US 12,073,492 B2
Method and system for generating attenuation map from SPECT emission data
Luyao Shi, New Haven, CT (US); Chi Liu, Orange, CT (US); John Onofrey, Woodbridge, CT (US); and Hui Liu, Beijing (CN)
Assigned to YALE UNIVERSITY, New Haven, CT (US)
Appl. No. 17/594,364
Filed by YALE UNIVERSITY, New Haven, CT (US)
PCT Filed Apr. 17, 2020, PCT No. PCT/US2020/028672
§ 371(c)(1), (2) Date Oct. 13, 2021,
PCT Pub. No. WO2020/214911, PCT Pub. Date Oct. 22, 2020.
Claims priority of provisional application 62/836,167, filed on Apr. 19, 2019.
Prior Publication US 2022/0207791 A1, Jun. 30, 2022
Int. Cl. G06T 11/00 (2006.01); G06N 3/08 (2023.01)
CPC G06T 11/003 (2013.01) [G06N 3/08 (2013.01); G06T 2207/10108 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A system for estimating attenuation coefficients or attenuation maps (ATTMAP) from only single photon emission computed tomography (SPECT) emission data using artificial neural networks, comprising:
a machine learning system based upon deep artificial neural networks for estimating attenuation maps for SPECT emission data consisting essentially of images reconstructed from a photopeak window and/or one or more scatter windows, without requiring additional computed tomography (CT) or other transmission images, the machine learning system both generates attenuation map images from the SPECT emission data, wherein images reconstructed from the photopeak window and/or the scatter window are concatenated/used as a multi-channel/single-channel image, and enforces output attenuation map images to be consistent with a ground truth attenuation map generated based upon empirical evidence.