Clinical MRI encompasses diverse imaging protocols--spanning anatomical targets (cardiac, brain, knee), contrasts (T1, T2, mapping), sampling patterns (Cartesian, radial, spiral, kt-space), and acceleration factors--yet current deep learning reconstructions are typically protocol-specific, hindering generalization and deployment. We introduce Scalable Deep Unrolled Model (SDUM), a universal framework combining a Restormer-based reconstructor, a learned coil sensitivity map estimator (CSME), sampling-aware weighted data consistency (SWDC), universal conditioning (UC) on cascade index and protocol metadata, and progressive cascade expansion training. SDUM exhibits foundation-model-like scaling behavior: reconstruction quality follows PSNR ${\sim}$ log(parameters) with correlation $r{=}0.986$ ($R^2{=}0.973$) up to 18 cascades, demonstrating predictable performance gains with model depth. A single SDUM trained on heterogeneous data achieves state-of-the-art results across all four CMRxRecon2025 challenge tracks--multi-center, multi-disease, 5T, and pediatric--without task-specific fine-tuning, surpassing specialized baselines by up to ${+}1.0$~dB. On CMRxRecon2024, SDUM outperforms the winning method PromptMR+ by ${+}0.55$~dB; on fastMRI brain, it exceeds PC-RNN by ${+}1.8$~dB. Ablations validate each component: SWDC ${+}0.43$~dB over standard DC, per-cascade CSME ${+}0.51$~dB, UC ${+}0.38$~dB. These results establish SDUM as a practical path toward universal, scalable MRI reconstruction.
Unrolled neural networks have enabled state-of-the-art reconstruction performance and fast inference times for the accelerated magnetic resonance imaging (MRI) reconstruction task. However, these approaches depend on fully-sampled scans as ground truth data which is either costly or not possible to acquire in many clinical medical imaging applications; hence, reducing dependence on data is desirable. In this work, we propose modeling the proximal operators of unrolled neural networks with scale-equivariant convolutional neural networks in order to improve the data-efficiency and robustness to …
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…
Paul C. Lauterbur Research Center for Biomedical Imaging（保罗·C·劳特伯生物医学成像研究中心）；Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences（中国科学院大学深圳先进技术学院）；University at Buffalo, the State University of New York（纽约州立大学布法罗分校）
Image reconstruction from undersampled k-space data has been playing an important role for fast MRI. Recently, deep learning has demonstrated tremendous success in various fields and also shown potential to significantly speed up MR reconstruction with reduced measurements. This article gives an overview of deep learning-based image reconstruction methods for MRI. Three types of deep learning-based approaches are reviewed, the data-driven, model-driven and integrated approaches. The main structure of each network in three approaches is explained and the analysis of common parts of reviewed net…
In accelerated MRI reconstruction, the anatomy of a patient is recovered from a set of under-sampled and noisy measurements. Deep learning approaches have been proven to be successful in solving this ill-posed inverse problem and are capable of producing very high quality reconstructions. However, current architectures heavily rely on convolutions, that are content-independent and have difficulties modeling long-range dependencies in images. Recently, Transformers, the workhorse of contemporary natural language processing, have emerged as powerful building blocks for a multitude of vision task…
Reliable MRI is crucial for accurate interpretation in therapeutic and diagnostic tasks. However, undersampling during MRI acquisition as well as the overparameterized and non-transparent nature of deep learning (DL) leaves substantial uncertainty about the accuracy of DL reconstruction. With this in mind, this study aims to quantify the uncertainty in image recovery with DL models. To this end, we first leverage variational autoencoders (VAEs) to develop a probabilistic reconstruction scheme that maps out (low-quality) short scans with aliasing artifacts to the diagnostic-quality ones. The VA…
Inverse problems for accelerated MRI typically incorporate domain-specific knowledge about the forward encoding operator in a regularized reconstruction framework. Recently physics-driven deep learning (DL) methods have been proposed to use neural networks for data-driven regularization. These methods unroll iterative optimization algorithms to solve the inverse problem objective function, by alternating between domain-specific data consistency and data-driven regularization via neural networks. The whole unrolled network is then trained end-to-end to learn the parameters of the network. Due t…
Cornell University（康奈尔大学）；Weill Medical College of Cornell University（康奈尔大学威尔医学院）
