Parallel Magnetic Resonance Imaging Research Articles

FCSSL: fusion enhanced contrastive self-supervised learning method for parallel MRI reconstruction

Objective. The implementation of deep learning in magnetic resonance imaging (MRI) has significantly advanced the reduction of data acquisition times. However, these techniques face substantial limitations in scenarios where acquiring fully sampled datasets is unfeasible or costly.Approach. To tackle this problem, we propose a fusion enhanced contrastive self-supervised learning (FCSSL) method for parallel MRI reconstruction, eliminating the need for fully sampledk-space training dataset and coil sensitivity maps. First, we introduce a strategy based on two pairs of re-undersampling masks within a contrastive learning framework, aimed at enhancing the representational capacity to achieve higher quality reconstruction. Subsequently, a novel adaptive fusion network, trained in a self-supervised learning manner, is designed to integrate the reconstruction results of the framework.Results. Experimental results on knee datasets under different sampling masks demonstrate that the proposed FCSSL achieves superior reconstruction performance compared to other self-supervised learning methods. Moreover,the performance of FCSSL approaches that of the supervised methods, especially under the 2DRU and RADU masks, but no need for fully sample data. The proposed FCSSL, trained under the 3× 1DRU and 2DRU masks, can effectively generalize to unseen 1D and 2D undersampling masks, respectively. For target domain data that exhibit significant differences from source domain data, the proposed model, fine-tuned with just a few dozen instances of undersampled data in the target domain, achieves reconstruction performance comparable to that achieved by the model trained with the entire set of undersampled data.Significance. The novel FCSSL model offers a viable solution for reconstructing high-quality MR images without needing fully sampled datasets, thereby overcoming a major hurdle in scenarios where acquiring fully sampled MR data is difficult.

VSHARP: Variable Splitting Half-quadratic ADMM algorithm for reconstruction of inverse-problems

Medical Imaging (MI) tasks, such as accelerated parallel Magnetic Resonance Imaging (MRI), often involve reconstructing an image from noisy or incomplete measurements. This amounts to solving ill-posed inverse problems, where a satisfactory closed-form analytical solution is not available. Traditional methods such as Compressed Sensing (CS) in MRI reconstruction can be time-consuming or prone to obtaining low-fidelity images. Recently, a plethora of Deep Learning (DL) approaches have demonstrated superior performance in inverse-problem solving, surpassing conventional methods. In this study, we propose vSHARP (variable Splitting Half-quadratic ADMM algorithm for Reconstruction of inverse Problems), a novel DL-based method for solving ill-posed inverse problems arising in MI. vSHARP utilizes the Half-Quadratic Variable Splitting method and employs the Alternating Direction Method of Multipliers (ADMM) to unroll the optimization process. For data consistency, vSHARP unrolls a differentiable gradient descent process in the image domain, while a DL-based denoiser, such as a U-Net architecture, is applied to enhance image quality. vSHARP also employs a dilated-convolution DL-based model to predict the Lagrange multipliers for the ADMM initialization. We evaluate vSHARP on tasks of accelerated parallel MRI Reconstruction using two distinct datasets and on accelerated parallel dynamic MRI Reconstruction using another dataset. Our comparative analysis with state-of-the-art methods demonstrates the superior performance of vSHARP in these applications.

Nonlinear metamaterials enhanced surface coil array for parallel magnetic resonance imaging

Magnetic resonance imaging (MRI) is a crucial medical imaging modality, with parallel MRI accelerating scans but often reducing the signal-to-noise ratio (SNR). Recent advances in metamaterials have shown considerable potential in enhancing the SNR of MRI and consequently improving the quality of parallel MRI. In this study, we present a nonlinear metamaterial comprising nonlinear meta-atoms designed to selectively enhance the radio-frequency reception field in MRI, while minimizing interference with the radio-frequency transmission field. We develop an electromagnetic field-circuit joint simulation process for analyzing and optimizing the nonlinear response. Experimental validation confirms that nonlinear metamaterial integration in a surface coil array delivers a 3-fold SNR increase for parallel MRI compared to using the surface coil array alone. This research advances our understanding of such metamaterials and demonstrates their potential for practical utilization in MRI and clinical settings, thereby promising substantial enhancements in imaging capabilities.

Accelerated parallel magnetic resonance imaging with compressed sensing using structured sparsity.

