A multi-modal medical image fusion method based on multi-scale transformer

By employing a multi-scale transformer-based multimodal medical image fusion method, the shortcomings of existing multimodal image fusion techniques in the diagnosis of brain gliomas are addressed. This method achieves multi-scale deep feature extraction and information preservation, thereby improving the accuracy and diagnostic assistance of image fusion.

CN115984257BActive Publication Date: 2026-05-08ARTIFICIAL INTELLIGENCE RES INST OF HEFEI COMPREHENSIVE NAT SCI CENT (ANHUI ARTIFICIAL INTELLIGENCE LAB) +1
2 Cites 0 Cited by

Patent Information

Application Number
CN202310144532.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-02-21
Publication Date
2026-05-08
Estimated Expiration
2043-02-21

AI Technical Summary

Technical Problem

Existing multimodal medical image fusion techniques suffer from low generalization performance, difficulty in handling image fusion of more than two modalities, lack of capture of global information and effective fusion of local information, and limited application of existing methods in medical diagnosis.

Method used

A multi-modal medical image fusion method based on multi-scale transformer is adopted. By constructing a multi-scale transformer module, combining convolution calculation and attention mechanism, the receptive field and patch size are adaptively adjusted, and a loss function is constructed to constrain the image generation quality, so as to achieve multi-scale deep feature extraction and information preservation.

Benefits of technology

It improves the accuracy and generalization ability of multimodal medical image fusion, provides better visual effects and quantitative results, supports the precise fusion of brain glioma lesion areas, and enhances the auxiliary function of medical imaging diagnosis.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a multi-modal medical image fusion method based on a multi-scale transformer and belongs to the technical field of medical image fusion. The application proposes a novel and efficient fusion model, designs a multi-scale transformer model to introduce a feature extraction network, so that the feature extraction network can effectively extract multi-scale deep features and reserve more meaningful information for a fusion task; in the process of network training, the receptive field and the patch size are self-adapted, and a structural similarity-based optimization objective function is constructed to constrain the image generation quality; convolution calculation is combined with the transformer to provide better visual effects and quantitative results for medical image fusion results.
Need to check novelty before this filing date? Find Prior Art