Deep generative models have gained recent traction in accelerated MRI reconstruction. Diffusion priors are particularly promising given their representational fidelity. Instead of the target transformation from undersampled to fully-sampled data required for MRI reconstruction, common diffusion priors are trained to learn a task-agnostic transformation from an asymptotic start-point of Gaussian noise onto the finite end-point of fully-sampled data. During inference, data-consistency projections are injected in between reverse diffusion steps to reach a compromise solution within the span of both the trained diffusion prior and the imaging operator for an accelerated MRI acquisition. Unfortunately, performance losses can occur due to the discrepancy between target and learned transformations given the asymptotic normality assumption in diffusion priors. To address this discrepancy, here we introduce a novel Fourier-constrained diffusion bridge (FDB) for MRI reconstruction that transforms between a finite start-point of moderately undersampled data and an end-point of fully-sampled data. We derive the theoretical formulation of FDB as a generalized diffusion process based on a stochastic degradation operator that performs random spatial-frequency removal. We propose an enhanced sampling algorithm with a learned correction term for soft dealiasing across reverse diffusion steps. Demonstrations on brain MRI indicate that FDB outperforms state-of-the-art methods including non-diffusion and diffusion priors.
This paper reports the development of a Python Non-Uniform Fast Fourier Transform (PyNUFFT) package, which accelerates non-Cartesian image reconstruction on heterogeneous platforms. Scientific computing with Python encompasses a mature and integrated environment. The NUFFT algorithm has been extensively used for non-Cartesian image reconstruction but previously there was no native Python NUFFT library. The current PyNUFFT software enables multi-dimensional NUFFT on heterogeneous platforms. The PyNUFFT also provides several solvers, including the conjugate gradient method, $\ell$1 total-variati…
Magnetic Resonance Imaging (MRI) is an important medical imaging modality, while it requires a long acquisition time. To reduce the acquisition time, various methods have been proposed. However, these methods failed to reconstruct images with a clear structure for two main reasons. Firstly, similar patches widely exist in MR images, while most previous deep learning-based methods ignore this property and only adopt CNN to learn local information. Secondly, the existing methods only use clear images to constrain the upper bound of the solution space, while the lower bound is not constrained, so…
Self-Consistent Nested Diffusion Bridge for Accelerated MRI Reconstruction
School of Information Science and Technology, Fudan University, Shanghai, China（复旦大学信息科学与技术学院）；Department of Data Science & AI, Faculty of Information Technology, Monash University, Melbourne, Australia（墨尔本大学信息科技学院数据科学与人工智能系）；Nuffield Department of Clinical Neurosciences, University of Oxford, London, UK（牛津大学临床神经科学系）；School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, China（电子科技大学机械与电子工程学院）；Department of Radiology, Sichuan Provincial People’s Hospital, Chengdu, China（四川省人民医院放射科）；Department of Radiology, Zhongda Hospital, Medical School, Southeast University, Nanjing, China（东南大学医学院中大医院放射科）；Shanghai AI Lab, Shanghai, China（上海人工智能实验室）；Sensetime Research, Shanghai, China（商汤研究）
We develop and evaluate a neural network-based method for Gibbs artifact and noise removal. A convolutional neural network (CNN) was designed for artifact removal in diffusion-weighted imaging data. Two implementations were considered: one for magnitude images and one for complex images. Both models were based on the same encoder-decoder structure and were trained by simulating MRI acquisitions on synthetic non-MRI images. Both machine learning methods were able to mitigate artifacts in diffusion-weighted images and diffusion parameter maps. The CNN for complex images was also able to reduce a…
Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（拉特伯研究中心生物医学成像，深圳先进技术研究所，中国科学院）；School of Artificial Intelligence, the University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）；Research Center for Medical AI, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（医学人工智能研究中心，深圳先进技术研究所，中国科学院）；Pazhou Lab, Guangzhou, China（琶洲实验室，广州，中国）；School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen, China（生物医学工程学院，深圳大学医学院，深圳大学，深圳，中国）
