Misaligned Image Feature Identification in Digital Subtraction Angiography
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In X-ray based imaging methods, inadequate registration between images often leads to image artifacts that can be misinterpreted in diagnosis and treatment, particularly in digital subtraction angiography, where movement artifacts and altered recording parameters are not fully compensated.
Innovation Solution
A computer-implemented method that receives and registers first and second image data sets of an examination object, determines a distance data set to identify misaligned image features caused by registration errors, and uses a trained function, such as a neural network, to classify and correct these features, thereby improving image alignment and reducing artifacts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If registration between image data sets is performed to compensate for movement artifacts and altered recording parameters, then image alignment is improved, but image artifacts may occur due to inadequate registering
Solution Approach 1:
The patent applies preliminary action by performing registration between image data sets before subtraction to compensate for movement artifacts and altered recording parameters. This advance alignment process attempts to correct geometric discrepancies before the critical subtraction operation, thereby improving image alignment while minimizing the formation of registration-related artifacts in the final differential image.
2Loss of information
If digital subtraction angiography is used to remove irrelevant components, then diagnostic clarity is improved, but misaligned image features cause misinterpretation
Solution Approach 1:
The patent implements feedback by identifying misaligned image features in the distance data set and using this information to adjust registration parameters. The system continuously monitors for misalignment artifacts and feeds this information back to improve the registration process, thereby enhancing the reliability of image interpretation while maintaining the diagnostic clarity achieved through digital subtraction angiography.
3Stability of the object's composition
If registration parameters are adjusted to improve alignment, then image consistency is improved, but complexity of registration process increases
Solution Approach 1:
The patent applies parameter changes by adjusting registration parameters based on identified misaligned image features. The system modifies geometric transformation parameters, scaling factors, and rotation angles to optimize alignment between image data sets. This dynamic parameter adjustment improves image consistency and reduces registration artifacts while managing process complexity through automated parameter optimization.
Data Source
AI summary
Systems and method for providing misaligned image features. A method includes receiving a first and a second image data set, wherein the first and the second image data sets map at least partially a shared examination region of an examination object, registering the first image data set with the second image data set, determining a distance data set based on the registered first image data set and the second image data set, identifying the misaligned image features in the distance data set that are caused by a misalignment between the registered first and the second image data sets, and providing the identified misaligned image features.