A medical image fusion method and system based on cross-modal Mamba and space-frequency cooperation

By combining cross-modal Mamba and space-frequency collaboration, this method addresses the issues of insufficient integration of local and global features and inadequate utilization of frequency domain information in existing medical image fusion, achieving high-quality medical image fusion and improving the visual effects and performance of the fused images.

CN122175797APending Publication Date: 2026-06-09JIANGSU OCEAN UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
JIANGSU OCEAN UNIV
Filing Date
2026-02-03
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing medical image fusion methods, when utilizing deep learning networks, struggle to effectively combine local and global features and neglect the importance of frequency domain information in image fusion, resulting in insufficient preservation of texture details and color information in the fused image.

Method used

A medical image fusion method based on cross-modal Mamba and spatial-frequency fusion is designed. By using parallel spatial feature fusion modules, frequency feature fusion modules, and spatial-frequency feature fusion modules, the method leverages the advantages of Mamba and CNN to extract and integrate feature information, and combines Fast Fourier Transform to capture frequency domain information, thereby achieving adaptive fusion of cross-modal features.

Benefits of technology

It significantly improves the visual quality and quantitative evaluation metrics of fused images, especially in preserving the clear texture information of MRI images and the color information of PET images, outperforming existing methods and enhancing the performance of image fusion.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122175797A_ABST
    Figure CN122175797A_ABST
Patent Text Reader

Abstract

The application discloses a medical image fusion method and system based on cross-modal Mamba and space-frequency cooperation, which comprises an adversarial learning network of a generator and two discriminators, wherein the generator is generally a double-branch encoder-single-branch decoder structure; the fusion image obtained by the application can better retain the clear texture information of the MRI image and fully retain the color information of the PET / SPECT image; the objective evaluation results show that the algorithm is better than the average value of the comparative method by about 24.35%, 3.0%, 14.86%, 24.84%, 21.31%, 5.2% and 21.23% in the seven indexes of spatial frequency, pixel feature mutual information, visual information fidelity, average gradient, edge retention, structural similarity index and wavelet feature mutual information, which further shows that the method can effectively retain the color information of the PET / SPECT image and better fuse the texture information of the MRI image, thereby improving the performance of the existing PET / SPECT and MRI image fusion algorithm.
Need to check novelty before this filing date? Find Prior Art