Modal distance constraint-based multimodal fusion image classification method

Abstract

The invention discloses a modal distance constraint-based multimodal fusion image classification method. The method includes the following steps that: first step, the rs-fMRI (resting-state functionalmagnetic resonance imaging) data and DTI (diffusion tensor imaging) data of a plurality of subjects are obtained; second step, a brain function network feature vector and a brain structure network feature vector are constructed for each subject; third step, feature filtering operation is performed on the feature vectors of two modalities based on the Kendall tau correlation coefficient and an overlap mode; fourth step, the relative distance constraint of the feature vectors of two modalities of the same subject before and after mapping is added on the original basis of the K-support norm, andthe objective function of a multimodal feature selection model is constructed, and the optimal feature vectors of two modalities are screened out; and fifth step, a classifier is trained on the basisof a multi-kernel support vector machine model, and the optimal feature vectors of two modalities of the subjects are inputted into the trained classifier, and the category labels of the subjects arepredicted. The classification accuracy of the method of the invention is high.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a multimodal fusion image classification method based on modal distance constraints. Background technique [0002] In the past ten years, with the advancement of brain imaging technology, brain science research has entered a period of rapid development. Magnetic resonance imaging, as a non-invasive in vivo brain function detection technology, has rapidly become the most widely used brain imaging technology in brain science research since its birth in the 1990s by virtue of its advantages of high resolution and no radiation. Among them, magnetic resonance imaging techniques include structural magnetic resonance imaging (sMRI, structural Magnetic Resonance Imaging), functional magnetic resonance imaging (fMRI, functional Magnetic Resonance Imaging), and diffusion tensor imaging (DTI, Diffusion Tensor Imaging). Each neuroimaging technique provides a characterizatio...

AI Technical Summary

Problems solved by technology

The current method of image classification based on multi-modal fusion is to connect the features extracted from different modalities into a long feature vector for subsequent analysis, without considering the relationship between different modal data, and the classification accuracy needs to be improved

Images