We present a method that combines compressed sensing with parallel imaging that takes advantage of the structure of the sparsifying transformation. Previous work has combined compressed sensing with parallel imaging using model-based reconstruction but without taking advantage of the structured sparsity. Blurry images for each coil are reconstructed from the fully sampled center region. The optimization problem of compressed sensing is modified to take these blurry images into account, and it is solved to estimate the missing details. Using data of brain, ankle, and shoulder anatomies, the combination of compressed sensing with structured sparsity and parallel imaging reconstructs an image with a lower relative error than does sparse SENSE or L1 ESPIRiT, which do not use structured sparsity. Taking advantage of structured sparsity improves the image quality for a given amount of data as long as a fully sampled region centered on the zero frequency of the appropriate size is acquired.

DFUSNN: zero-shot dual-domain fusion unsupervised neural network for parallel MRI reconstruction

Objective. Recently, deep learning models have been used to reconstruct parallel magnetic resonance (MR) images from undersampled k-space data. However, most existing approaches depend on large databases of fully sampled MR data for training, which can be challenging or sometimes infeasible to acquire in certain scenarios. The goal is to develop an effective alternative for improved reconstruction quality that does not rely on external training datasets. Approach. We introduce a novel zero-shot dual-domain fusion unsupervised neural network (DFUSNN) for parallel MR imaging reconstruction without any external training datasets. We employ the Noise2Noise (N2N) network for the reconstruction in the k-space domain, integrate phase and coil sensitivity smoothness priors into the k-space N2N network, and use an early stopping criterion to prevent overfitting. Additionally, we propose a dual-domain fusion method based on Bayesian optimization to enhance reconstruction quality efficiently. Results. Simulation experiments conducted on three datasets with different undersampling patterns showed that the DFUSNN outperforms all other competing unsupervised methods and the one-shot Hankel-k-space generative model (HKGM). The DFUSNN also achieves comparable results to the supervised Deep-SLR method. Significance. The novel DFUSNN model offers a viable solution for reconstructing high-quality MR images without the need for external training datasets, thereby overcoming a major hurdle in scenarios where acquiring fully sampled MR data is difficult.

A noise robust image reconstruction using slice aware cycle interpolator network for parallel imaging in MRI.

Reducing Magnetic resonance imaging (MRI) scan time has been an important issue for clinical applications. In order to reduce MRI scan time, imaging acceleration was made possible by undersampling k-space data. This is achieved by leveraging additional spatial information from multiple, independent receiver coils, thereby reducing the number of sampled k-spacelines. The aim of this study is to develop a deep-learning method for parallel imaging with a reduced number of auto-calibration signals (ACS) lines in noisyenvironments. A cycle interpolator network is developed for robust reconstruction of parallel MRI with a small number of ACS lines in noisy environments. The network estimates missing (unsampled) lines of each coil data, and these estimated missing lines are then utilized to re-estimate the sampled k-space lines. In addition, a slice aware reconstruction technique is developed for noise-robust reconstruction while reducing the number of ACS lines. We conducted an evaluation study using retrospectively subsampled data obtained from three healthy volunteers at 3T MRI, involving three different slice thicknesses (1.5, 3.0, and 4.5 mm) and three different image contrasts (T1w, T2w, and FLAIR). Despite the challenges posed by substantial noise in cases with a limited number of ACS lines and thinner slices, the slice aware cycle interpolator network reconstructs the enhanced parallel images. It outperforms RAKI, effectively eliminating aliasing artifacts. Moreover, the proposed network outperforms GRAPPA and demonstrates the ability to successfully reconstruct brain images even under severe noisyconditions. The slice aware cycle interpolator network has the potential to improve reconstruction accuracy for a reduced number of ACS lines in noisyenvironments.

IMJENSE: Scan-Specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRI.

