US 11,748,598 B2
Positron emission tomography (PET) system design optimization using deep imaging
Chuanyong Bai, Solon, OH (US); Yang-Ming Zhu, Wilmington, MA (US); Andriy Andreyev, Willoughby Hills, OH (US); Bin Zhang, Cleveland, OH (US); and Chi-Hua Tung, Aurora, OH (US)
Assigned to KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
Appl. No. 16/758,000
Filed by KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
PCT Filed Oct. 16, 2018, PCT No. PCT/EP2018/078126
§ 371(c)(1), (2) Date Apr. 21, 2020,
PCT Pub. No. WO2019/081256, PCT Pub. Date May 2, 2019.
Claims priority of provisional application 62/575,547, filed on Oct. 23, 2017.
Prior Publication US 2020/0289077 A1, Sep. 17, 2020
Int. Cl. A61B 6/00 (2006.01); A61B 6/03 (2006.01); G06N 3/084 (2023.01); G06N 3/045 (2023.01)
CPC A61B 6/5205 (2013.01) [A61B 6/037 (2013.01); A61B 6/5235 (2013.01); A61B 6/584 (2013.01); G06N 3/045 (2023.01); G06N 3/084 (2013.01)] 15 Claims
OG exemplary drawing
 
1. An imaging method, comprising:
acquiring first training images of one or more imaging subjects using a first image acquisition device;
acquiring second training images of the same one or more imaging subjects as the first training images using a second image acquisition device of the same imaging modality as the first imaging device and having a shorter timing resolution than the first imaging device, the first imaging device and the second imaging device being separate imaging devices; and
training a neural network (NN) to transform the first training images into transformed first training images by:
comparing the first training images to the second training images; and
generating the transformed first training images by minimizing a value of a difference metric between the first training images and the second training images.