The Nyquist-Shannon theorem states that the information accessible by discrete Fourier protocols saturates when the sampling rate reaches twice the bandwidth of the detected continuous time signal. This maximum rate (the NS-limit) plays a prominent role in Magnetic Resonance Imaging (MRI). Nevertheless, reconstruction methods other than Fourier analysis can extract useful information from data oversampled with respect to the NS-limit, given that relevant prior knowledge is available. Here we present PhasE-Constrained OverSampled MRI (PECOS), a method that exploits data oversampling in combinat…
Sorbonne Université（索邦大学）；Institut du Cerveau - Paris Brain Institute - ICM（巴黎大脑研究所（ICM））；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；Inserm（法国国家健康与医学研究院）；AP-HP（巴黎公共援助医院集团）；Hôpital de la Pitié Salpêtrière（皮蒂耶-萨尔佩特里埃医院）
Early and accurate diagnosis of parkinsonian syndromes is critical to provide appropriate care to patients and for inclusion in therapeutic trials. The red nucleus is a structure of the midbrain that plays an important role in these disorders. It can be visualized using iron-sensitive magnetic resonance imaging (MRI) sequences. Different iron-sensitive contrasts can be produced with MRI. Combining such multimodal data has the potential to improve segmentation of the red nucleus. Current multimodal segmentation algorithms are computationally consuming, cannot deal with missing modalities and ne…
Facebook AI Research（Facebook人工智能研究）；fastMRI team（fastMRI团队）
Deep learning approaches to accelerated MRI take a matrix of sampled Fourier-space lines as input and produce a spatial image as output. In this work we show that by careful choice of the offset used in the sampling procedure, the symmetries in k-space can be better exploited, producing higher quality reconstructions than given by standard equally-spaced samples or randomized samples motivated by compressed sensing.
There is growing interest in learning Fourier domain sampling strategies (particularly for magnetic resonance imaging, MRI) using optimization approaches. For non-Cartesian sampling patterns, the system models typically involve non-uniform FFT (NUFFT) operations. Commonly used NUFFT algorithms contain frequency domain interpolation, which is not differentiable with respect to the sampling pattern, complicating the use of gradient methods. This paper describes an efficient and accurate approach for computing approximate gradients involving NUFFTs. Multiple numerical experiments validated the im…
The advanced magnetic resonance (MR) image reconstructions such as the compressed sensing and subspace-based imaging are considered as large-scale, iterative, optimization problems. Given the large number of reconstructions required by the practical clinical usage, the computation time of these advanced reconstruction methods is often unacceptable. In this work, we propose using Google's Tensor Processing Units (TPUs) to accelerate the MR image reconstruction. TPU is an application-specific integrated circuit (ASIC) for machine learning applications, which has recently been used to solve large…
EPFL（洛桑联邦理工学院）；Bilkent University（比尔肯特大学）；National University of Singapore（新加坡国立大学）
In the area of magnetic resonance imaging (MRI), an extensive range of non-linear reconstruction algorithms have been proposed that can be used with general Fourier subsampling patterns. However, the design of these subsampling patterns has typically been considered in isolation from the reconstruction rule and the anatomy under consideration. In this paper, we propose a learning-based framework for optimizing MRI subsampling patterns for a specific reconstruction rule and anatomy, considering both the noiseless and noisy settings. Our learning algorithm has access to a representative set of t…
CEA/NeuroSpin（法国原子能与替代能源委员会神经自旋中心）；CEA（法国原子能与替代能源委员会）；CNRS（法国国家科学研究中心）；Université Paris-Saclay（巴黎萨克雷大学）；Université Paris Diderot（巴黎第七大学）；Sorbonne Paris Cité（索邦巴黎西岱大学）；Inria Saclay Ile-de-France（法国国家信息与自动化研究所萨克雷-法兰西岛分院）
Deep neural networks have recently been thoroughly investigated as a powerful tool for MRI reconstruction. There is a lack of research, however, regarding their use for a specific setting of MRI, namely non-Cartesian acquisitions. In this work, we introduce a novel kind of deep neural networks to tackle this problem, namely density compensated unrolled neural networks, which rely on Density Compensation to correct the uneven weighting of the k-space. We assess their efficiency on the publicly available fastMRI dataset, and perform a small ablation study. Our results show that the density-compe…
