DSA Image Artifact Removal via Global and Local Registration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Digital Subtraction Angiography (DSA) systems struggle to effectively remove artifacts from medical images, particularly due to differences in collection time between mask and shadow images, leading to low-quality vascular images.
Innovation Solution
A method involving global and local registration of mask and contrast images, followed by subtraction to produce high-quality vascular images, is implemented. This method includes preprocessing images with techniques like logarithmic transformation, regularization, normalization, or denoising, and uses block matching and boundary extension to achieve accurate registration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If simple splicing of images at different positions is performed, then the photographing process can be completed, but motion artifacts occur due to time differences between mask and shadow images
Solution Approach 1:
The patent performs preliminary registration actions on the mask image and shadow image before splicing. By aligning the images through registration based on reference points and transformation matrices, the system compensates for motion artifacts that would otherwise occur due to time differences between image acquisitions, thereby maintaining high image quality while enabling efficient photographing
Solution Approach 2:
The patent introduces reference points and transformation matrices as intermediaries to bridge the mask image and shadow image. These intermediaries enable precise alignment and coordination between the two images, resolving the temporal mismatch issue and allowing artifact-free splicing of multiple position images
2Area of stationary object
If images at different positions are spliced without registration, then the complete DSA image can be obtained, but artifact removal is ineffective
Solution Approach 1:
The patent performs preliminary registration on images at different positions before splicing them into a complete DSA image. By establishing coordinate transformations and aligning images based on reference points, the system ensures that artifacts are minimized or eliminated in the final composite image, thereby achieving both comprehensive coverage and high precision
Solution Approach 2:
The patent divides the complete DSA image into multiple position-specific images, applies registration to each segment independently, and then splices them together. This segmented approach allows precise artifact removal in each region while maintaining the overall completeness of the vascular structure visualization
Data Source
AI summary
A method for artifact removal of a medical image and a DSA system are provided. The method includes: acquiring an image set of a collected position in a target portion, the image set including a mask image and a contrast image in one-to-one correspondence; performing global registration on the mask image and the contrast image of the collected position, and obtaining a first registration result; performing local registration on the image set after the global registration based on the first registration result, and obtaining a corresponding second registration result; and performing subtraction on the image set after the local registration based on the second registration result, and obtaining a subtraction image of the target portion.