Modern MRI scanners utilize one or more arrays of small receive-only coils to collect k-space data. The sensitivity maps of the coils, when estimated using traditional methods, differ from the true sensitivity maps, which are generally unknown. Consequently, the reconstructed MR images exhibit undesired spatial variation in intensity. These intensity variations can be at least partially corrected using pre-scan data. In this work, we propose an intensity correction method that utilizes pre-scan data. For demonstration, we apply our method to a digital phantom, as well as to cardiac MRI data collected from a commercial scanner by Siemens Healthineers. The code is available at https://github.com/OSU-MR/SCC.
Accelerated magnetic resonance (MR) imaging attempts to reduce acquisition time by collecting data below the Nyquist rate. As an ill-posed inverse problem, many plausible solutions exist, yet the majority of deep learning approaches generate only a single solution. We instead focus on sampling from the posterior distribution, which provides more comprehensive information for downstream inference tasks. To do this, we design a novel conditional normalizing flow (CNF) that infers the signal component in the measurement operator's nullspace, which is later combined with measured data to form complete images. Using fastMRI brain and knee data, we demonstrate fast inference and accuracy that surpasses recent posterior sampling techniques for MRI. Code is available at https://github.com/jwen307/mri_cnf/
PURPOSE: To present and validate a self-supervised MRI reconstruction method that does not require fully sampled k-space data. METHODS: ReSiDe is inspired by plug-and-play (PnP) methods and employs a denoiser as a regularizer. In contrast to traditional PnP approaches that utilize generic denoisers or train deep learning-based denoisers using high-quality images or image patches, ReSiDe directly trains the denoiser on the image or images being reconstructed from the undersampled data. We introduce two variations of our method, ReSiDe-S and ReSiDe-M. ReSiDe-S is scan-specific and works with a single set of undersampled measurements, while ReSiDe-M operates on multiple sets of undersampled measurements. More importantly, the trained denoisers in ReSiDe-M are stored for PnP recovery without further training. To improve robustness, the denoising strength in ReSiDe-S and ReSiDe- M is auto-tuned using the discrepancy principle. RESULTS: Studies I, II, and III compare ReSiDe-S and ReSiDe-M against other self-supervised or unsupervised methods using data from T1- and T2-weighted brain MRI, MRXCAT digital perfusion phantom, and first-pass cardiac perfusion, respectively. ReSiDe-S and ReSiDe-M outperform other methods in terms of reconstruction signal-to-noise ratio and structural similarity index measure for Studies I and II and in terms of expert scoring for Study III. CONCLUSION: A self-supervised image reconstruction method is presented and validated in both static and dynamic MRI applications. These developments can benefit MRI applications where availability of fully sampled training data is limited.
In inverse problems, one seeks to reconstruct an image from incomplete and/or degraded measurements. Such problems arise in magnetic resonance imaging (MRI), computed tomography, deblurring, superresolution, inpainting, and other applications. It is often the case that many image hypotheses are consistent with both the measurements and prior information, and so the goal is not to recover a single ``best'' hypothesis but rather to explore the space of probable hypotheses, i.e., to sample from the posterior distribution. In this work, we propose a regularized conditional Wasserstein GAN that can generate dozens of high-quality posterior samples per second. Using quantitative evaluation metrics like conditional Fr\'{e}chet inception distance, we demonstrate that our method produces state-of-the-art posterior samples in both multicoil MRI and inpainting applications.
To solve inverse problems, plug-and-play (PnP) methods have been developed that replace the proximal step in a convex optimization algorithm with a call to an application-specific denoiser, often implemented using a deep neural network (DNN). Although such methods have been successful, they can be improved. For example, denoisers are usually designed/trained to remove white Gaussian noise, but the denoiser input error in PnP algorithms is usually far from white or Gaussian. Approximate message passing (AMP) methods provide white and Gaussian denoiser input error, but only when the forward operator is a large random matrix. In this work, for Fourier-based forward operators, we propose a PnP algorithm based on generalized expectation-consistent (GEC) approximation -- a close cousin of AMP -- that offers predictable error statistics at each iteration, as well as a new DNN denoiser that leverages those statistics. We apply our approach to magnetic resonance imaging (MRI) image recovery and demonstrate its advantages over existing PnP and AMP methods.