MMR-Mamba: Multi-Modal MRI Reconstruction with Mamba and Spatial-Frequency Information Fusion
The Hong Kong Polytechnic University（香港理工大学）；University of Science and Technology of China（中国科学技术大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Stanford University（斯坦福大学）
Self-Consistent Recursive Diffusion Bridge for Medical Image Translation
Bilkent University（毕尔肯大学）；National Magnetic Resonance Research Center (UMRAM)（国家磁共振研究中心）；Stanford University（斯坦福大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
University of Minnesota（明尼苏达大学）；Sungkyunkwan University（成均馆大学）
Recent studies show that deep learning (DL) based MRI reconstruction outperforms conventional methods, such as parallel imaging and compressed sensing (CS), in multiple applications. Unlike CS that is typically implemented with pre-determined linear representations for regularization, DL inherently uses a non-linear representation learned from a large database. Another line of work uses transform learning (TL) to bridge the gap between these two approaches by learning linear representations from data. In this work, we combine ideas from CS, TL and DL reconstructions to learn deep linear convol…
University of Florida（佛罗里达大学）；Georgia State University（佐治亚州立大学）
Goal: This work aims at developing a novel calibration-free fast parallel MRI (pMRI) reconstruction method incorporate with discrete-time optimal control framework. The reconstruction model is designed to learn a regularization that combines channels and extracts features by leveraging the information sharing among channels of multi-coil images. We propose to recover both magnitude and phase information by taking advantage of structured convolutional networks in image and Fourier spaces. Methods: We develop a novel variational model with a learnable objective function that integrates an adapti…
Optimizing k-space sampling trajectories is a promising yet challenging topic for fast magnetic resonance imaging (MRI). This work proposes to optimize a reconstruction method and sampling trajectories jointly concerning image reconstruction quality in a supervised learning manner. We parameterize trajectories with quadratic B-spline kernels to reduce the number of parameters and apply multi-scale optimization, which may help to avoid sub-optimal local minima. The algorithm includes an efficient non-Cartesian unrolled neural network-based reconstruction and an accurate approximation for backpr…
Cornell University（康奈尔大学）；Massachusetts General Hospital（麻省总医院）
Acquisition of Magnetic Resonance Imaging (MRI) scans can be accelerated by under-sampling in k-space (i.e., the Fourier domain). In this paper, we consider the problem of optimizing the sub-sampling pattern in a data-driven fashion. Since the reconstruction model's performance depends on the sub-sampling pattern, we combine the two problems. For a given sparsity constraint, our method optimizes the sub-sampling pattern and reconstruction model, using an end-to-end learning strategy. Our algorithm learns from full-resolution data that are under-sampled retrospectively, yielding a sub-sampling …
Recently, the finite-rate-of-innovation (FRI) based continuous domain regularization is emerging as an alternative to the conventional on-the-grid sparse regularization for the compressed sensing (CS) due to its ability to alleviate the basis mismatch between the true support of the shape in the continuous domain and the discrete grid. In this paper, we propose a new off-the-grid regularization for the CS-MRI reconstruction. Following the recent works on two dimensional FRI, we assume that the discontinuities/edges of the image are localized in the zero level set of a band-limited periodic fun…
Magnetic resonance imaging (MRI) is increasingly utilized for image-guided radiotherapy due to its outstanding soft-tissue contrast and lack of ionizing radiation. However, geometric distortions caused by gradient nonlinearity (GNL) limit anatomical accuracy, potentially compromising the quality of tumour treatments. In addition, slow MR acquisition and reconstruction limit the potential for real-time image guidance. Here, we demonstrate a deep learning-based method that rapidly reconstructs distortion-corrected images from raw k-space data for real-time MR-guided radiotherapy applications. We…
