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

Abstract

The invention is applicable to the technical field of medical images, and provides an image-driven brain atlas construction method and device, equipment and a storage medium. The method comprises the steps of obtaining multi-modal data of a to-be-predicted brain, wherein the multi-modal data is obtained according to image data collected by the brain in at least three different modes; inputting the multi-modal data into a preset fusion network for processing, and outputting to obtain characteristic parameters of the brain; the processing of the multi-modal data by the fusion network comprises the steps of extracting non-Euclidean spatial features and Euclidean spatial features of the multi-modal data, and performing hypergraph fusion on the non-Euclidean spatial features and the Euclidean spatial features to obtain feature parameters which are used for representing a brain connection matrix and/or a disease category of the brain. FEatures of different spaces are mapped into a hypergraph data structure for hypergraph fusion, possible isomerism among the features of the different spaces is avoided, and therefore complementary fusion features among the multi-modal data are obtained.

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

Images