Abstract
Adaptive intelligence aims at empowering machine learning techniques with the additional use of domain knowledge. In this work, we present the application of adaptive intelligence to accelerate MR acquisition. Starting from undersampled k-space data, an iterative learning-based reconstruction scheme inspired by compressed sensing theory is used to reconstruct the images. We developed a novel deep neural network to refine and correct prior reconstruction assumptions given the training data. The network was trained and tested on a knee MRI dataset from the 2019 fastMRI challenge organized by Facebook AI Research and NYU Langone Health. All submissions to the challenge were initially ranked based on similarity with a known groundtruth, after which the top 4 submissions were evaluated radiologically. Our method was evaluated by the fastMRI organizers on an independent challenge dataset. It ranked #1, shared #1, and #3 on respectively the 8× accelerated multi-coil, the 4× multi-coil, and the 4× single-coil tracks. This demonstrates the superior performance and wide applicability of the method.
Highlights
M AGNETIC Resonance Imaging (MRI) is a widely applied non-invasive imaging modality, with excellent soft tissue contrast and high spatial resolution
The main contributions of this work are: i) we propose a novel Convolutional Neural Networks (CNN) network that integrates and enhances the conventional Compressed Sensing (CS) approach; ii) it integrates multiscale sparsification, inspired by wavelet transforms, but in a learnable manner; iii) we adopt domain-specific knowledge, such as data consistency, a prior on known phase behavior, and the location of the background: these computations cannot be learned by a CNN; iv) the proposed model exploits the correlation between neighbouring slices by adopting a 2.5D learning approach
METHODS we present the background of our solution, first by introducing the Iterative Shrinkage-Thresholding Algorithm (ISTA) [37] and, second, by introducing its deep learning-based variant, ISTA-Net [33]
Summary
M AGNETIC Resonance Imaging (MRI) is a widely applied non-invasive imaging modality, with excellent soft tissue contrast and high spatial resolution. The total examination time can vary from 15 minutes for knee imaging to an hour or more for cardiac imaging. Remaining still for this long in a confined space is challenging for any patient, being especially difficult for children, elderly and patients under pain. The acquisition time affects the temporal resolution and subsequently limits the potential of MRI for dynamic imaging, where high temporal resolution and robustness against motion are critical for diagnosis. The relatively long scan times lead to high costs that limit the availability of MRI scanners [2]. There is still a need for further scan acceleration
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
