US 12,379,440 B2
Multichannel deep learning reconstruction of multiple repetitions
Simon Arberet, Princeton, NJ (US); Marcel Dominik Nickel, Herzogenaurach (DE); Thomas Benkert, Neunkirchen am Brand (DE); Mahmoud Mostapha, Princeton, NJ (US); and Mariappan S. Nadar, Plainsboro, NJ (US)
Assigned to Siemens Healthineers AG, Forchheim (DE)
Filed by Siemens Healthineers AG, Forchheim (DE)
Filed on Jul. 27, 2022, as Appl. No. 17/815,230.
Prior Publication US 2024/0036138 A1, Feb. 1, 2024
Int. Cl. G01R 33/563 (2006.01); G01R 33/56 (2006.01); G06F 18/214 (2023.01)
CPC G01R 33/5608 (2013.01) [G01R 33/56341 (2013.01); G06F 18/214 (2023.01)] 17 Claims
OG exemplary drawing
 
1. A system for using a multichannel network for image reconstruction, the system comprising:
a medical scanner configured to scan a region of a patient, the scan providing scan data including multiple respective repetitions or directions;
a multichannel network comprising a fixed number of input channels, the multichannel network configured to reconstruct a representation of the scan data;
an adapter configured to duplicate the multichannel network such that each of the multiple respective repetitions or directions is used at least once as an input to the multichannel network or the duplicated multichannel network
compressing or decompressing with parallel imaging, using an encoder decoder network, the multiple respective repetitions such that each input channel of a fixed number of input channels for the multichannel network includes an input from the scan data;
and a display configured to display the representation of the scan data.