An official website of the United States government
Self‐supervised learning has shown great promise because of its ability to train deep learning (DL) magnetic resonance imaging (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, while the other is used 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 sampled data. The proposed multi‐mask self‐supervised learning via data undersampling (SSDU) applies a holdout masking operation on the acquired measurements to split them into multiple pairs of disjoint sets for each training sample, while using one of these pairs for DC units and the other for defining loss, thereby more efficiently using the undersampled data. Multi‐mask SSDU is applied on fully sampled 3D knee and prospectively undersampled 3D brain MRI datasets, for various acceleration rates and patterns, and compared with the parallel imaging method, CG‐SENSE, and single‐mask SSDU DL‐MRI, as well as supervised DL‐MRI when fully sampled data are available. The results on knee MRI show that the proposed multi‐mask SSDU outperforms SSDU and performs as well as supervised DL‐MRI. A clinical reader study further ranks the multi‐mask SSDU higher than supervised DL‐MRI in terms of signal‐to‐noise ratio and aliasing artifacts. Results on brain MRI show that multi‐mask SSDU achieves better reconstruction quality compared with SSDU. The reader study demonstrates that multi‐mask SSDU at R = 8 significantly improves reconstruction compared with single‐mask SSDU at R = 8, as well as CG‐SENSE at R = 2.
more »
« less
Self‐supervised learning of physics‐guided reconstruction neural networks without fully sampled reference data
PurposeTo develop a strategy for training a physics‐guided MRI reconstruction neural network without a database of fully sampled data sets. MethodsSelf‐supervised learning via data undersampling (SSDU) for physics‐guided deep learning reconstruction partitions available measurements into two disjoint sets, one of which is used in the data consistency (DC) units in the unrolled network and the other is used to define the loss for training. The proposed training without fully sampled data is compared with fully supervised training with ground‐truth data, as well as conventional compressed‐sensing and parallel imaging methods using the publicly available fastMRI knee database. The same physics‐guided neural network is used for both proposed SSDU and supervised training. The SSDU training is also applied to prospectively two‐fold accelerated high‐resolution brain data sets at different acceleration rates, and compared with parallel imaging. ResultsResults on five different knee sequences at an acceleration rate of 4 shows that the proposed self‐supervised approach performs closely with supervised learning, while significantly outperforming conventional compressed‐sensing and parallel imaging, as characterized by quantitative metrics and a clinical reader study. The results on prospectively subsampled brain data sets, in which supervised learning cannot be used due to lack of ground‐truth reference, show that the proposed self‐supervised approach successfully performs reconstruction at high acceleration rates (4, 6, and 8). Image readings indicate improved visual reconstruction quality with the proposed approach compared with parallel imaging at acquisition acceleration. ConclusionThe proposed SSDU approach allows training of physics‐guided deep learning MRI reconstruction without fully sampled data, while achieving comparable results with supervised deep learning MRI trained on fully sampled data.
