Image Reconstruction Sequencing for Faster High-Quality Output
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional image reconstruction methods often result in marginal benefits due to excessive iterations and lack of dynamic sequencing of reconstruction algorithms, leading to inefficient use of computing resources and time constraints.
Innovation Solution
A system and method utilizing a multi-processor unit to determine an optimal weighted execution sequence of reconstruction algorithms, leveraging parallel processing to test multiple sequences on a representative portion of image data, reducing the need for extensive pre- and post-processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional image reconstruction methods use excessive iterations to improve image quality, then manufacturing precision is improved, but loss of time and productivity deteriorate
Solution Approach 1:
The patent applies dynamics by making the iteration count adaptive rather than static. The system dynamically determines the optimal number of iterations based on convergence criteria, where the iteration process automatically stops when the image quality metric stabilizes, preventing excessive iterations while ensuring sufficient reconstruction quality.
Solution Approach 2:
The patent changes the parameter of iteration count from a fixed excessive value to a dynamically adjusted value based on convergence monitoring. By monitoring image quality metrics across iterations and stopping when improvement falls below a threshold, the system optimizes the balance between image quality and reconstruction time.
2Manufacturing precision
If multiple reconstruction algorithms are tested with different sequences to improve image quality, then manufacturing precision is improved, but device complexity and loss of time worsen
Solution Approach 1:
The patent applies preliminary action by pre-determining optimal algorithm sequences using training data before actual reconstruction. The system learns the best sequencing of reconstruction algorithms from training datasets, so that during actual operation, the pre-optimized sequence can be directly applied without extensive real-time testing, reducing both complexity and time.
Solution Approach 2:
The patent uses copying by applying the optimal algorithm sequence learned from training data to actual reconstruction tasks. The system copies the successful sequencing pattern identified during training and applies it to new datasets, avoiding the need to re-test all possible sequences for each reconstruction task.
3Manufacturing precision
If extensive pre- and post-processing is performed to improve image reconstruction accuracy, then manufacturing precision is improved, but productivity and loss of time worsen
Solution Approach 1:
The patent extracts and removes unnecessary pre- and post-processing steps by identifying and eliminating redundant operations. The system focuses only on the essential reconstruction algorithms and their optimal sequencing, discarding excessive processing steps that do not contribute meaningfully to image quality, thereby improving processing efficiency.
Data Source
AI summary
This disclosure introduces an approach that includes techniques for determining an optimal weighted execution sequence of available reconstruction algorithms using a multi-processor unit. The introduced approach includes executing a series of optimal weighted execution sequence candidates on a representative slice of the image data and comparing their results to select one of the candidates as the optimal weighted execution sequence.