Tomographic Image Composite Generation for Fine Structure Clarity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating composite two-dimensional images from tomographic images acquired through tomosynthesis imaging fail to effectively depict structures of interest in depth and fine structures, leading to blurred or faint representations.
Innovation Solution
An image processing device that detects structures of interest from multiple tomographic images, selects the most representative tomographic images based on the type of structure, and generates a composite two-dimensional image using these selected images, ensuring clear representation of structures in depth and fine details.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple tomographic images are combined using addition or averaging methods, then the composite two-dimensional image shows overall structure, but fine structures such as calcification and linear structures like spicula become faint and difficult to see
Solution Approach 1:
The patent segments the combination process by separately handling different types of structures. It identifies structures of interest (calcification, spicula, tumors) and selects specific tomographic images for each type rather than uniformly combining all images. This segmentation allows fine structures to be preserved while maintaining overall structure representation.
Solution Approach 2:
The patent applies local quality by selecting tomographic images based on the specific type of structure of interest detected in each region. Different weights and selection criteria are applied to different regions depending on whether they contain calcification, spicula, or tumors, optimizing the visualization for each local structure type rather than using a uniform combination approach.
2Measurement precision
If structures of interest from one tomographic image are combined, then the composite image shows the structure, but structures present across multiple tomographic images in the depth direction are not properly reflected
Solution Approach 1:
The patent performs preliminary detection of structures of interest across all tomographic images before combining them. By pre-identifying which structures appear in which images and their spatial relationships, the system can then select and combine images in a way that preserves depth information, rather than combining images without prior analysis of structure distribution.
Solution Approach 2:
The patent transitions from two-dimensional image combination to three-dimensional structure-aware combination. By considering the depth dimension and which tomographic images contain which structures, the system creates a composite image that reflects the three-dimensional spatial distribution of structures of interest, not just their two-dimensional projections.
Data Source
AI summary
A processor detects a structure of interest from a plurality of tomographic images indicating a plurality of tomographic planes of an object. The processor selects a tomographic image from the plurality of tomographic images according to a type of the structure of interest in a region in which the structure of interest has been detected and generates a composite two-dimensional image using the selected tomographic image in the region in which the structure of interest has been detected and using a predetermined tomographic image in a region in which the structure of interest has not been detected.