Parallel imaging is a commonly used technique to accelerate magnetic resonance imaging (MRI) data acquisition. Mathematically, parallel MRI reconstruction can be formulated as an inverse problem relating the sparsely sampled k-space measurements to the desired MRI image. Despite the success of many existing reconstruction algorithms, it remains a challenge to reliably reconstruct a high-quality image from highly reduced k-space measurements. Recently, implicit neural representation has emerged as a powerful paradigm to exploit the internal information and the physics of partially acquired data to generate the desired object. In this study, we introduced IMJENSE, a scan-specific implicit neural representation-based method for improving parallel MRI reconstruction. Specifically, the underlying MRI image and coil sensitivities were modeled as continuous functions of spatial coordinates, parameterized by neural networks and polynomials, respectively. The weights in the networks and coefficients in the polynomials were simultaneously learned directly from sparsely acquired k-space measurements, without fully sampled ground truth data for training. Benefiting from the powerful continuous representation and joint estimation of the MRI image and coil sensitivities, IMJENSE outperforms conventional image or k-space domain reconstruction algorithms. With extremely limited calibration data, IMJENSE is more stable than supervised calibrationless and calibration-based deep-learning methods. Results show that IMJENSE robustly reconstructs the images acquired at 5× and 6× accelerations with only 4 or 8 calibration lines in 2D Cartesian acquisitions, corresponding to 22.0% and 19.5% undersampling rates. The high-quality results and scanning specificity make the proposed method hold the potential for further accelerating the data acquisition of parallel MRI.

Improved Complex Convolutional Neural Network Based on SPIRiT and Dense Connection for Parallel MRI Reconstruction

To accelerate the data acquisition speed of magnetic resonance imaging (MRI) and improve the reconstructed MR images’ quality, we propose a parallel MRI reconstruction model (SPIRiT-Net), which combines the iterative self-consistent parallel imaging reconstruction model (SPIRiT) with the cascaded complex convolutional neural networks (CCNNs). More specifically, this model adopts the SPIRiT model for reconstruction in the k-space domain and the cascaded CCNNs with dense connection for reconstruction in the image domain. Meanwhile, this model introduces the data consistency layers for better reconstruction in both the image domain and the k-space domain. The experimental results on two clinical knee datasets as well as the fastMRI brain dataset under different undersampling patterns show that the SPIRiT-Net model achieves better reconstruction performance in terms of visual effect, peak signal-to-noise ratio, and structural similarity over SPIRiT, Deepcomplex, and DONet. It will be beneficial to the diagnosis of clinical medicine.

DONet: Dual-Octave Network for Fast MR Image Reconstruction.

Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration has long been the subject of research. This is commonly achieved by obtaining multiple undersampled images, simultaneously, through parallel imaging. In this article, we propose the dual-octave network (DONet), which is capable of learning multiscale spatial-frequency features from both the real and imaginary components of MR data, for parallel fast MR image reconstruction. More specifically, our DONet consists of a series of dual-octave convolutions (Dual-OctConvs), which are connected in a dense manner for better reuse of features. In each Dual-OctConv, the input feature maps and convolutional kernels are first split into two components (i.e., real and imaginary) and then divided into four groups according to their spatial frequencies. Then, our Dual-OctConv conducts intragroup information updating and intergroup information exchange to aggregate the contextual information across different groups. Our framework provides three appealing benefits: 1) it encourages information interaction and fusion between the real and imaginary components at various spatial frequencies to achieve richer representational capacity; 2) the dense connections between the real and imaginary groups in each Dual-OctConv make the propagation of features more efficient by feature reuse; and 3) DONet enlarges the receptive field by learning multiple spatial-frequency features of both the real and imaginary components. Extensive experiments on two popular datasets (i.e., clinical knee and fastMRI), under different undersampling patterns and acceleration factors, demonstrate the superiority of our model in accelerated parallel MR image reconstruction.

Nonmonotone variable metric Barzilai-Borwein method for composite minimization problem

<abstract><p>In this study, we develop a nonmonotone variable metric Barzilai-Borwein method for minimizing the sum of a smooth function and a convex, possibly nondifferentiable, function. At each step, the descent direction is obtained by taking the difference between the minimizer of the scaling proximal function and the current iteration point. An adaptive nonmonotone line search is proposed for determining the step length along this direction. We also show that the limit point of the iterates sequence is a stationary point. Numerical results with parallel magnetic resonance imaging, Poisson, and Cauchy noise deblurring demonstrate the effectiveness of the new algorithm.</p></abstract>

Fast and Reliable Score-Based Generative Model for Parallel MRI.

