US 12,008,695 B2
Methods and systems for translating magnetic resonance images to pseudo computed tomography images
Sandeep Kaushik, Bangalore (IN); Dattesh Shanbhag, Bangalore (IN); Cristina Cozzini, Bavaria (DE); and Florian Wiesinger, Bavaria (DE)
Assigned to GE PRECISION HEALTHCARE LLC, Milwaukee, WI (US)
Filed by GE Precision Healthcare LLC, Milwaukee, WI (US)
Filed on Sep. 25, 2020, as Appl. No. 17/033,183.
Prior Publication US 2022/0101576 A1, Mar. 31, 2022
Int. Cl. G06T 11/60 (2006.01); A61B 5/00 (2006.01); A61B 5/055 (2006.01); G01R 33/56 (2006.01); G06F 18/214 (2023.01)
CPC G06T 11/60 (2013.01) [A61B 5/0033 (2013.01); A61B 5/055 (2013.01); A61B 5/7267 (2013.01); G01R 33/5608 (2013.01); G06F 18/214 (2023.01); G06T 2210/41 (2013.01); G06V 2201/033 (2022.01)] 15 Claims
OG exemplary drawing
 
1. A method, comprising:
acquiring a magnetic resonance (MR) image;
generating, with a multi-task neural network, a pseudo CT image, a bone mask, and a bone Hounsfield unit (HU) image corresponding to the MR image, wherein the pseudo CT image comprises a set of three density classes, the density classes comprising air, tissue, and bone, and wherein the bone HU image includes image values within a bone region of interest in terms of HU; and
outputting the MR image and the pseudo CT image,
wherein the multi-task neural network is trained with a whole image regression loss for the pseudo CT image, a segmentation loss for the bone mask, and a regression loss focused on bone segments for the bone HU image.