一种fMRI脑网络机制启发的动态功能模式学习方法

• Format: Patent
• Language: Chinese
• Published: 01.06.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

本发明公开一种基于fMRI脑网络机制启发的动态功能模式学习方法，包含：采集若干被试的静息态fMRI脑影像数据；将静息态fMRI脑影像数据进行预处理操作；根据预处理后的静息态fMRI脑影像数据，采用GICA-IR方法分别获得组水平和个体水平的静息态脑功能网络及其对应的时间序列；使用滑动时间窗方法计算每个被试对应的静息态脑功能网络之间的动态功能连接矩阵，并将其上三角元素张成动态功能连接向量，进而获得所有被试对应的动态功能连接向量集；利用深度神经网络模型和仿射传播聚类算法提取出隐含于动态功能连接向量集中的大脑固有动态功能连接模式。本发明为揭示脑认知活动的基本原理、脑神经疾病的受损机制以及探索职业脑可塑性重组特征等提供坚实基础。 A dynamic function mode learning method inspired by an fMRI brain network mechanism, comprising: collecting resting-state fMRI brain image data of several subjects; performing a preprocessing operation on the resting-state fMRI brain image data; according to the preprocessed resting-state fMRI brain image data, using a GICA-IR method to separately obtain a group-level resting-state brain function network and an individual-level resting-state brain function network, as well as time sequences corresponding thereto; using a sliding time window method to calculate a dynamic function connection matrix between resting-state brain function networks corresponding to each subject, and stretching triangular el