The score-based generative model (SGM) can generate high-quality samples, which have been successfully adopted for magnetic resonance imaging (MRI) reconstruction. However, the recent SGMs may take thousands of steps to generate a high-quality image. Besides, SGMs neglect to exploit the redundancy in k space. To overcome the above two drawbacks, in this article, we propose a fast and reliable SGM (FRSGM). First, we propose deep ensemble denoisers (DEDs) consisting of SGM and the deep denoiser, which are used to solve the proximal problem of the implicit regularization term. Second, we propose a spatially adaptive self-consistency (SASC) term as the regularization term of the k -space data. We use the alternating direction method of multipliers (ADMM) algorithm to solve the minimization model of compressed sensing (CS)-MRI incorporating the image prior term and the SASC term, which is significantly faster than the related works based on SGM. Meanwhile, we can prove that the iterating sequence of the proposed algorithm has a unique fixed point. In addition, the DED and the SASC term can significantly improve the generalization ability of the algorithm. The features mentioned above make our algorithm reliable, including the fixed-point convergence guarantee, the exploitation of the k space, and the powerful generalization ability.

Improved Sensitivity Encoding Parallel Magnetic Resonance Imaging Reconstruction Algorithm Based on Efficient Sum of Outer Products Dictionary Learning

Improved Sensitivity Encoding Parallel Magnetic Resonance Imaging Reconstruction Algorithm Based on Efficient Sum of Outer Products Dictionary Learning

Exploring the Potential of Radiomics Features of the Hippocampus in Alzheimer’s Disease Considering Standard versus Parallel Imaging

AbstractBackgroundRadiomics features obtained from anatomical magnetic resonance imaging (MRI) have been showing potential as biomarkers for the diagnosis of Alzheimer’s disease (AD). Nevertheless, little is known about how accelerated parallel MRI acquisitions impact such features and their potential in diagnosing AD. Therefore, this study aimed to compare the radiomics features extracted from the hippocampus considering standard and parallel imaging.MethodA total of 235 age and gender‐matched subjects (128 cognitively normal (CN) and 107 AD) with both T1‐weighted MPRAGE (standard) and accelerated MPRAGE GRAPPA or SENSE images were selected from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Freesurfer was used to process the images and to obtain the volumes of these regions: hippocampus, entorhinal cortex, amygdala, and inferior lateral ventricle (summed bilaterally); and caudal and rostral midfrontal, pars opercularis, pars triangularis, inferior parietal, superior parietal, supramarginal, and superior temporal gyri (all summed into one feature). Using Pyradiomics, the following radiomics features from the bilateral hippocampus were extracted: kurtosis, mean, range, contrast, elongation, flatness, and maximum 3D diameter. To compare the two acquisitions (standard vs parallel), support vector machine models were created to classify AD vs CN. To mitigate AD heterogeneity in ADNI, 5‐fold cross‐validation was used to create 5 train and test sets based on the hippocampus volumes: (each train fold has 80% of 1st quartile AD and 80% 1st quartile CN, and the test fold has 20% of 1st quartile AD and 20% 1st quartile CN volumes, and so on – randomly selected).ResultAdding radiomics features improved the classification of AD vs CN in both acquisitions (Table 1): the positive predictive value increased from 77.2% to 90.3% in the standard, while the negative predictive value increased to 84.7% to 91.6% in the parallel acquisition. In both cases, models using all volumes surpassed those using only the hippocampus volume by 7.4% (86.0% balanced accuracy, standard) and 4.2% (85.5%, balanced accuracy, parallel) (Table 1).ConclusionRadiomics features of the hippocampus improve the performance of the models in both acquisitions, but with different predictive values, confirming their potential. Also, the relevance of other brain regions in AD besides the hippocampus was observed.

Stable Deep MRI Reconstruction Using Generative Priors.

Data-driven approaches recently achieved remarkable success in magnetic resonance imaging (MRI) reconstruction, but integration into clinical routine remains challenging due to a lack of generalizability and interpretability. In this paper, we address these challenges in a unified framework based on generative image priors. We propose a novel deep neural network based regularizer which is trained in a generative setting on reference magnitude images only. After training, the regularizer encodes higher-level domain statistics which we demonstrate by synthesizing images without data. Embedding the trained model in a classical variational approach yields high-quality reconstructions irrespective of the sub-sampling pattern. In addition, the model shows stable behavior when confronted with out-of-distribution data in the form of contrast variation. Furthermore, a probabilistic interpretation provides a distribution of reconstructions and hence allows uncertainty quantification. To reconstruct parallel MRI, we propose a fast algorithm to jointly estimate the image and the sensitivity maps. The results demonstrate competitive performance, on par with state-of-the-art end-to-end deep learning methods, while preserving the flexibility with respect to sub-sampling patterns and allowing for uncertainty quantification.

The application of quantitative perfusion analysis of golden-angle radial sparse parallel MRI and R2∗ value for predicting pathological prognostic factors in rectal cancer

To investigate the diagnostic value of golden-angle radial sparse parallel magnetic resonance imaging (MRI) (GRASP) and R2∗ in predicting the prognostic factors of resectable rectal cancer. A total of 108 patients with rectal adenocarcinoma were included in this retrospective study. The volume transfer constant (Ktrans), rate constant (Kep), plasma volume fraction (Ve), and R2∗ were obtained. Univariate and multivariate logistic regression were conducted. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic performance of the imaging parameters. The Ktrans was found to be significantly higher in rectal cancers with positive lymph node metastasis (LNM), higher tumour grade, positive lymphovascular invasion (LVI), and higher ki-67 (all p<0.05). The Kep was also significantly higher in the LNM-positive group (p<0.001), while the R2∗ was higher in rectal cancers with LNM-positive, higher tumour grade, LVI-positive, and higher ki-67 (all p<0.05). Combining the Ktrans and R2∗ provided the highest area under the ROC curve (AUC) for LNM-positive and higher ki-67 tumours differentiation (0.790 and 0.823, respectively). Combining quantitative parameters of the Ktrans and R2∗ could be used to non-invasively predict pathological prognostic factors preoperatively.

Fast Parallel Magnetic Resonance Imaging Reconstruction Based on Sparsifying Transform Learning and Structured Low-Rank Model

Fast Parallel Magnetic Resonance Imaging Reconstruction Based on Sparsifying Transform Learning and Structured Low-Rank Model

PARCEL: Physics-Based Unsupervised Contrastive Representation Learning for Multi-Coil MR Imaging.

With the successful application of deep learning to magnetic resonance (MR) imaging, parallel imaging techniques based on neural networks have attracted wide attention. However, in the absence of high-quality, fully sampled datasets for training, the performance of these methods is limited. And the interpretability of models is not strong enough. To tackle this issue, this paper proposes a Physics-bAsed unsupeRvised Contrastive rEpresentation Learning (PARCEL) method to speed up parallel MR imaging. Specifically, PARCEL has a parallel framework to contrastively learn two branches of model-based unrolling networks from augmented undersampled multi-coil k-space data. A sophisticated co-training loss with three essential components has been designed to guide the two networks in capturing the inherent features and representations for MR images. And the final MR image is reconstructed with the trained contrastive networks. PARCEL was evaluated on two vivo datasets and compared to five state-of-the-art methods. The results show that PARCEL is able to learn essential representations for accurate MR reconstruction without relying on fully sampled datasets. The code will be made available at https://github.com/ternencewu123/PARCEL.

Emerging Trends in Fast MRI Using Deep-Learning Reconstruction on Undersampled k-Space Data: A Systematic Review.

Magnetic Resonance Imaging (MRI) is an essential medical imaging modality that provides excellent soft-tissue contrast and high-resolution images of the human body, allowing us to understand detailed information on morphology, structural integrity, and physiologic processes. However, MRI exams usually require lengthy acquisition times. Methods such as parallel MRI and Compressive Sensing (CS) have significantly reduced the MRI acquisition time by acquiring less data through undersampling k-space. The state-of-the-art of fast MRI has recently been redefined by integrating Deep Learning (DL) models with these undersampled approaches. This Systematic Literature Review (SLR) comprehensively analyzes deep MRI reconstruction models, emphasizing the key elements of recently proposed methods and highlighting their strengths and weaknesses. This SLR involves searching and selecting relevant studies from various databases, including Web of Science and Scopus, followed by a rigorous screening and data extraction process using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. It focuses on various techniques, such as residual learning, image representation using encoders and decoders, data-consistency layers, unrolled networks, learned activations, attention modules, plug-and-play priors, diffusion models, and Bayesian methods. This SLR also discusses the use of loss functions and training with adversarial networks to enhance deep MRI reconstruction methods. Moreover, we explore various MRI reconstruction applications, including non-Cartesian reconstruction, super-resolution, dynamic MRI, joint learning of reconstruction with coil sensitivity and sampling, quantitative mapping, and MR fingerprinting. This paper also addresses research questions, provides insights for future directions, and emphasizes robust generalization and artifact handling. Therefore, this SLR serves as a valuable resource for advancing fast MRI, guiding research and development efforts of MRI reconstruction for better image quality and faster data acquisition.

