Tomographic Image Analysis for Lesion Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Interpreting multiple tomographic images obtained through tomosynthesis imaging requires cumbersome operations and significant time, as healthcare professionals need to switch between images to detect and observe lesions, which is inefficient compared to reading two-dimensional images.
Innovation Solution
An image processing device and method that captures radiographic images from different angles, reconstructs tomographic images, and allows users to specify regions or positions of interest in a two-dimensional image, then analyzes and detects corresponding regions or positions in multiple tomographic images, displaying only the relevant images containing the object of interest.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple tomographic images are obtained through tomosynthesis imaging, then the ability to detect and observe lesions is improved, but the time and effort required for interpretation increases significantly
Solution Approach 1:
The patent extracts and displays only the relevant tomographic images that contain the object of interest, rather than requiring interpretation of all captured images. The display control unit selectively outputs images based on detection results, extracting only the necessary information for diagnosis while filtering out irrelevant images.
Solution Approach 2:
The patent performs preliminary detection and analysis of tomographic images to identify which ones contain the object of interest before presenting them to the user. The detection unit pre-processes the images to determine relevance, so that only pre-selected meaningful images are displayed for interpretation.
2Measurement precision
If multiple tomographic images are obtained through tomosynthesis imaging, then the ability to detect and observe lesions is improved, but the operational complexity increases due to switching between images
Solution Approach 1:
The system extracts and displays only the relevant tomographic images that contain the object of interest, eliminating the need for users to manually switch through multiple images. The display control unit automatically filters and presents only the necessary images for diagnosis.
Solution Approach 2:
The system performs automatic detection and selection of relevant images without requiring manual intervention to switch between images. The detection unit and display control unit work autonomously to identify and present meaningful images, reducing the operational burden on users.
3Measurement precision
If image analysis is performed by comparing region of interest with corresponding regions in multiple tomographic images, then the accuracy of detecting relevant images is improved, but the processing time increases
Solution Approach 1:
The patent performs image analysis only on the necessary corresponding regions between the two-dimensional image and tomographic images, rather than analyzing entire images. By focusing analysis on specific regions of interest and their corresponding areas, the system achieves accurate matching while reducing overall processing time.
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 efficient interpretation of tomographic images by displaying only the images with the object of interest, reducing the time and effort required for medical examination and improving workflow efficiency, while also reducing exposure and capture time for the subject.
Implementation Method 1
plural first radiographic images are captured by the radiographic image detector by irradiating radiation from the radiation irradiating section
Implementation Method 2
the tomographic image generating means generates plural tomographic images of the subject by reconstructing the plural first radiographic images
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An image processing device includes a tomographic image generating means that acquires generates tomographic images, a display processing means that displays a second radiographic image, and detection means. If a region of interest is specified on the second radiographic image, the detection means performs image analysis by comparing the region of interest with corresponding regions that are regions in the tomographic images corresponding to the region of interest, and detects a tomographic image including a corresponding region that is similar to the region of interest. If a position of interest is specified on the second radiographic image, the detection means performs image analysis by comparing the position of interest with corresponding positions that are positions in the tomographic images corresponding to the position of interest, and detects a tomographic image including a corresponding position that is similar to the position of interest.