The previously established LOUPE (Learning-based Optimization of the Under-sampling Pattern) framework for optimizing the k-space sampling pattern in MRI was extended in three folds: firstly, fully sampled multi-coil k-space data from the scanner, rather than simulated k-space data from magnitude MR images in LOUPE, was retrospectively under-sampled to optimize the under-sampling pattern of in-vivo k-space data; secondly, binary stochastic k-space sampling, rather than approximate stochastic k-space sampling of LOUPE during training, was applied together with a straight-through (ST) estimator …
Netherlands Cancer Institute（荷兰癌症研究所）；qurAI group（qurAI团队）；University of Amsterdam（阿姆斯特丹大学）
Magnetic Resonance Imaging can produce detailed images of the anatomy and physiology of the human body that can assist doctors in diagnosing and treating pathologies such as tumours. However, MRI suffers from very long acquisition times that make it susceptible to patient motion artifacts and limit its potential to deliver dynamic treatments. Conventional approaches such as Parallel Imaging and Compressed Sensing allow for an increase in MRI acquisition speed by reconstructing MR images from sub-sampled MRI data acquired using multiple receiver coils. Recent advancements in Deep Learning combi…
CoilDrop-MRI: Self-supervised physics-guided MRI reconstruction with coil dropout
School of Biomedical Engineering, Tsinghua Medicine, Tsinghua University（清华大学生物医学工程系）；Oxford Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford（牛津大学整合神经影像中心）；Department of Radiology & Biomedical Imaging, University of California San Francisco（加州大学旧金山分校放射科与生物医学成像系）
Deep learning based on unrolled algorithm has served as an effective method for accelerated magnetic resonance imaging (MRI). However, many methods ignore the direct use of edge information to assist MRI reconstruction. In this work, we present the edge-weighted pFISTA-Net that directly applies the detected edge map to the soft-thresholding part of pFISTA-Net. The soft-thresholding value of different regions will be adjusted according to the edge map. Experimental results of a public brain dataset show that the proposed yields reconstructions with lower error and better artifact suppression co…
Deep learning (DL) based unrolled reconstructions have shown state-of-the-art performance for under-sampled magnetic resonance imaging (MRI). Similar to compressed sensing, DL can leverage high-dimensional data (e.g. 3D, 2D+time, 3D+time) to further improve performance. However, network size and depth are currently limited by the GPU memory required for backpropagation. Here we use a memory-efficient learning (MEL) framework which favorably trades off storage with a manageable increase in computation during training. Using MEL with multi-dimensional data, we demonstrate improved image reconstr…
University of Minnesota（明尼苏达大学）；Center for Magnetic Resonance Research, University of Minnesota（明尼苏达大学磁共振研究中心）
Deep learning (DL) has emerged as a tool for improving accelerated MRI reconstruction. A common strategy among DL methods is the physics-based approach, where a regularized iterative algorithm alternating between data consistency and a regularizer is unrolled for a finite number of iterations. This unrolled network is then trained end-to-end in a supervised manner, using fully-sampled data as ground truth for the network output. However, in a number of scenarios, it is difficult to obtain fully-sampled datasets, due to physiological constraints such as organ motion or physical constraints such…
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China（深圳先进技术研究院，中国科学院，中国）；School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, China（生物医学工程学院，深圳大学医学院，深圳大学，中国）；University of Chinese Academy of Sciences, China（中国科学院大学，中国）；Faculty of Computer Science and Artificial Intelligence, Shenzhen University of Advanced Technology, China（计算机科学与人工智能学院，深圳先进技术大学，中国）；State Key Laboratory of Biomedical Imaging Science and System, Chinese Academy of Sciences, China（生物医学成像科学与系统国家重点实验室，中国科学院，中国）
Cornell University（康奈尔大学）；Massachusetts Institute of Technology（麻省理工学院）；Massachusetts General Hospital（麻省总医院）
Compressed Sensing MRI (CS-MRI) has shown promise in reconstructing under-sampled MR images, offering the potential to reduce scan times. Classical techniques minimize a regularized least-squares cost function using an expensive iterative optimization procedure. Recently, deep learning models have been developed that model the iterative nature of classical techniques by unrolling iterations in a neural network. While exhibiting superior performance, these methods require large quantities of ground-truth images and have shown to be non-robust to unseen data. In this paper, we explore a novel st…
Interlaced R2D2 DNN Series for Scalable Non-Cartesian MRI with Sensitivity Self-calibration
