一种基于分块条件扩散和动态正则项修正的高分辨率有限角CT重建方法
By combining block-based conditional diffusion and dynamic regularization correction with filtering back projection algorithm and position coding, the problem of insufficient resolution and reliability in finite-angle CT reconstruction is solved, and efficient high-resolution CT image reconstruction is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DALIAN UNIV OF TECH
- Filing Date
- 2026-05-14
- Publication Date
- 2026-07-17
AI Technical Summary
Existing finite-angle CT reconstruction schemes based on diffusion models have shortcomings in terms of reconstruction resolution, accuracy, and reliability. Traditional methods are difficult to achieve high-resolution CT image reconstruction and suffer from artifacts, blurring, and structural distortion.
A method based on block-based conditional diffusion and dynamic regularization is adopted, which combines filtering back projection algorithm, position encoding and dynamic regularization. Through the block-based conditional diffusion module and the dynamic regularization consistency correction module, the reliability and resolution of the reconstruction process are improved.
It achieves clear imaging of high-resolution CT images under limited angle projection conditions, improves the accuracy and efficiency of non-destructive testing, and reduces artifacts and structural errors.
Smart Images
Figure SMS_2 
Figure SMS_9 
Figure SMS_14