Multi-Modal Brain Network Calculation Method and Device, Equipment and Storage Medium
Abstract
The invention discloses a multi-modal brain network calculation method, device and equipment and a storage medium, and the method is used for training a brain disease prediction model, and comprises the steps: respectively extracting brain region structure features and brain region function features from magnetic resonance diffusion tensor imaging data and brain function magnetic resonance data; a graph representation diffusion learning network is utilized to separate universal features and unique features in brain region structural features and brain region functional features, then effective fusion of multi-modal universal and unique features is realized based on an alignment algorithm and an adaptive weighting technology, complementary information among multi-modal data is fully mined, and the multi-modal data are fully extracted. Therefore, the model can learn effective features related to diseases in the training process, the precision of the brain disease prediction model obtained through final training is higher, and the prediction effect of the model is better.
CN115775626A