Institute of Sensors, Signals and Systems, Heriot-Watt University Edinburgh, United Kingdom（传感器、信号与系统研究所，赫里奥特-沃斯大学爱丁堡分校，英国）；Department of Diagnostic Imaging and Interventional Radiology, Lausanne University and Hospital, Switzerland（诊断影像与介入放射学系，洛桑大学及医院，瑞士）
UPCMR: A Universal Prompt-guided Model for Random Sampling Cardiac MRI Reconstruction
Leiden University Medical Center（莱顿大学医学中心）；Cardiologs；Philips（飞利浦）；Eindhoven University of Technology（埃因霍温理工大学）；Philips Innovative Technologies（飞利浦创新技术）
Unrolled Reconstruction with Integrated Super-Resolution for Accelerated 3D LGE MRI
Kahlert School of Computing, University of Utah, Salt Lake City, UT, USA Radiology \& Imaging Sciences, University of Utah, Salt Lake City, UT, USA Cardiology, University of Utah, Salt Lake City, UT, USA
Unrolled neural networks have recently achieved state-of-the-art accelerated MRI reconstruction. These networks unroll iterative optimization algorithms by alternating between physics-based consistency and neural-network based regularization. However, they require several iterations of a large neural network to handle high-dimensional imaging tasks such as 3D MRI. This limits traditional training algorithms based on backpropagation due to prohibitively large memory and compute requirements for calculating gradients and storing intermediate activations. To address this challenge, we propose Gre…
While low-rank matrix prior has been exploited in dynamic MR image reconstruction and has obtained satisfying performance, tensor low-rank models have recently emerged as powerful alternative representations for three-dimensional dynamic MR datasets. In this paper, we introduce a novel deep unrolling network for dynamic MRI, namely the learned transform-based tensor low-rank network (LT$^2$LR-Net). First, we generalize the tensor singular value decomposition (t-SVD) into an arbitrary unitary transform-based version and subsequently propose the novel transformed tensor nuclear norm (TTNN). Then…
Graz University of Technology（格拉茨工业大学）；NYU School of Medicine（纽约大学医学院）；AIT Austrian Institute of Technology GmbH（奥地利技术研究所）
Purpose: To allow fast and high-quality reconstruction of clinical accelerated multi-coil MR data by learning a variational network that combines the mathematical structure of variational models with deep learning. Theory and Methods: Generalized compressed sensing reconstruction formulated as a variational model is embedded in an unrolled gradient descent scheme. All parameters of this formulation, including the prior model defined by filter kernels and activation functions as well as the data term weights, are learned during an offline training procedure. The learned model can then be applie…
Technical University of Munich（慕尼黑工业大学）；Imperial College London（帝国理工学院）；University Hospital of Tuebingen（图宾根大学医院）；University of Minnesota（明尼苏达大学）；New York University（纽约大学）；Friedrich-Alexander University Erlangen（埃尔朗根-纽伦堡大学）
Physics-driven deep learning methods have emerged as a powerful tool for computational magnetic resonance imaging (MRI) problems, pushing reconstruction performance to new limits. This article provides an overview of the recent developments in incorporating physics information into learning-based MRI reconstruction. We consider inverse problems with both linear and non-linear forward models for computational MRI, and review the classical approaches for solving these. We then focus on physics-driven deep learning approaches, covering physics-driven loss functions, plug-and-play methods, generat…
Learning Subject-Specific Anatomical Representations via Manifold Expansion: Application to Accelerated Multi-Contrast MRI
Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital（马萨诸塞州总医院阿西诺拉·A·马丁诺斯生物医学成像中心）；Harvard Medical School（哈佛医学院）；Massachusetts General Hospital（马萨诸塞州总医院）
B-FIRE: Binning-Free Diffusion Implicit Neural Representation for Hyper-Accelerated Motion-Resolved MRI
Radiation Oncology, University of California, San Francisco, California（加州大学旧金山分校放射肿瘤学系）；Radiology and Biomedical Imaging, University of California, San Francisco, California（加州大学旧金山分校放射学与生物医学成像系）；Siemens Medical Solutions USA, Inc., Cleveland, Ohio（西门子医疗解决方案美国公司，克利夫兰，俄亥俄）；Radiology at Children’s Hospital Los Angeles, Keck School of Medicine, University of Southern California, Los Angeles, California（洛杉矶儿童医院放射学，美国南加州大学凯克医学院，洛杉矶，加利福尼亚）
Self-supervised learning has shown great promise due to its capability to train deep learning MRI reconstruction methods without fully-sampled data. Current self-supervised learning methods for physics-guided reconstruction networks split acquired undersampled data into two disjoint sets, where one is used for data consistency (DC) in the unrolled network and the other to define the training loss. In this study, we propose an improved self-supervised learning strategy that more efficiently uses the acquired data to train a physics-guided reconstruction network without a database of fully-sampl…
