in MRI reconstruction, and leveraging MR signal modeling for qMRI reconstruction. Furthermore, a gradient descent optimization is incorporated into the diffusion steps, enhancing feature learning and improving denoising. The proposed method demonstrates a significant promise, particularly for reconstructing images at high acceleration factors. Notably, it maintains great reconstruction accuracy for static and quantitative MRI reconstruction across diverse anatomical structures. Beyond its immediate applications, this method provides potential generalization capability, making it adaptable to inverse problems across various domains.

Cascade of Denoising and Mapping Neural Networks for MRI R2* Relaxometry of Iron-Loaded Liver

MRI of effective transverse relaxation rate (R2*) measurement is a reliable method for liver iron concentration quantification. However, R2* mapping can be degraded by noise, especially in the case of iron overload. This study aimed to develop a deep learning method for MRI R2* relaxometry of an iron-loaded liver using a two-stage cascaded neural network. The proposed method, named CadamNet, combines two convolutional neural networks separately designed for image denoising and parameter mapping into a cascade framework, and the physics-based R2* decay model was incorporated in training the mapping network to enforce data consistency further. CadamNet was trained using simulated liver data with Rician noise, which was constructed from clinical liver data. The performance of CadamNet was quantitatively evaluated on simulated data with varying noise levels as well as clinical liver data and compared with the single-stage parameter mapping network (MappingNet) and two conventional model-based R2* mapping methods. CadamNet consistently achieved high-quality R2* maps and outperformed MappingNet at varying noise levels. Compared with conventional R2* mapping methods, CadamNet yielded R2* maps with lower errors, higher quality, and substantially increased efficiency. In conclusion, the proposed CadamNet enables accurate and efficient iron-loaded liver R2* mapping, especially in the presence of severe noise.

Wave-Encoded Model-Based Deep Learning for Highly Accelerated Imaging with Joint Reconstruction.

A recently introduced model-based deep learning (MoDL) technique successfully incorporates convolutional neural network (CNN)-based regularizers into physics-based parallel imaging reconstruction using a small number of network parameters. Wave-controlled aliasing in parallel imaging (CAIPI) is an emerging parallel imaging method that accelerates imaging acquisition by employing sinusoidal gradients in the phase- and slice/partition-encoding directions during the readout to take better advantage of 3D coil sensitivity profiles. We propose wave-encoded MoDL (wave-MoDL) combining the wave-encoding strategy with unrolled network constraints for highly accelerated 3D imaging while enforcing data consistency. We extend wave-MoDL to reconstruct multicontrast data with CAIPI sampling patterns to leverage similarity between multiple images to improve the reconstruction quality. We further exploit this to enable rapid quantitative imaging using an interleaved look-locker acquisition sequence with T2 preparation pulse (3D-QALAS). Wave-MoDL enables a 40 s MPRAGE acquisition at 1 mm resolution at 16-fold acceleration. For quantitative imaging, wave-MoDL permits a 1:50 min acquisition for T1, T2, and proton density mapping at 1 mm resolution at 12-fold acceleration, from which contrast-weighted images can be synthesized as well. In conclusion, wave-MoDL allows rapid MR acquisition and high-fidelity image reconstruction and may facilitate clinical and neuroscientific applications by incorporating unrolled neural networks into wave-CAIPI reconstruction.

Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers.

Supervised reconstruction models are characteristically trained on matched pairs of undersampled and fully-sampled data to capture an MRI prior, along with supervision regarding the imaging operator to enforce data consistency. To reduce supervision requirements, the recent deep image prior framework instead conjoins untrained MRI priors with the imaging operator during inference. Yet, canonical convolutional architectures are suboptimal in capturing long-range relationships, and priors based on randomly initialized networks may yield suboptimal performance. To address these limitations, here we introduce a novel unsupervised MRI reconstruction method based on zero-Shot Learned Adversarial TransformERs (SLATER). SLATER embodies a deep adversarial network with cross-attention transformers to map noise and latent variables onto coil-combined MR images. During pre-training, this unconditional network learns a high-quality MRI prior in an unsupervised generative modeling task. During inference, a zero-shot reconstruction is then performed by incorporating the imaging operator and optimizing the prior to maximize consistency to undersampled data. Comprehensive experiments on brain MRI datasets clearly demonstrate the superior performance of SLATER against state-of-the-art unsupervised methods.

