Image-driven brain map construction method, device, equipment and storage medium

Abstract

This application is applicable to the field of medical imaging technology, and provides an image-driven brain atlas construction method, device, equipment and storage medium. The method includes: acquiring multimodal data of the brain to be predicted, the multimodal data is obtained from image data collected in at least three different modalities of the brain; inputting the multimodal data into a preset fusion Process in the network, and output the characteristic parameters of the brain; the processing of multimodal data by the fusion network includes extracting non-Euclidean spatial features and Euclidean spatial features of multimodal data, and supergraphing non-Euclidean spatial features and Euclidean spatial features The feature parameters are obtained through fusion, and the feature parameters are used to represent the brain connection matrix and / or disease category of the brain. Mapping the features of different spaces into a hypergraph data structure for hypergraph fusion avoids the possible heterogeneity between features of different spaces, thereby obtaining complementary fusion features between multimodal data.

Description

technical field [0001] The present application belongs to the technical field of medical imaging, and in particular relates to an image-driven brain atlas construction method, device, equipment and storage medium. Background technique [0002] With the development of medical imaging technology, data of different modalities can describe the information of a certain disease in the brain, which can be used to assist in the diagnosis and treatment of diseases. However, the information that can be provided by single modality data is often limited. Therefore, obtaining fusion features by fusing data of different modalities has become a popular research direction at present. [0003] At present, the commonly used mode fusion method is to directly fuse the data of different modes through weighted summation. However, there may be heterogeneity between the data of different modalities, which makes it impossible to accurately extract the fusion features of different modal data, so it ...

AI Technical Summary

Problems solved by technology

[0004] This application provides an image-driven brain atlas construction method, device, equipment, and storage medium to solve the problem that due to the possible heterogeneity between data of different modalities, it is impossible to accurately extract the fusion features of data of different modalities, thus making it impossible to construct Accurate brain map, causing misjudgment of disease diagnosis

Images