FINDER: Zero-Shot Field-Integrated Network for Distortion-free EPI Reconstruction in Diffusion MRI
Sejong University（世宗大学）；Forschungszentrum Jülich（于利希研究中心）；Athinoula A. Martinos Center for Biomedical Imaging（Athinoula A. Martinos生物医学成像中心）；Harvard Medical School（哈佛医学院）；Hongik University（弘益大学）
Self-Supervised Joint Reconstruction and Denoising of T2-Weighted PROPELLER MRI of the Lungs at 0.55T
New York University Grossman School of Medicine（纽约大学格罗斯曼医学院）；New York University Tandon School of Engineering（纽约大学坦登工程学院）；Indiana University School of Medicine（印第安纳大学医学院）
FlowMoDL: Model-Based Deep Learning with Conjugate-Gradient Data Consistency for Highly Accelerated 4D Flow MRI Reconstruction
Leibniz University Hannover（莱布尼茨汉诺威大学）；Friedrich-Alexander-Universität Erlangen-Nürnberg（弗里德里希-亚历山大-埃尔兰根-纽伦堡大学）；University Medical Center of the Johannes Gutenberg University Mainz（美因茨约翰内斯·古腾堡大学医学中心）；L3S（L3S研究所）；CAIMED（CAIMED机构）；Institute of Information Processing (tnt)（信息处理研究所（tnt））；Institute of Medical Biostatistics, Epidemiology and Informatics（医学生物统计学、流行病学与信息学研究所）
Amsterdam UMC（阿姆斯特丹大学医学中心）；University of Amsterdam（阿姆斯特丹大学）；MS Center Amsterdam（阿姆斯特丹多发性硬化中心）；Amsterdam Neuroscience（阿姆斯特丹神经科学研究所）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；Leiden University（莱顿大学）；Delft University of Technology（代尔夫特理工大学）
Machine Learning methods can learn how to reconstruct Magnetic Resonance Images and thereby accelerate acquisition, which is of paramount importance to the clinical workflow. Physics-informed networks incorporate the forward model of accelerated MRI reconstruction in the learning process. With increasing network complexity, robustness is not ensured when reconstructing data unseen during training. We aim to embed data consistency (DC) in deep networks while balancing the degree of network complexity. While doing so, we will assess whether either explicit or implicit enforcement of DC in varyin…
University of California at Berkeley（加州大学伯克利分校）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；GE Global Research（通用电气全球研究院）；International Computer Science Institute（国际计算机科学研究所）
Purpose: To improve reconstruction fidelity of fine structures and textures in deep learning (DL) based reconstructions. Methods: A novel patch-based Unsupervised Feature Loss (UFLoss) is proposed and incorporated into the training of DL-based reconstruction frameworks in order to preserve perceptual similarity and high-order statistics. The UFLoss provides instance-level discrimination by mapping similar instances to similar low-dimensional feature vectors and is trained without any human annotation. By adding an additional loss function on the low-dimensional feature space during training, t…
Data-Efficient Networks for Multi-Contrast MRI Reconstruction based on a Generalized Content/Style Prior
Leiden University Medical Center（莱顿大学医学中心）；Philips Innovative Technologies（飞利浦创新技术公司）；Philips Cardiologs（飞利浦Cardiologs公司）；Eindhoven University of Technology（埃因霍温理工大学）
A broad class of problems at the core of computational imaging, sensing, and low-level computer vision reduces to the inverse problem of extracting latent images that follow a prior distribution, from measurements taken under a known physical image formation model. Traditionally, hand-crafted priors along with iterative optimization methods have been used to solve such problems. In this paper we present unrolled optimization with deep priors, a principled framework for infusing knowledge of the image formation into deep networks that solve inverse problems in imaging, inspired by classical ite…
Self-supervised Deep Unrolled Reconstruction Using Regularization by Denoising
State University of New York at Buffalo（纽约州立大学布法罗分校）；Cleveland Clinic（克利夫兰诊所）；Paul C. Lauterbur Research Center for Biomedical Imaging, SIAT, CAS（中国科学院深圳先进技术研究院保罗·C·劳特伯生物医学成像研究中心）
Physics-Driven Autoregressive State Space Models for Medical Image Reconstruction
Dept. of Electrical and Electronics Engineering, and National Magnetic Resonance Research Center (UMRAM), Bilkent University（电气与电子工程系，国家磁共振研究中心（UMRAM），比尔肯大学）
PE-CSNet: An equivariant network architecture with learnable patch-based sparse representation
The Hong Kong Polytechnic University（香港理工大学）；Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Physics-guided deep learning (PG-DL) via algorithm unrolling has received significant interest for improved image reconstruction, including MRI applications. These methods unroll an iterative optimization algorithm into a series of regularizer and data consistency units. The unrolled networks are typically trained end-to-end using a supervised approach. Current supervised PG-DL approaches use all of the available sub-sampled measurements in their data consistency units. Thus, the network learns to fit the rest of the measurements. In this study, we propose to improve the performance and robust…
