An r2* image synthesis method based on a generative adversarial network

By using a generative adversarial network-based method to generate R2* images from T1-weighted images and T2-weighted images, the time-consuming and artifact-sensitive problems of existing technologies are solved, and fast and accurate image generation is achieved, providing an effective tool for auxiliary diagnosis of Parkinson's disease.

CN119723260BActive Publication Date: 2025-10-10UNIV OF SCI & TECH OF CHINA +1
2 Cites 0 Cited by

Patent Information

Application Number
CN202411631844.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-11-15
Publication Date
2025-10-10
Estimated Expiration
2044-11-15

AI Technical Summary

Technical Problem

The existing methods for obtaining R2* images are time-consuming and computationally intensive, and are sensitive to magnetic susceptibility artifacts and motion artifacts, and cannot be incorporated into routine clinical protocols.

Method used

A generative adversarial network-based method is used to generate R2* images from T1-weighted images and T2-weighted images through data preprocessing, ROI segmentation, GAN model and quantitative evaluation. The transverse relaxation rate constant is corrected using a single exponential decay model, and image synthesis is performed by combining the pix2pix image conversion framework and the VGG-16 model.

Benefits of technology

It achieves rapid and accurate generation of R2* images, improves the relevance and accuracy of image generation, and provides a powerful tool for auxiliary diagnosis of neurodegenerative diseases such as Parkinson's disease.

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

Abstract

The application provides an R2* image synthesis method based on a generative adversarial network, comprising the following steps: S1, data preprocessing: calculating and correcting R2* values from MEGRE sequences; S2, ROI segmentation: after matching the R2* graph with the AALv3 template, the average R2* values of the regions of interest are extracted from the synthesis graph and the real graph; S3, GAN model: the generator inputs the T1 weighted image and the T2 weighted image, and generates the corresponding R2* image; the discriminator distinguishes the synthesized R2* image generated by the generator from the real R2* image obtained from the real MEGRE sequence; S4, quantitative evaluation of the generated image: the normalized mean square error, the peak signal-to-noise ratio and the structural similarity index are used to evaluate the similarity between the synthesized image and the real R2* graph; S5, statistical analysis: the R2* values of the regions of interest in the synthesized graph and the real R2* graph are analyzed and compared. The application realizes the auxiliary diagnosis of neurodegenerative diseases similar to Parkinson's disease from the perspective of medical image synthesis and processing.
Need to check novelty before this filing date? Find Prior Art