Emission Tomography Reconstruction with Adaptive Count-Density Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing emission tomography systems face challenges in optimizing the number of iterations and reconstruction parameters based on the quality of detected emissions and clinical purpose, leading to issues such as over-fitting or poor resolution.
Innovation Solution
A method and system that adaptively control reconstruction by determining the count density and pixel size to set the number of iterations, using data quality measures like BMI and motion to adjust settings, thereby optimizing image quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If the number of iterations is increased to improve image resolution, then manufacturing precision is improved, but reliability deteriorates due to over-fitting and noise enhancement
Solution Approach 1:
The patent implements feedback by continuously monitoring the change in image quality metrics between successive iterations. When the improvement falls below a threshold or begins to deteriorate (indicating over-fitting), the reconstruction process automatically stops, preventing noise enhancement while maintaining optimal resolution.
Solution Approach 2:
The patent employs dynamic iteration control where the number of iterations is not fixed but adaptively adjusted based on data quality characteristics such as count density. The system dynamically selects reconstruction parameters including iteration count, filtering strength, and regularization based on the specific characteristics of each dataset.
2Reliability
If the number of iterations is decreased to avoid over-fitting, then reliability is improved, but manufacturing precision deteriorates due to poor resolution
Solution Approach 1:
The patent changes reconstruction parameters adaptively based on data quality. For high-count-density data, more iterations are permitted to achieve higher resolution. For low-count-density data, fewer iterations are used with increased regularization to prevent over-fitting, thus maintaining reliability while optimizing resolution for each case.
Solution Approach 2:
The patent performs preliminary assessment of data quality characteristics (count density, noise levels, patient motion) before initiating reconstruction. Based on this preliminary analysis, optimal reconstruction parameters including iteration count are pre-determined, preventing both over-fitting and under-resolution issues.
3Ease of operation
If manual designation of reconstruction parameters is used to simplify operation, then ease of operation is improved, but device complexity increases due to need for user expertise
Solution Approach 1:
The reconstruction system performs self-service by automatically analyzing data quality characteristics and selecting optimal reconstruction parameters without user intervention. The system independently determines iteration count, filtering parameters, and regularization strength based on count density and other quality metrics, eliminating the need for user expertise in parameter selection.
Solution Approach 2:
The patent implements automatic parameter adaptation where reconstruction parameters are dynamically changed based on data characteristics. The system automatically adjusts iteration count, resolution settings, and regularization parameters according to count density and quality metrics, replacing manual parameter designation with intelligent automated control.
Data Source
AI summary
For controlling reconstruction in emission tomography, the quality of data for detected emissions and/or the application controls the settings used in reconstruction. For example, a count density of the detected emissions is used to control the number of iterations in reconstruction to more likely avoid over and under fitting. The count density may be adaptively determined by re-binning through pixel size adjustment to find a smallest pixel size providing a sufficient count density. As another example, the detected data may have poor quality due to motion or high body mass index (BMI) of the patient, so the reconstruction is set to perform differently (e.g., less smoothing for high motion or a different number of iterations for high BMI). The quality of the data may be used in conjunction with the application or task for imaging the patient to control the reconstruction.