Control Point Identification in DSA Gradient Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Digital Subtraction Angiography (DSA) faces significant motion artifacts due to patient movements, reducing the diagnostic value of vascular images, as existing technologies fail to accurately identify control points and register images effectively.
Innovation Solution
A method for identifying control points in gradient images by segmenting them into blocks, determining the number of control points based on preset numbers and pixel values, and iteratively selecting target control points, followed by image registration using similarity measurements to align mask and live images, thereby reducing motion artifacts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing control point identification methods are used, then the process is simple, but the accuracy of control point identification is low leading to poor image registration
Solution Approach 1:
The patent divides the image into multiple blocks and processes each block separately to identify control points. This segmentation approach improves identification accuracy by focusing on local features while managing complexity through divide-and-conquer processing.
Solution Approach 2:
The patent applies different processing strategies to different image blocks based on their local characteristics. By determining the number of control points to be selected for each block based on pixel values within that block, the method adapts to local image quality variations, improving overall accuracy without uniform complexity.
2Reliability
If image registration is not performed accurately, then processing is faster, but motion artifacts remain significant reducing diagnostic value
Solution Approach 1:
The patent performs control point identification and image registration before the final image subtraction process. By preparing accurate control points and registering images in advance, the method ensures high reliability of the final subtracted images while managing time through efficient preprocessing.
Solution Approach 2:
The patent uses similarity measurements to evaluate registration quality and iteratively improves alignment. This feedback mechanism ensures motion artifacts are minimized and diagnostic value is maximized, with the iteration process balanced against time constraints.
3Measurement precision
If more control points are selected, then image registration accuracy improves, but computational complexity increases
Solution Approach 1:
The patent determines the number of control points to be selected for each image block based on pixel values within that block. This local adaptation allows more control points in complex regions and fewer in simple regions, optimizing registration accuracy while controlling computational power requirements.
Solution Approach 2:
The patent dynamically adjusts the number of control points based on image characteristics and processing requirements. By changing this parameter adaptively rather than using a fixed number, the method achieves high registration accuracy when needed while reducing computational burden when possible.
Data Source
AI summary
This disclosure relates to a method for identifying control points, an apparatus and a computer device. Multiple image blocks are obtained by segmenting a target gradient image, and a number of control points to be selected for each image block is determined based on a first preset number of control points and pixel values within each image block. Target control points are therefore identified in the target gradient image based on image block information corresponding to each image block. The target gradient image is a gradient image of a target image of an inspected object. The target image includes any one of a mask image, a live image, or a subtracted image. The image block information includes the number of control points to be selected for the corresponding image block and a size of the image block.