more »
« less
- Award ID(s):
- 1651825
- PAR ID:
- 10454136
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- Magnetic Resonance in Medicine
- Volume:
- 84
- Issue:
- 6
- ISSN:
- 0740-3194
- Page Range / eLocation ID:
- p. 3172-3191
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Motivation: We explore the “Implicit Data Crime” of datasets whose subsampled k-space is filled using parallel imaging. These datasets are treated as fully-sampled, but their points derive from (1)prospective sampling, and (2)reconstruction of un-sampled points, creating artificial data correlations given low SNR or high acceleration. Goal(s): How will downstream tasks, including reconstruction algorithm comparison and optimal trajectory design, be biased by effects of parallel imaging on a prospectively undersampled dataset? Approach: Comparing reconstruction performance using data that are fully sampled with data that are completed using the SENSE algorithm. Results: Utilizing parallel imaging filled k-space results in biased downstream perception of algorithm performance. Impact: This study demonstrates evidence of overly-optimistic bias resulting from the use of k-space filled in with parallel imaging as ground truth data. Researchers should be aware of this possibility and carefully examine the computational pipeline behind datasets they use.more » « less
-
Parallel magnetic resonance imaging (MRI) is a widely-used technique that accelerates data collection by making use of the spatial encoding provided by multiple receiver coils. A key issue in parallel MRI is the estimation of coil sensitivity maps (CSMs) that are used for reconstructing a single high-quality image. This paper addresses this issue by developing SS-JIRCS, a new self-supervised model-based deep-learning (DL) method for image reconstruction that is equipped with automated CSM calibration. Our deep network consists of three types of modules: data-consistency, regularization, and CSM calibration. Unlike traditional supervised DL methods, these modules are directly trained on undersampled and noisy k-space data rather than on fully sampled high-quality ground truth. We present empirical results on simulated data that show the potential of the proposed method for achieving better performance than several baseline methods.more » « less
-
The application of compressed sensing (CS)-enabled data reconstruction for accelerating magnetic resonance imaging (MRI) remains a challenging problem. This is due to the fact that the information lost in k-space from the acceleration mask makes it difficult to reconstruct an image similar to the quality of a fully sampled image. Multiple deep learning-based structures have been proposed for MRI reconstruction using CS, in both the k-space and image domains, and using unrolled optimization methods. However, the drawback of these structures is that they are not fully utilizing the information from both domains (k-space and image). Herein, we propose a deep learning-based attention hybrid variational network that performs learning in both the k-space and image domains. We evaluate our method on a well-known open-source MRI dataset (652 brain cases and 1172 knee cases) and a clinical MRI dataset of 243 patients diagnosed with strokes from our institution to demonstrate the performance of our network. Our model achieves an overall peak signal-to-noise ratio/structural similarity of 40.92 ± 0.29/0.9577 ± 0.0025 (fourfold) and 37.03 ± 0.25/0.9365 ± 0.0029 (eightfold) for the brain dataset, 31.09 ± 0.25/0.6901 ± 0.0094 (fourfold) and 29.49 ± 0.22/0.6197 ± 0.0106 (eightfold) for the knee dataset, and 36.32 ± 0.16/0.9199 ± 0.0029 (20-fold) and 33.70 ± 0.15/0.8882 ± 0.0035 (30-fold) for the stroke dataset. In addition to quantitative evaluation, we undertook a blinded comparison of image quality across networks performed by a subspecialty trained radiologist. Overall, we demonstrate that our network achieves a superior performance among others under multiple reconstruction tasks.more » « less
-
PurposeTo develop an improved k‐space reconstruction method using scan‐specific deep learning that is trained on autocalibration signal (ACS) data. TheoryRobust artificial‐neural‐networks for k‐space interpolation (RAKI) reconstruction trains convolutional neural networks on ACS data. This enables nonlinear estimation of missing k‐space lines from acquired k‐space data with improved noise resilience, as opposed to conventional linear k‐space interpolation‐based methods, such as GRAPPA, which are based on linear convolutional kernels. MethodsThe training algorithm is implemented using a mean square error loss function over the target points in the ACS region, using a gradient descent algorithm. The neural network contains 3 layers of convolutional operators, with 2 of these including nonlinear activation functions. The noise performance and reconstruction quality of the RAKI method was compared with GRAPPA in phantom, as well as in neurological and cardiac in vivo data sets. ResultsPhantom imaging shows that the proposed RAKI method outperforms GRAPPA at high (≥4) acceleration rates, both visually and quantitatively. Quantitative cardiac imaging shows improved noise resilience at high acceleration rates (rate 4:23% and rate 5:48%) over GRAPPA. The same trend of improved noise resilience is also observed in high‐resolution brain imaging at high acceleration rates. ConclusionThe RAKI method offers a training database‐free deep learning approach for MRI reconstruction, with the potential to improve many existing reconstruction approaches, and is compatible with conventional data acquisition protocols.more » « less