Golden-angle radial sparse parallel magnetic resonance imaging of rectal perfusion: utility in the diagnosis of poorly differentiated rectal cancer.

The objective of this retrospective investigation is to evaluate the diagnostic efficacy of a dual-parameter strategy that integrates either time-resolved angiography with stochastic trajectories (TWIST) or golden-angle radial sparse parallel (GRASP)-derived dynamic contrast agent-enhanced magnetic resonance imaging (DCE-MRI) with diffusion-weighted imaging (DWI) for the identification of poorly differentiated rectal cancer (RC). The purpose of this investigation is to contrast the aforementioned methodology with conventional single-factor assessments that rely solely on DWI, and ascertain its comparative efficacy. This study was not registered on a clinical trial platform. Consecutive individuals diagnosed with non-mucinous rectal adenocarcinoma through endoscopy-guided biopsy between December 2020 and October 2022 were involved in our study. These patients had also undergone DCE-MRI and DWI. The perfusion metrics of influx forward volume transfer constant (Ktrans) and rate constant (Kep), along with the apparent diffusion coefficient (ADC), were quantified by a pair of investigators. The study compared the area under the curve (AUC) of the receiver operating characteristic (ROC) for both sequences to identify poorly differentiated RC. The investigation incorporated patients who fulfilled the specified criteria. The inclusion criteria for the investigation were as follows: (I) a diagnosis of RC proved through pathological examination, either via endoscopically-guided biopsy or surgical resection; (II) availability of complete MRI images; (III) absence of any prior history of neoadjuvant chemoradiotherapy during the MRI scan. Our investigation comprised a total of 179 participants. Compared to diffusion parameter alone, an integrated assessment of diffusion parameter (ADC) and perfusion parameters (Ktrans or Kep) obtained with GRASP leads to a superior diagnostic accuracy (AUC, 0.97±0.02 vs. 0.89±0.03, 0.97±0.02 vs. 0.89±0.03, P=0.005 and 0.003, respectively); however, there was no additional benefit from ADC with perfusion parameters obtained from TWIST (Ktrans or Kep) (AUC, 0.93±0.04 vs. 0.89±0.03, 0.93±0.03 vs. 0.89±0.03; P= 0.955 and 0.981, respectively, for the integration of ADC with Ktrans and Kep). By integrating diffusion and perfusion features into a dual-parameter model, the GRASP method enhances the diagnostic efficacy of MRI in discriminating RCs with poor differentiation. Conversely, the TWIST approach did not yield the aforementioned outcome.

Fast and Calibrationless Low-Rank Parallel Imaging Reconstruction through Unrolled Deep Learning Estimation of Multi-Channel Spatial Support Maps.

Low-rank technique has emerged as a powerful calibrationless alternative for parallel magnetic resonance (MR) imaging. Calibrationless low-rank reconstruction, such as low-rank modeling of local k-space neighborhoods (LORAKS), implicitly exploits both coil sensitivity modulations and the finite spatial support constraint of MR images through an iterative low-rank matrix recovery process. Although powerful, this slow iteration process is computationally demanding and reconstruction requires empirical rank optimization, hampering its robust applications for high-resolution volume imaging. This paper proposes a fast and calibrationless low-rank reconstruction of undersampled multi-slice MR brain data, based on the finite spatial support constraint reformulation with a direct deep learning estimation of spatial support maps. The iteration process of low-rank reconstruction is unrolled into a complex-valued network by training on fully-sampled multi-slice axial brain datasets acquired from the same MR coil system. To utilize coil-subject geometric parameters available for datasets, the model minimizes a hybrid loss on two sets of spatial support maps, corresponding to brain data at the original slice locations as actually acquired and nearby locations within the standard reference coordinate. This deep learning framework was integrated with LORAKS reconstruction and was evaluated with publically available gradient-echo T1-weighted brain datasets. It directly produced high-quality multi-channel spatial support maps from undersampled data, enabling rapid reconstruction without iteration. Moreover, it led to effective reductions of artifacts and noise amplification at high acceleration. In summary, our proposed deep learning framework offers a new strategy to advance the existing calibrationless low-rank reconstruction, rendering it computationally efficient, simple, and robust in practice.