Medical image cross-modality generation method based on dual-contrast frequency domain decomposition and adaptive diffusion

By employing a method based on dual-contrast frequency domain decomposition and adaptive diffusion, the problems of grayscale shift and texture conflict in multimodal data fusion during medical image generation were solved. This method enables targeted processing of high-frequency information and restoration of low-frequency structures, generating high-quality, high-resolution medical images that meet real-time clinical needs.

CN121095366BActive Publication Date: 2026-06-26CHONGQING UNIV OF TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHONGQING UNIV OF TECH
Filing Date
2025-07-08
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing technologies in medical image generation suffer from grayscale shifts or texture conflicts due to differences in imaging parameters during multimodal data fusion, lack of specificity in frequency domain processing, high computational complexity of diffusion models that are difficult to meet real-time clinical needs, and underutilization of k-space data information.

Method used

A method based on dual-contrast frequency domain decomposition and adaptive diffusion is adopted. Through k-space decomposition and enhancement processes, a k-space dual-stream adaptive degradation and prediction network is constructed. By utilizing an adaptive Gaussian filter bank and a residual noise diffusion model, combined with anatomical structure consistency constraints and multimodal fusion optimization strategies, targeted processing of high-frequency information and recovery of low-frequency structures are achieved.

Benefits of technology

It improves the quality and visual realism of cross-modal generation of medical images, solves the problems of grayscale shift and texture conflict during multimodal fusion, and generates images with rich details and high resolution to meet the real-time needs of clinical practice.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121095366B_ABST
    Figure CN121095366B_ABST
Patent Text Reader

Abstract

The application provides a medical image cross-modality generation method based on double-contrast frequency domain decomposition and adaptive diffusion, which comprises the following steps: acquiring MRI samples and preprocessing, constructing a k-space decomposition and enhancement process, constructing a k-space double-flow adaptive degradation network, and constructing a k-space double-flow adaptive prediction network. Through data enhancement technology and an adaptive Gaussian filter set, different frequency components are separated and enhanced, common edge features are highlighted, and the quality of generated information is improved. By using a residual noise diffusion model, high-resolution images with rich details and high diversity are generated while maintaining smooth areas and large-scale structures of images. By introducing anatomical structure consistency constraints and multi-modality fusion optimization strategies, the complementary information of T1 and T2 weighted MRI is fully utilized, and the generation effect and visual authenticity of the medical image cross-modality generation in a complex scene are significantly improved.
Need to check novelty before this filing date? Find Prior Art