US 11,748,921 B2
Learnable extrapolation for deep learning-based medical image reconstruction
Simon Arberet, Princeton, NJ (US); Mariappan S. Nadar, Plainsboro, NJ (US); Boris Mailhe, Plainsboro, NJ (US); and Marcel Dominik Nickel, Herzogenaurach (DE)
Assigned to Siemens Healthcare GmbH, Erlangen (DE)
Filed by Siemens Healthcare GmbH, Erlangen (DE)
Filed on Nov. 13, 2020, as Appl. No. 17/97,060.
Claims priority of provisional application 63/090,311, filed on Oct. 12, 2020.
Prior Publication US 2022/0114771 A1, Apr. 14, 2022
Int. Cl. G06T 11/00 (2006.01); G06N 20/00 (2019.01); G06T 7/00 (2017.01)
CPC G06T 11/003 (2013.01) [G06N 20/00 (2019.01); G06T 7/0012 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method for reconstruction of a medical image in a medical imaging system, the method comprising:
scanning, by the medical imaging system, a patient, the scanning resulting in measurements;
reconstructing, by an image processor, the medical image from the measurements, wherein the reconstructing comprises an unrolled iterative reconstruction including regularization implemented with a machine-learned network and the reconstructing includes an extrapolation step with a machine-learned parameter having different values for different iterations; and
displaying the medical image.