US 12,423,817 B2
Brain network and brain addictive connectivity computing method and device
Shuqiang Wang, Shenzhen (CN); and Changhong Jing, Shenzhen (CN)
Assigned to SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY CHINESE ACADEMY OF SCIENCES, Shenzhen (CN)
Filed by SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY CHINESE ACADEMY OF SCIENCES, Shenzhen (CN)
Filed on Dec. 29, 2022, as Appl. No. 18/090,490.
Application 18/090,490 is a continuation of application No. PCT/CN2022/076041, filed on Feb. 11, 2022.
Claims priority of application No. 202111536650.4 (CN), filed on Dec. 16, 2021.
Prior Publication US 2023/0196578 A1, Jun. 22, 2023
Int. Cl. G06T 7/00 (2017.01); A61B 5/00 (2006.01)
CPC G06T 7/0014 (2013.01) [A61B 5/4064 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30016 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A brain network and brain addictive connectivity computing method, comprising:
obtaining a plurality of real brain functional magnetic resonance (fMRI) images associated with different labels; wherein the different labels are used to indicate different concentrations of an addictive substance; the plurality of real brain fMRI images comprise a plurality of real brain regional fMRI images, and the plurality of real brain fMRI images associated with the different labels comprise at least one training real brain fMRI image sample and at least one testing real brain fMRI image sample;
generating first brain topologies associated with the different labels based on the at least one training real brain fMRI image sample and a brain atlas template, each first brain topology being a connectivity feature of a brain neural circuit;
obtaining an addictive real brain fMRI image, which is a published real brain fMRI image that is associated with brain nicotine addiction and that is obtained from a professional doctor or professional institution;
generating a brain addiction standard feature map based on the addictive real brain fMRI image, wherein the brain addiction standard feature map comprises connectivity information of a plurality of brain addictive abnormal regions and a weight distribution value of each brain addictive abnormal region;
determining an initial weight value of each of the first brain topologies according to the brain addiction standard feature map;
training an addictive brain network analysis model based on the first brain topologies associated with the different labels and the initial weight value of each of the first brain topologies; and
inputting the at least one testing real brain fMRI image sample into the addictive brain network analysis model to generate first weighted brain topologies, the first weighted brain topologies being respective weighted brain topologies associated with the different labels.