Emission Tomography Reconstruction Using Adaptive Iteration Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing emission tomography systems face challenges in optimizing the number of iterations and reconstruction parameters, leading to over-fitting or under-fitting, noise enhancement, and poor image resolution due to varying patient conditions and data quality.
Innovation Solution
Adaptive data-space driven reconstruction methods that utilize count density and patient-specific factors like BMI and motion to control the number of iterations and pixel size, optimizing the reconstruction process for improved image quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the number of iterations is increased to improve image resolution, then image resolution is improved, but noise enhancement and over-fitting occur
Solution Approach 1:
The patent dynamically adjusts the number of reconstruction iterations based on count density parameters. By changing the iteration parameter according to the actual data quality (count density), the system optimizes image resolution while preventing noise enhancement and over-fitting that occur with excessive iterations.
Solution Approach 2:
The system uses count density as a feedback metric to control the reconstruction process. The count density calculated from detected emissions feeds back into the decision of how many iterations to perform, creating a closed-loop control that adapts to data quality and prevents over-fitting.
2Object-generated harmful factors
If the number of iterations is decreased to reduce noise, then noise enhancement is reduced, but image resolution deteriorates
Solution Approach 1:
The system adjusts the iteration parameter based on count density to achieve the optimal balance. When count density is high, more iterations can be performed without excessive noise, preserving resolution. When count density is low, fewer iterations prevent noise enhancement while maintaining acceptable resolution.
Solution Approach 2:
The patent applies different reconstruction parameters (number of iterations) based on local data quality characteristics. By evaluating count density in the specific dataset and applying appropriate iteration counts tailored to that data quality, the system achieves optimal resolution without noise enhancement for each specific case.
3Ease of operation
If manual designation of reconstruction parameters is used to simplify operation, then ease of operation is improved, but manufacturing precision deteriorates
Solution Approach 1:
The system performs self-service by automatically determining optimal reconstruction parameters based on count density calculations. The emission tomography system itself evaluates its detected data quality and selects appropriate iteration counts without requiring manual input, thereby maintaining both ease of operation and reconstruction precision.
Solution Approach 2:
The system uses feedback from count density measurements to automatically control reconstruction parameters. This closed-loop approach eliminates the need for manual parameter designation while maintaining optimal reconstruction quality, as the system self-adjusts based on actual data characteristics.
4Device complexity
If fixed reconstruction parameters are used to simplify the process, then device complexity is reduced, but adaptability deteriorates
Solution Approach 1:
The patent implements dynamic parameter changes based on count density, allowing the reconstruction process to adapt to different patient conditions and data qualities. This maintains relatively simple device architecture while achieving high adaptability through software-based parameter adjustment.
Solution Approach 2:
The system transitions from static, fixed reconstruction parameters to dynamic parameters that change based on count density. This enables the reconstruction process to adapt to varying patient conditions, body mass indices, and motion levels while maintaining a relatively simple overall system design.
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.