Iterative X-Ray Image Correction with Adaptive Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing methods for medical image data, particularly in X-ray imaging, often result in local quality optima due to the use of relative image quality measures, leading to suboptimal corrections for artifacts such as motion and metal artifacts.
Innovation Solution
A computer-implemented method that iteratively adjusts quality thresholds based on input data characteristics and acquisition information to reduce the likelihood of local optima, using a combination of relative and absolute quality measures to optimize correction parameters, such as motion and beam hardening artifacts, through techniques like downhill simplex methods and machine learning algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If relative image quality measures are used to compare intermediate data sets, then computational complexity is reduced and training requirements are minimized, but the probability of achieving only local quality optima increases
Solution Approach 1:
The patent dynamically adjusts the quality threshold parameter during iterative optimization. The threshold is not fixed but adapts based on the optimization progress and data characteristics, allowing the system to transition from exploratory phases (lower thresholds) to refinement phases (higher thresholds), thereby reducing the probability of stagnating at local optima while maintaining computational efficiency
Solution Approach 2:
The quality threshold is made dynamic rather than static. The system continuously monitors optimization progress and adjusts the threshold accordingly, enabling the optimization process to adapt to changing conditions and escape local optima when necessary, while converging reliably when the threshold indicates sufficient improvement
2Productivity
If a fixed quality threshold is used for comparing intermediate data sets, then the optimization process is simple and fast, but false positive and false negative detections increase leading to suboptimal corrections
Solution Approach 1:
The system incorporates feedback mechanisms that monitor the distribution of quality measures during optimization. Based on this feedback, the quality threshold is adjusted to account for false positives and negatives, allowing the system to maintain high optimization speed while improving assessment precision through adaptive thresholding informed by actual performance data
3Measurement precision
If the quality threshold is lowered to reduce false negatives, then more potential corrections are identified, but the false positive rate increases leading to rejection of valid corrections
Solution Approach 1:
The quality threshold is adjusted periodically or at specific optimization stages rather than remaining constant. During early iterations when explorability is needed, lower thresholds increase sensitivity. As optimization progresses and convergence approaches, the threshold is raised to reduce false positives, ensuring reliable acceptance of corrections while maintaining high detection sensitivity when needed
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A computer-implemented method comprising the following steps: - generating an initial intermediate data set group (36) of several intermediate data sets (37, 38, 39) by applying a respective correction operation (40) to an input data set (35), - ordering the intermediate data sets (37, 38, 39) with respect to their image quality by a sorting algorithm (42), by: • determining a respective relative quality measure (44) for the relative image quality of intermediate data sets (38) by means of a comparison algorithm (43), • whereupon the order (49) of the intermediate data sets (38, 39) is specified by a comparison of the relative quality measure (44) with a quality threshold (45), - where, if a termination condition (46) is not met, a modified intermediate data set group (47) is formed, after which, in a further iteration, the ordering of the intermediate data sets (37, 38, 39) and the evaluation are carried out. the termination condition (46) is repeated,wherein, on the one hand, different quality limits (45) are used in at least two of the iterations and/or wherein, on the other hand, in at least one of the iterations, the quality limit (45) is specified depending on the input data set (35) and/or on a recording information (50) that relates to at least one property of the recording of the input data set (35).