Image Processing Apparatus Prioritizing Structures of Interest
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing technologies struggle to determine the superiority and inferiority of structures of interest having the same type, particularly in cases where these structures overlap, as they do not consider the mutual relationships between them.
Innovation Solution
An image processing apparatus that acquires projection images, reconstructs tomographic images, detects structures of interest, and determines priorities for each structure of interest based on their mutual relationships, such as closeness and size, to create a synthesized two-dimensional image that emphasizes the most relevant structures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If structures of interest are detected using independent recognition modules for each type, then detection capability is improved, but the ability to determine superiority and inferiority of structures with the same type deteriorates
Solution Approach 1:
The patent merges multiple independent recognition modules into a unified recognition system that processes all structures of interest simultaneously. This unified system analyzes mutual relationships between structures of the same type (such as calcifications) to determine their superiority and inferiority, thereby resolving the contradiction between maintaining detection capability and preserving relationship information.
2Productivity
If synthesized two-dimensional image is created by simple synthesis methods, then image creation speed is improved, but the ability to emphasize structures of interest deteriorates
Solution Approach 1:
The patent introduces priority values as a new parameter to control the synthesis process. By assigning different priority levels to structures of interest based on their mutual relationships and clinical significance, the system emphasizes important structures while maintaining efficient synthesis processing. This resolves the contradiction between fast image creation and accurate structure emphasis.
3Device complexity
If all structures of interest are given equal priority, then processing simplicity is improved, but diagnostic accuracy deteriorates
Solution Approach 1:
The patent applies local quality by assigning different priority levels to different structures of interest based on their specific characteristics and mutual relationships. Instead of uniform processing, the system evaluates each structure's importance locally (e.g., clustered calcifications receive higher priority than isolated ones), thereby improving diagnostic accuracy without excessive complexity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables the determination of superiority and inferiority of structures of interest with the same type by considering their mutual relationships, resulting in improved visibility and interpretation of the synthesized two-dimensional images.
Implementation Method 1
acquire projection images obtained by imaging a subject with radiation at a plurality of angles
Implementation Method 2
reconstruct a plurality of tomographic images from the acquired projection images
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
An image processing apparatus includes at least one processor that is configured to: acquire projection images obtained by imaging a subject with radiation at a plurality of angles; reconstruct a plurality of tomographic images from the acquired projection images; detect a plurality of structures of interest from the plurality of reconstructed tomographic images; and determine a priority for each of the structures of interest having the same type among the plurality of detected structures of interest by using a mutual relationship with other structures of interest.