Optimizing constrained reconstruction in magnetic resonance imaging for signal detection

Constrained reconstruction in magnetic resonance imaging (MRI) allows the use of prior information through constraints to improve reconstructed images. These constraints often take the form of regularization terms in the objective function used for reconstruction. Constrained reconstruction leads to images which appear to have fewer artifacts than reconstructions without constraints but because the methods are typically nonlinear, the reconstructed images have artifacts whose structure is hard to predict. In this work, we compared different methods of optimizing the regularization parameter using a total variation (TV) constraint in the spatial domain and sparsity in the wavelet domain for one-dimensional (2.56×) undersampling using variable density undersampling. We compared the mean squared error (MSE), structural similarity (SSIM), L-curve and the area under the receiver operating characteristic (AUC) using a linear discriminant for detecting a small and a large signal. We used a signal-known-exactly task with varying backgrounds in a simulation where the anatomical variation was the major source of clutter for the detection task. Our results show that the AUC dependence on regularization parameters varies with the imaging task (i.e. the signal being detected). The choice of regularization parameters for MSE, SSIM, L-curve and AUC were similar. We also found that a model-based reconstruction including TV and wavelet sparsity did slightly better in terms of AUC than just enforcing data consistency but using these constraints resulted in much better MSE and SSIM. These results suggest that the increased performance in MSE and SSIM over-estimate the improvement in detection performance for the tasks in this paper. The MSE and SSIM metrics show a big difference in performance where the difference in AUC is small. To our knowledge, this is the first time that signal detection with varying backgrounds has been used to optimize constrained reconstruction in MRI.

Joint calibrationless reconstruction of highly undersampled multicontrast MR datasets using a low-rank Hankel tensor completion framework.

To jointly reconstruct highly undersampled multicontrast two-dimensional (2D) datasets through a low-rank Hankel tensor completion framework. A multicontrast Hankel tensor completion (MC-HTC) framework is proposed to exploit the shareable information in multicontrast datasets with respect to their highly correlated image structure, common spatial support, and shared coil sensitivity for joint reconstruction. This is achieved by first organizing multicontrast k-space datasets into a single block-wise Hankel tensor. Subsequent low-rank tensor approximation via higher-order singular value decomposition (HOSVD) uses the image structural correlation by considering different contrasts as virtual channels. Meanwhile, the HOSVD imposes common spatial support and shared coil sensitivity by treating data from different contrasts as from additional k-space kernels. The missing k-space data are then recovered by iteratively performing such low-rank approximation and enforcing data consistency. This joint reconstruction framework was evaluated using multicontrast multichannel 2D human brain datasets (T1 -weighted, T2 -weighted, fluid-attenuated inversion recovery, and T1 -weighted-inversion recovery) of identical image geometry with random and uniform undersampling schemes. The proposed method offered high acceleration, exhibiting significantly less residual errors when compared with both single-contrast SAKE (simultaneous autocalibrating and k-space estimation) and multicontrast J-LORAKS (joint parallel-imaging-low-rank matrix modeling of local k-space neighborhoods) low-rank reconstruction. Furthermore, the MC-HTC framework was applied uniquely to Cartesian uniform undersampling by incorporating a novel complementary k-space sampling strategy where the phase-encoding direction among different contrasts is orthogonally alternated. The proposed MC-HTC approach presents an effective tensor completion framework to jointly reconstruct highly undersampled multicontrast 2D datasets without coil-sensitivity calibration.

Improved robust tensor principal component analysis for accelerating dynamic MR imaging reconstruction.

Dynamic magnetic resonance imaging (dMRI) strikes a balance between reconstruction speed and image accuracy in medical imaging field. In this paper, an improved robust tensor principal component analysis (RTPCA) method is proposed to reconstruct the dynamic magnetic resonance imaging (MRI) from highly under-sampled K-space data. The MR reconstruction problem is formulated as a high-order low-rank tenor plus sparse tensor recovery problem, which is solved by robust tensor principal component analysis (RTPCA) with a new tensor nuclear norm (TNN). To further exploit the low-rank structures in multi-way data, the core matrix nuclear norm, extracted from the diagonal elements of the core tensor under tensor singular value decomposition (t-SVD) framework, is also integrated into TNN for enforcing the low-rank structure in MRI datasets. The experimental results show that the proposed method outperforms state-of-the-art methods in terms of both MR image reconstruction accuracy and computational efficiency on 3D and 4D experiment datasets, especially for 4D MR image reconstruction. Graphical abstract The flowchart of the proposed method to reconstruct the dynamic magnetic resonance imaging (MRI) from highly under-sampled K-space data in the kth iteration. To further exploit the low-rank structures in multi-way data, the core matrix nuclear norm, extracted from the diagonal elements of the core tensor under tensor singular value decomposition (t-SVD) framework, is also integrated into tensor nuclear norm (TNN) for enforcing the low-rank structure in MRI datasets. In each iteration, the first step is to get low-rank tensor ℓk - 1 by using soft thresholding on the singular values of ℓk - 1 = χk - 1 - ξk - 1, and an improved tensor nuclear norm method is proposed to process the low-rank tensor ℓk - 1 firstly. Then, the shrinkage operator is applied to ξk - 1 = χk - 1 - ℓk - 1 for sparse part ξk - 1. The final reconstructed d-MRI χk is obtained by enforcing data consistency that the residual in K-space is subtracted by the sum of the reconstructed low-rank tensor and sparse tensor.

