Title:
BRAIN NETWORK AND BRAIN ADDICTION CONNECTION CALCULATION METHOD AND APPARATUS
Document Type and Number:
WIPO Patent Application WO/2023/108873
Kind Code:
A1
Abstract:
Embodiments of the present application provide a brain network and brain addiction connection calculation method and apparatus. The method comprises: obtaining real brain functional magnetic resonance imaging (fMRI) images of different tags; generating first brain topology structures of different tags on the basis of training real brain fMRI image samples; generating a brain addiction standard feature map on the basis of an addictive real brain fMRI image; determining initial weight values of the first brain topology structures according to the brain addiction standard feature map; training an addictive brain network analysis model on the basis of the first brain topology structures of different tags and the initial weight values of the first brain topology structures; and inputting test real brain fMRI image samples into the addictive brain network analysis model to generate first weighted brain topology structures. The method can effectively learn abnormal brain topology features related to addiction, thereby accurately analyzing a brain network of an addictive brain, and improving the overall performance of the model.
Inventors:
WANG SHUQIANG (CN)
JING CHANGHONG (CN)
JING CHANGHONG (CN)
Application Number:
PCT/CN2022/076041
Publication Date:
June 22, 2023
Filing Date:
February 11, 2022
Export Citation:
Assignee:
SHENZHEN INST OF ADV TECH CAS (CN)
International Classes:
G06T7/00
Foreign References:
| CN113920123A | 2022-01-11 | |||
| CN113040715A | 2021-06-29 | |||
| CN106510709A | 2017-03-22 | |||
| CN109376751A | 2019-02-22 | |||
| CN111067522A | 2020-04-28 | |||
| CN108960341A | 2018-12-07 |
Attorney, Agent or Firm:
SCIHEAD IP LAW FIRM (CN)
Download PDF: