TY - GEN
T1 - Deep image reconstruction using unregistered measurements without groundtruth
AU - Gan, Weijie
AU - Sun, Yu
AU - Eldeniz, Cihat
AU - Liu, Jiaming
AU - An, Hongyu
AU - Kamilov, Ulugbek S.
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/4/13
Y1 - 2021/4/13
N2 - One of the key limitations in conventional deep learning based image reconstruction is the need for registered pairs of training images containing a set of high-quality groundtruth images. This paper addresses this limitation by proposing a novel unsupervised deep registration-augmented reconstruction method (U-Dream) for training deep neural nets to reconstruct high-quality images by directly mapping pairs of unregistered and artifact-corrupted images. The ability of U-Dream to circumvent the need for accurately registered data makes it widely applicable to many biomedical image reconstruction tasks. We validate it in accelerated magnetic resonance imaging (MRI) by training an image reconstruction model directly on pairs of undersampled measurements from images that have undergone nonrigid deformations.
AB - One of the key limitations in conventional deep learning based image reconstruction is the need for registered pairs of training images containing a set of high-quality groundtruth images. This paper addresses this limitation by proposing a novel unsupervised deep registration-augmented reconstruction method (U-Dream) for training deep neural nets to reconstruct high-quality images by directly mapping pairs of unregistered and artifact-corrupted images. The ability of U-Dream to circumvent the need for accurately registered data makes it widely applicable to many biomedical image reconstruction tasks. We validate it in accelerated magnetic resonance imaging (MRI) by training an image reconstruction model directly on pairs of undersampled measurements from images that have undergone nonrigid deformations.
KW - Deep learning
KW - Deformable image registration
KW - Image reconstruction
KW - Magnetic resonance imaging
UR - http://www.scopus.com/inward/record.url?scp=85107236540&partnerID=8YFLogxK
U2 - 10.1109/ISBI48211.2021.9434079
DO - 10.1109/ISBI48211.2021.9434079
M3 - Conference contribution
AN - SCOPUS:85107236540
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 1531
EP - 1534
BT - 2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021
PB - IEEE Computer Society
T2 - 18th IEEE International Symposium on Biomedical Imaging, ISBI 2021
Y2 - 13 April 2021 through 16 April 2021
ER -