Deep learning for accelerated and robust MRI reconstruction.

Deep learning (DL) has recently emerged as a pivotal technology for enhancing magnetic resonance imaging (MRI), a critical tool in diagnostic radiology. This review paper provides a comprehensive overview of recent advances in DL for MRI reconstruction, and focuses on various DL approaches and architectures designed to improve image quality, accelerate scans, and address data-related challenges. It explores end-to-end neural networks, pre-trained and generative models, and self-supervised methods, and highlights their contributions to overcoming traditional MRI limitations. It also discusses the role of DL in optimizing acquisition protocols, enhancing robustness against distribution shifts, and tackling biases. Drawing on the extensive literature and practical insights, it outlines current successes, limitations, and future directions for leveraging DL in MRI reconstruction, while emphasizing the potential of DL to significantly impact clinical imaging practices.Affiliations [3 and 6] has been split into two different affiliations. Please check if action taken is appropriate and amend if necessary.looks good.

K-band: Self-supervised MRI Reconstruction via Stochastic Gradient Descent over K-space Subsets.

Although deep learning (DL) methods are powerful for solving inverse problems, their reliance on high-quality training data is a major hurdle. This is significant in high-dimensional (dynamic/volumetric) magnetic resonance imaging (MRI), where acquisition of high-resolution fully sampled k-space data is impractical. We introduce a novel mathematical framework, dubbed k-band, that enables training DL models using only partial, limited-resolution k-space data. Specifically, we introduce training with stochastic gradient descent (SGD) over k-space subsets. In each training iteration, rather than using the fully sampled k-space for computing gradients, we use only a small k-space portion. This concept is compatible with different sampling strategies; here we demonstrate the method for k-space "bands", which have limited resolution in one dimension and can hence be acquired rapidly. We prove analytically that our method stochastically approximates the gradients computed in a fully-supervised setup, when two simple conditions are met: (i) the limited-resolution axis is chosen randomly-uniformly for every new scan, hence k-space is fully covered across the entire training set, and (ii) the loss function is weighed with a mask, derived here analytically, which facilitates accurate reconstruction of high-resolution details. Numerical experiments with raw MRI data indicate that k-band outperforms two other methods trained on limited-resolution data and performs comparably to state-of-the-art (SoTA) methods trained on high-resolution data. k-band hence obtains SoTA performance, with the advantage of training using only limited-resolution data. This work hence introduces a practical, easy-to-implement, self-supervised training framework, which involves fast acquisition and self-supervised reconstruction and offers theoretical guarantees.

AI in MRI: Computational Frameworks for a Faster, Optimized, and Automated Imaging Workflow.

Over the last decade, artificial intelligence (AI) has made an enormous impact on a wide range of fields, including science, engineering, informatics, finance, and transportation [...].

Synthesizing Complex-Valued Multicoil MRI Data from Magnitude-Only Images.

Despite the proliferation of deep learning techniques for accelerated MRI acquisition and enhanced image reconstruction, the construction of large and diverse MRI datasets continues to pose a barrier to effective clinical translation of these technologies. One major challenge is in collecting the MRI raw data (required for image reconstruction) from clinical scanning, as only magnitude images are typically saved and used for clinical assessment and diagnosis. The image phase and multi-channel RF coil information are not retained when magnitude-only images are saved in clinical imaging archives. Additionally, preprocessing used for data in clinical imaging can lead to biased results. While several groups have begun concerted efforts to collect large amounts of MRI raw data, current databases are limited in the diversity of anatomy, pathology, annotations, and acquisition types they contain. To address this, we present a method for synthesizing realistic MR data from magnitude-only data, allowing for the use of diverse data from clinical imaging archives in advanced MRI reconstruction development. Our method uses a conditional GAN-based framework to generate synthetic phase images from input magnitude images. We then applied ESPIRiT to derive RF coil sensitivity maps from fully sampled real data to generate multi-coil data. The synthetic data generation method was evaluated by comparing image reconstruction results from training Variational Networks either with real data or synthetic data. We demonstrate that the Variational Network trained on synthetic MRI data from our method, consisting of GAN-derived synthetic phase and multi-coil information, outperformed Variational Networks trained on data with synthetic phase generated using current state-of-the-art methods. Additionally, we demonstrate that the Variational Networks trained with synthetic k-space data from our method perform comparably to image reconstruction networks trained on undersampled real k-space data.

Implicit data crimes: Machine learning bias arising from misuse of public data.

SignificancePublic databases are an important resource for machine learning research, but their growing availability sometimes leads to "off-label" usage, where data published for one task are used for another. This work reveals that such off-label usage could lead to biased, overly optimistic results of machine-learning algorithms. The underlying cause is that public data are processed with hidden processing pipelines that alter the data features. Here we study three well-known algorithms developed for image reconstruction from magnetic resonance imaging measurements and show they could produce biased results with up to 48% artificial improvement when applied to public databases. We relate to the publication of such results as implicit "data crimes" to raise community awareness of this growing big data problem.

CORE-PI: Non-iterative convolution-based reconstruction for parallel MRI in the wavelet domain.

PURPOSE: To develop and test a novel parameter-free non-iterative wavelet domain method for reconstruction of undersampled multicoil MR data. THEORY AND METHODS: A linear parallel MRI method that operates in the Stationary Wavelet Transform (SWT) domain is proposed. The method is coined COnvolution-based REconstruction for Parallel MRI (CORE-PI). This method computes the SWT of the unknown MR image directly from subsampled k-space measurements, without modifying the RF excitation pulse. It then reconstructs the image using the wavelet filter bank approach, with simple linear computations. The CORE-PI implementation is demonstrated by experiments with a numeric brain phantom and in vivo brain scans data, with various wavelet types and high reduction factors. It is compared to the well-known parallel MRI methods GRAPPA and l1-SPIRiT. RESULTS: The experimental results show that CORE-PI is suitable for different 1D Cartesian k-space undersampling schemes, including regular and irregular ones, and for wavelets of different families. CORE-PI accurately reconstructs the SWT coefficients of the unknown MR image; this wavelet-domain decomposition is fully computed despite the k-space undersampling. Furthermore, CORE-PI provides high-quality final reconstructions, with an average NRMSE of 0.013, which is significantly lower than that obtained by GRAPPA and l1-SPIRiT. Moreover, CORE-PI offers significantly faster computation times: the typical CORE-PI runtime is about 60 seconds, which is about 20% shorter than that of l1-SPIRiT and 55%-75% shorter than that of GRAPPA. CONCLUSION: COnvolution-based REconstruction for Parallel MRI advantageously offers: (a) flexible 1D undersampling of a Cartesian k-space, (b) a parameter-free non-iterative implementation, (c) reconstruction performance comparable or better than that of GRAPPA and l1-SPIRiT, and (d) robust fast computations.