TY - JOUR
T1 - An adaptive intelligence algorithm for undersampled knee MRI reconstruction
AU - Pezzotti, Nicola
AU - Yousefi, Sahar
AU - Elmahdy, Mohamed S.
AU - van Gemert, Jeroen Hendrikus Fransiscus
AU - Schuelke, Christophe
AU - Doneva, Mariya
AU - Nielsen, Tim
AU - Lelieveldt, Boudewijn P.F.
AU - Staring, Marius
AU - More Authors, null
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
KW - Deep learning
KW - FastMRI challenge
KW - Image reconstruction
KW - ISTA
KW - MRI
UR - http://www.scopus.com/inward/record.url?scp=85099197996&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2020.3034287
DO - 10.1109/ACCESS.2020.3034287
M3 - Article
AN - SCOPUS:85099197996
SN - 2169-3536
VL - 8
SP - 204825
EP - 204838
JO - IEEE Access
JF - IEEE Access
ER -