Modern MRI schemes, which rely on compressed sensing or deep learning algorithms to recover MRI data from undersampled multichannel Fourier measurements, are widely used to reduce scan time. The image quality of these approaches is heavily dependent on the sampling pattern. We introduce a continuous strategy to jointly optimize the sampling pattern and network parameters. We use a multichannel forward model, consisting of a non-uniform Fourier transform with continuously defined sampling locations, to realize the data consistency block within a model-based deep learning image reconstruction sc…
Magnetic Resonance Imaging (MRI) of hard biological tissues is challenging due to the fleeting lifetime and low strength of their response to resonant stimuli, especially at low magnetic fields. Consequently, the impact of MRI on some medical applications, such as dentistry, continues to be limited. Here, we present three-dimensional reconstructions of ex-vivo human teeth, as well as a rabbit head and part of a cow femur, all obtained at a field strength of only 260 mT. These images are the first featuring soft and hard tissues simultaneously at sub-Tesla fields, and they have been acquired in…
PhaseGen: A Diffusion-Based Approach for Complex-Valued MRI Data Generation
Institute for AI in Medicine (IKIM)（人工智能医学研究所）；University Hospital Essen（埃森大学医院）；Cancer Research Center Cologne Essen (CCCE)（科隆埃森癌症研究中心）；University Medicine Essen（埃森大学医学部）；Technical University Dortmund（多特蒙德工业大学）；German Cancer Research Center (DKFZ)（德国癌症研究中心）；German Cancer Consortium (DKTK)（德国癌症联盟）；University of Duisburg-Essen（杜伊斯堡-埃森大学）
Brigham and Women’s Hospital（布莱根妇女医院）；Harvard Medical School（哈佛医学院）
Magnetic Resonance Imaging (MRI) scans are time consuming and precarious, since the patients remain still in a confined space for extended periods of time. To reduce scanning time, some experts have experimented with undersampled k spaces, trying to use deep learning to predict the fully sampled result. These studies report that as many as 20 to 30 minutes could be saved off a scan that takes an hour or more. However, none of these studies have explored the possibility of using masked image modeling (MIM) to predict the missing parts of MRI k spaces. This study makes use of 11161 reconstructed…
Distributed learning has shown great potential in medical image analysis. It allows to use multi-center training data with privacy protection. However, data distributions in local centers can vary from each other due to different imaging vendors, and annotation protocols. Such variation degrades the performance of learning-based methods. To mitigate the influence, two groups of methods have been proposed for different aims, i.e., the global methods and the personalized methods. The former are aimed to improve the performance of a single global model for all test data from unseen centers (known…
Deep learning networks have shown promising results in fast magnetic resonance imaging (MRI) reconstruction. In our work, we develop deep networks to further improve the quantitative and the perceptual quality of reconstruction. To begin with, we propose reconsynergynet (RSN), a network that combines the complementary benefits of independently operating on both the image and the Fourier domain. For a single-coil acquisition, we introduce deep cascade RSN (DC-RSN), a cascade of RSN blocks interleaved with data fidelity (DF) units. Secondly, we improve the structure recovery of DC-RSN for T2 wei…
Otto von Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）；Human Technopole（人类技术园）；German Centre for Neurodegenerative Disease（德国神经退行性疾病中心）；Centre for Behavioural Brain Sciences（行为脑科学中心）
Computed tomography and magnetic resonance imaging are two widely used clinical imaging modalities for non-invasive diagnosis. However, both of these modalities come with certain problems. CT uses harmful ionising radiation, and MRI suffers from slow acquisition speed. Both problems can be tackled by undersampling, such as sparse sampling. However, such undersampled data leads to lower resolution and introduces artefacts. Several techniques, including deep learning based methods, have been proposed to reconstruct such data. However, the undersampled reconstruction problem for these two modalit…