Plug-and-play (PnP) methods that employ application-specific denoisers have been proposed to solve inverse problems, including MRI reconstruction. However, training application-specific denoisers is not feasible for many applications due to the lack of training data. In this work, we propose a PnP-inspired recovery method that does not require data beyond the single, incomplete set of measurements. The proposed method, called recovery with a self-calibrated denoiser (ReSiDe), trains the denoiser from the patches of the image being recovered. The denoiser training and a call to the denoising subroutine are performed in each iteration of a PnP algorithm, leading to a progressive refinement of the reconstructed image. For validation, we compare ReSiDe with a compressed sensing-based method and a PnP method with BM3D denoising using single-coil MRI brain data.
We consider the problem of classifying noisy, phase-modulated radar waveforms. While traditionally this has been accomplished by applying classical machine-learning algorithms on hand-crafted features, it has recently been shown that better performance can be attained by training deep neural networks (DNNs) to classify raw I/Q waveforms. However, existing DNNs assume time-synchronized waveforms and do not exploit complex-valued signal structure, and many aspects of the their DNN design and training are suboptimal. We demonstrate that, with an improved DNN architecture and training procedure, it is possible to reduce classification error from 18% to 0.14% on asynchronous waveforms from the SIDLE dataset. Unlike past work, we furthermore demonstrate that accurate classification of multiple overlapping waveforms is also possible, by achieving 4.0% error with 4 asynchronous SIDLE waveforms.
This article considers "sketched learning," or "compressive learning," an approach to large-scale machine learning where datasets are massively compressed before learning (e.g., clustering, classification, or regression) is performed. In particular, a "sketch" is first constructed by computing carefully chosen nonlinear random features (e.g., random Fourier features) and averaging them over the whole dataset. Parameters are then learned from the sketch, without access to the original dataset. This article surveys the current state-of-the-art in sketched learning, including the main concepts and algorithms, their connections with established signal-processing methods, existing theoretical guarantees---on both information preservation and privacy preservation, and important open problems.
Cardiac magnetic resonance imaging (CMR) is a noninvasive imaging modality that provides a comprehensive evaluation of the cardiovascular system. The clinical utility of CMR is hampered by long acquisition times, however. In this work, we propose and validate a plug-and-play (PnP) method for CMR reconstruction from undersampled multi-coil data. To fully exploit the rich image structure inherent in CMR, we pair the PnP framework with a deep learning (DL)-based denoiser that is trained using spatiotemporal patches from high-quality, breath-held cardiac cine images. The resulting "PnP-DL" method iterates over data consistency and denoising subroutines. We compare the reconstruction performance of PnP-DL to that of compressed sensing (CS) using eight breath-held and ten real-time (RT) free-breathing cardiac cine datasets. We find that, for breath-held datasets, PnP-DL offers more than one dB advantage over commonly used CS methods. For RT free-breathing datasets, where ground truth is not available, PnP-DL receives higher scores in qualitative evaluation. The results highlight the potential of PnP-DL to accelerate RT CMR.
We consider the problem of inferring the input and hidden variables of a stochastic multi-layer neural network from an observation of the output. The hidden variables in each layer are represented as matrices. This problem applies to signal recovery via deep generative prior models, multi-task and mixed regression and learning certain classes of two-layer neural networks. A unified approximation algorithm for both MAP and MMSE inference is proposed by extending a recently-developed Multi-Layer Vector Approximate Message Passing (ML-VAMP) algorithm to handle matrix-valued unknowns. It is shown that the performance of the proposed Multi-Layer Matrix VAMP (ML-Mat-VAMP) algorithm can be exactly predicted in a certain random large-system limit, where the dimensions $N\times d$ of the unknown quantities grow as $N\rightarrow\infty$ with $d$ fixed. In the two-layer neural-network learning problem, this scaling corresponds to the case where the number of input features and training samples grow to infinity but the number of hidden nodes stays fixed. The analysis enables a precise prediction of the parameter and test error of the learning.