MoDL: Model-Based Deep Learning Architecture for Inverse Problems.

We introduce a model-based image reconstruction framework with a convolution neural network (CNN)-based regularization prior. The proposed formulation provides a systematic approach for deriving deep architectures for inverse problems with the arbitrary structure. Since the forward model is explicitly accounted for, a smaller network with fewer parameters is sufficient to capture the image information compared to direct inversion approaches. Thus, reducing the demand for training data and training time. Since we rely on end-to-end training with weight sharing across iterations, the CNN weights are customized to the forward model, thus offering improved performance over approaches that rely on pre-trained denoisers. Our experiments show that the decoupling of the number of iterations from the network complexity offered by this approach provides benefits, including lower demand for training data, reduced risk of overfitting, and implementations with significantly reduced memory footprint. We propose to enforce data-consistency by using numerical optimization blocks, such as conjugate gradients algorithm within the network. This approach offers faster convergence per iteration, compared to methods that rely on proximal gradients steps to enforce data consistency. Our experiments show that the faster convergence translates to improved performance, primarily when the available GPU memory restricts the number of iterations.

Discovery of genuine functional dependencies from relational data with missing values

Functional dependencies (FDs) play an important role in maintaining data quality. They can be used to enforce data consistency and to guide repairs over a database. In this work, we investigate the problem of missing values and its impact on FD discovery. When using existing FD discovery algorithms, some genuine FDs could not be detected precisely due to missing values or some non-genuine FDs can be discovered even though they are caused by missing values with a certain NULL semantics. We define a notion of genuineness and propose algorithms to compute the genuineness score of a discovered FD. This can be used to identify the genuine FDs among the set of all valid dependencies that hold on the data. We evaluate the quality of our method over various real-world and semi-synthetic datasets with extensive experiments. The results show that our method performs well for relatively large FD sets and is able to accurately capture genuine FDs.

A Plug-and-Play Priors Approach for Solving Nonlinear Imaging Inverse Problems

In the past two decades, nonlinear image reconstruction methods have led to substantial improvements in the capabilities of numerous imaging systems. Such methods are traditionally formulated as optimization problems that are solved iteratively by simultaneously enforcing data consistency and incorporating prior models. Recently, the Plug-and-Play Priors (PPP) framework suggested that by using more sophisticated denoisers, not necessarily corresponding to an optimization objective, it is possible to improve the quality of reconstructed images. In this letter, we show that the PPP approach is applicable beyond linear inverse problems. In particular, we develop the fast iterative shrinkage/thresholding algorithm variant of PPP for model-based nonlinear inverse scattering. The key advantage of the proposed formulation over the original ADMM-based one is that it does not need to perform an inversion on the forward model. We show that the proposed method produces high quality images using both simulated and experimentally measured data.

WE‐AB‐207A‐08: BEST IN PHYSICS (IMAGING): Advanced Scatter Correction and Iterative Reconstruction for Improved Cone‐Beam CT Imaging On the TrueBeam Radiotherapy Machine

