Region-Specific Image Reconstruction to Reduce Tissue Crosstalk
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing imaging systems use a single filter function kernel across different tissues/organs, leading to varying image quality and increased artifacts, particularly in regions like the lung, liver, and heart, due to crosstalk and suboptimal filtering.
Innovation Solution
The system selects filter kernels with matching cut-off frequencies for specific regions of interest and background regions, generating separate orthographic projection images for each, followed by combining and back projecting to create a high-quality reconstructed image.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single filter function kernel is used across different tissues/organs, then the processing process is simplified and processing efficiency is improved, but image quality varies and artifacts increase in certain regions
Solution Approach 1:
The patent applies different filter function kernels to different anatomical regions based on their specific characteristics. Each region (e.g., lung, liver, heart) receives a customized filter kernel optimized for its tissue properties, thereby improving image quality and reducing artifacts in each specific region while maintaining overall processing efficiency through automated region identification and kernel selection.
2Device complexity
If a single filter function kernel is used across different tissues/organs, then device complexity is reduced, but crosstalk between different tissues/organs increases and image quality deteriorates
Solution Approach 1:
The system automatically identifies different anatomical regions and selects appropriate filter kernels for each region, improving image accuracy by reducing crosstalk between tissues. The complexity is managed through automated region segmentation and kernel selection algorithms, which streamline the process while maintaining high image quality across all regions.
Solution Approach 2:
The imaging process is segmented into distinct anatomical regions, with each region processed using a specialized filter kernel. This segmentation approach reduces crosstalk between different tissues by isolating their processing pathways, thereby improving overall image reliability while keeping the system manageable through automated region detection and classification.
3Manufacturing precision
If region-specific filter kernels are used, then crosstalk between tissues/organs is reduced and image quality is improved, but processing complexity and disk space requirements increase
Solution Approach 1:
The patent implements region-specific filtering by automatically identifying anatomical regions and applying customized filter kernels to each. This approach improves image quality by reducing crosstalk between tissues while managing processing complexity through automated workflows that handle region detection, kernel selection, and application without requiring manual intervention for each region.
Solution Approach 2:
The system performs self-service by automatically identifying anatomical regions and selecting appropriate filter kernels without external intervention. This automation reduces the perceived processing complexity for users while maintaining high image quality through optimized region-specific filtering, and manages disk space by selectively storing only the necessary filtered images.
Data Source
AI summary
An imaging system and reconstruction method are described. The method includes identifying at least one region of interest in a first reconstructed image, generating a region-of-interest orthographic projection image of each region of interest and a background-region orthographic projection image of a background region, obtaining a region-of-interest filtered orthographic projection image of each region of interest and a background-region filtered orthographic projection image, wherein the region-of-interest filtered orthographic projection image is obtained by filtering a current-region-of-interest orthographic projection image using a filter kernel function matched with a current region of interest, and the background-region filtered orthographic projection image is obtained by filtering the background-region orthographic projection image using a filter kernel function matched with the background region, and generating a second reconstructed image based on the region-of-interest filtered orthographic projection image of each region of interest and the background-region filtered orthographic projection image.