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.
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
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.
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.
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.