Purpose:To improve CBCT image quality for image‐guided radiotherapy by applying advanced reconstruction algorithms to overcome scatter, noise, and artifact limitationsMethods:CBCT is used extensively for patient setup in radiotherapy. However, image quality generally falls short of diagnostic CT, limiting soft‐tissue based positioning and potential applications such as adaptive radiotherapy. The conventional TrueBeam CBCT reconstructor uses a basic scatter correction and FDK reconstruction, resulting in residual scatter artifacts, suboptimal image noise characteristics, and other artifacts like cone‐beam artifacts. We have developed an advanced scatter correction that uses a finite‐element solver (AcurosCTS) to model the behavior of photons as they pass (and scatter) through the object. Furthermore, iterative reconstruction is applied to the scatter‐corrected projections, enforcing data consistency with statistical weighting and applying an edge‐preserving image regularizer to reduce image noise. The combined algorithms have been implemented on a GPU. CBCT projections from clinically operating TrueBeam systems have been used to compare image quality between the conventional and improved reconstruction methods. Planning CT images of the same patients have also been compared.Results:The advanced scatter correction removes shading and inhomogeneity artifacts, reducing the scatter artifact from 99.5 HU to 13.7 HU in a typical pelvis case. Iterative reconstruction provides further benefit by reducing image noise and eliminating streak artifacts, thereby improving soft‐tissue visualization. In a clinical head and pelvis CBCT, the noise was reduced by 43% and 48%, respectively, with no change in spatial resolution (assessed visually). Additional benefits include reduction of cone‐beam artifacts and reduction of metal artifacts due to intrinsic downweighting of corrupted rays.Conclusion:The combination of an advanced scatter correction with iterative reconstruction substantially improves CBCT image quality. It is anticipated that clinically acceptable reconstruction times will result from a multi‐GPU implementation (the algorithms are under active development and not yet commercially available).All authors are employees of and (may) own stock of Varian Medical Systems.

Conflict resolution with data currency and consistency

This article introduces a new approach for conflict resolution: given a set of tuples pertaining to the same entity, it identifies a single tuple in which each attribute has the latest and consistent value in the set. This problem is important in data integration, data cleaning, and query answering. It is, however, challenging since in practice, reliable time stamps are often absent, among other things. We propose a model for conflict resolution by specifying data currency in terms of partial currency orders and currency constraints and by enforcing data consistency with constant conditional functional dependencies. We show that identifying data currency orders helps us repair inconsistent data, and vice versa. We investigate a number of fundamental problems associated with conflict resolution and establish their complexity. In addition, we introduce a framework and develop algorithms for conflict resolution by integrating data currency and consistency inferences into a single process and by interacting with users. We experimentally verify the accuracy and efficiency of our methods using real-life and synthetic data.

Enforcing data consistency in data integration systems by XQuery trigger service

PurposeExtensible Markup Language (XML)‐based data integration systems (DIS) aim to support global updates. Data consistency among data sources is not yet enforced at the integration level or enforced in an ad hoc manner which leads to redundant checking of consistency or unrepairable mistakes. This paper aims to provide XQuery trigger service to enforce data integrity and data consistency in the DIS at the integration level.Design/methodology/approachData consistency is enforced among data sources through providing XQuery trigger service for the XML‐DIS. An XQuery trigger model is defined and shown how to use this model to define different integrity constraints and triggers at the integration level. The paper proposes the architecture of the XQuery trigger service and shows how to enforce data consistency in the DIS. Important components including event detection, condition evaluation and action firing are discussed. Necessary algorithms including how to produce ChangeRecord, how to find activated triggers, how to process LET and FOR clauses and how to create data objects from XML fragment are proposed. Trigger termination and failure handling are also discussed.FindingsXQuery trigger can express miscellaneous data integrity constraints and triggers in the DIS and is highly abstract, refined and easy to understand. XQuery trigger service provides an easy‐to‐maintain method of the data consistency rules and a uniform, nonredundant and centralized enforcement of data consistency.Originality/valueAn XQuery trigger model with namespace annotations, which can define constraints and triggers among different data sources. An XQuery trigger service architecture for the XML‐DIS, which can enforce data consistency at the integration level. For DIS administrators, who want to enforce data consistency when permitting updates at the integration level.

Shared-storage clusters

Clusters represent a collection of interconnected computers that collaborate on executing an application and present themselves as one unified computing resource. They are becoming an important segment in the computer industry. The two main flavors of cluster architectures are shared-storage and shared-nothing. This article presents host and I/O implementation details, and performance trade-offs that need to be enforced due to sharing data in shared-storage clusters. Sharing data requires the need for global concurrency and coherency protocols to maintain consistency of the database, and enforce data consistency in the local node’s buffers, respectively. Various shared-storage architectures will be investigated, including the Virtual Shared and Shared-Intermediate Memory models. This article also presents few selected shared-storage clusters, including the DEC VAXCluster, IBM parallel Sysplex and Compaq/Tandem ServerNet.