Causal Device for Hybrid Imaging Attenuation Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing hybrid imaging technologies, such as PET/MRI, face challenges in accurate attenuation correction, motion and registration errors, and various artifacts, which affect the accuracy and reliability of imaging data. Additionally, existing priority triage methods for medical imaging are not always accurate in predicting patient urgency, leading to delays or unnecessary interventions.
Innovation Solution
A causal device and method that utilize causal relationships between variables to improve image reconstruction and priority triage. This involves a causal module to identify causal relationships and a causal feature learning module to extract causal features, which are then used for more accurate image reconstruction and patient prioritization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If PET/MRI hybrid imaging is performed to obtain complementary anatomical and functional information, then imaging accuracy and comprehensiveness are improved, but attenuation correction errors and registration errors increase due to the lack of direct photon attenuation information in MRI and differences in imaging geometry
Solution Approach 1:
The patent introduces an attenuation map as an intermediary component that translates MRI data into PET attenuation correction factors. The attenuation map serves as a mediator between the MRI anatomical information and PET functional data, enabling accurate attenuation correction without direct photon attenuation measurement in MRI. This resolves the contradiction by providing a reliable transformation mechanism between the two imaging modalities.
Solution Approach 2:
The patent replaces the traditional mechanical registration process with an automated image registration system that uses algorithms to align PET and MRI images based on anatomical landmarks and intensity correlations. This substitution eliminates manual intervention and reduces registration errors caused by physiological state differences, thereby improving both imaging accuracy and data reliability.
2Productivity
If existing priority triage methods are used to predict patient urgency, then the triage process can be automated, but prediction accuracy decreases leading to delays in treatment or unnecessary interventions
Solution Approach 1:
The patent transforms the priority triage system from using fixed rules to using dynamic parameters derived from causal relationships in imaging data. By continuously adjusting triage parameters based on causal feature analysis of imaging results, the system maintains high prediction accuracy while achieving automation. This resolves the contradiction by enabling adaptive parameter adjustment that improves both efficiency and accuracy.
Solution Approach 2:
The patent applies different causal analysis methods to different regions and features of imaging data based on their specific characteristics. Instead of using a uniform approach, the system identifies causally relevant features in different anatomical regions and applies appropriate analysis techniques locally, thereby improving overall prediction accuracy while maintaining automated efficiency.
Data Source
AI summary
A causal device, which includes a causal module and a causal feature learning module coupled to the causal module, and a causal method thereof is disclosed to ensure accurate fusion of hybrid imaging or improve priority triage of imaging tests. The causal module is configured to identify or utilize causal relationship(s) between a plurality of variables; the causal feature learning module is configured to extract at least one first causal feature of one of the plurality of variables.