Medical Image Reconstruction via Data Consistency Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional medical image reconstruction techniques struggle with inconsistencies in data acquisition, leading to artifacts in reconstructed images due to factors like subject motion, metal objects, and dynamic changes during imaging, lacking systematic methods to quantify and mitigate these issues.
Innovation Solution
The approach involves analyzing imaging data to create subsets with high data consistency, generating synthetic projection data, calculating data inconsistency metrics, and compensating for inconsistencies to reconstruct images with reduced artifacts using techniques like SMART-RECON.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional image reconstruction techniques are used, then image reconstruction is achieved, but artifacts are introduced due to data inconsistencies
Solution Approach 1:
The patent segments the acquired data into multiple subsets based on consistency levels. Data is classified into different groups (e.g., consistent data, partially consistent data, inconsistent data) and processed separately through different reconstruction methods, thereby reducing artifacts while maintaining reconstruction capability
Solution Approach 2:
Different reconstruction methods are applied to different data subsets based on their consistency characteristics. High-consistency data uses one reconstruction method while low-consistency data uses another, optimizing the balance between reconstruction accuracy and artifact reduction for each local data region
2Object-affected harmful factors
If data consistency is improved through filtering, then artifact reduction is achieved, but information loss occurs
Solution Approach 1:
Instead of uniformly filtering all data, the patent segments data into consistency-based subsets and applies selective filtering only to necessary portions, preserving informative data while removing only the most inconsistent portions
Solution Approach 2:
The patent employs feedback mechanisms where reconstructed images from consistent data subsets are used to guide and adjust the processing of inconsistent data subsets, allowing iterative refinement that preserves useful information while reducing artifacts
3Area of stationary object
If all acquired data is used for reconstruction, then complete image coverage is achieved, but artifacts increase due to inconsistencies
Solution Approach 1:
The patent divides the complete data set into multiple consistency-based subsets and processes them through different reconstruction pathways, allowing full image coverage through the combined results while minimizing artifacts by excluding or correcting inconsistent data portions
Solution Approach 2:
The patent merges reconstructed images from multiple data subsets (consistent, partially consistent, inconsistent) through a combining process that weights and integrates results, achieving comprehensive image coverage while the merging algorithm suppresses artifact propagation from inconsistent data
Data Source
AI summary
A system and method for reconstructing an image of a subject includes acquiring a reference dataset and reconstructing a prior image of the subject from the reference dataset and selecting at least a portion of the prior image that corresponds to a portion of the prior image of the subject that is free of artifacts. The method also includes acquiring a medical imaging dataset of the subject, performing a vertical comparison of the medical imaging dataset and the reference dataset to create a data inconsistency metric, and repeating the preceding steps to create a plurality of data inconsistency metrics. The method further includes performing a horizontal comparison of the data inconsistency metrics to identify inconsistent data, compensating for the inconsistent data, and reconstructing an image of the subject with reduced artifacts compared to the prior image.