一种淀粉样蛋白相关影像学异常的磁共振图像随访方法及系统
By constructing a bias field fitting model and using branch deformation field registration technology, the problems of bias field correction and skull dissection in magnetic resonance images were solved, achieving high-precision detection of amyloid-related imaging abnormalities and improving the accuracy of detection results and clinical application value.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WEST CHINA HOSPITAL SICHUAN UNIV
- Filing Date
- 2026-05-12
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, magnetic resonance imaging (MRI) for detecting amyloid-related imaging abnormalities (ARIA-E and ARIA-H) suffers from problems such as insufficient bias field correction accuracy, poor adaptability of cranial dissection to atrophied brain tissue, interference from grayscale of new lesions in longitudinal registration, and lack of targeted artifact removal in the post-processing stage, which affect the accuracy and clinical usability of the detection results.
By extracting white matter control points, constructing a bias field fitting model for bias field correction and intensity normalization, combining global alignment and edge detection, performing active contour evolution for skull dissection, and using branch deformation field registration processing, performing voxel-by-voxel difference operations and anisotropic diffusion filtering for noise reduction, artifact removal, achieving differentiated geometric screening, and generating detection results.
It improves the accuracy of bias field correction and the precision of skull dissection, reduces artifact interference, ensures the grayscale consistency of longitudinal images and the accuracy of lesion detection, and enhances the reliability of detection results and clinical application value.
Smart Images
Figure CN122175980B_ABST