Tomosynthesis Image Storage Reducing Capacity via CAD Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for storing and managing tomographic images from tomosynthesis imaging, such as those used in breast cancer diagnosis, result in high image storage capacity demands due to the generation of multiple images, with existing solutions requiring operator intervention and potentially low accuracy in detecting abnormal parts, leading to incomplete storage of relevant images.
Innovation Solution
An image display and management system that automatically detects abnormal parts, displays relevant tomographic images and composite two-dimensional images, and allows operators to set which images are displayed and stored, with the option to delete or compress non-displayed images, thereby reducing storage capacity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple tomographic images are stored for comprehensive diagnosis, then diagnostic accuracy is improved, but storage capacity requirements increase
Solution Approach 1:
The system extracts and stores only the essential tomographic images that contain abnormal parts detected by CAD, rather than storing all acquired images. The image storage unit selectively retains images based on abnormal part detection results, extracting only the necessary diagnostic information while discarding redundant normal images.
Solution Approach 2:
The system changes the parameter of image selection from storing all images to storing only images with detected abnormal parts. By using CAD to detect abnormal parts and changing the storage criterion parameter, the system maintains diagnostic accuracy for abnormal regions while significantly reducing overall storage requirements.
2Loss of information
If all acquired tomographic images are stored, then complete diagnostic information is preserved, but operator workload increases
Solution Approach 1:
The system performs self-service by automatically detecting abnormal parts using CAD and automatically selecting which images to store and display. The image storage unit and display control unit operate autonomously based on CAD results, eliminating the need for operators to manually review and select images, thus reducing operator burden while preserving complete diagnostic information.
Solution Approach 2:
The system performs preliminary action by pre-detecting abnormal parts using CAD before the operator views the images. This preliminary detection and selection process prepares the diagnostic information in advance, so when the operator accesses the images, only relevant cases requiring attention are presented, reducing the operator's workload.
3Quantity of substance
If only images with CAD-detected abnormal parts are stored, then storage capacity is reduced, but detection accuracy may be insufficient
Solution Approach 1:
The system implements feedback by using CAD detection results to guide image selection and storage. The CAD unit continuously analyzes images and provides feedback on abnormal part locations, which then determines which images are stored and displayed. This feedback loop ensures that images containing abnormal parts are reliably identified and preserved for diagnosis.
Solution Approach 2:
The CAD system acts as an intermediary between image acquisition and image storage/display. It mediates the process by analyzing all acquired images and selectively identifying those containing abnormal parts, serving as a bridge that filters and prepares information for the storage and display units based on detection accuracy.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A display control unit displays, on a display unit, a tomographic image for which a display command is given among a plurality of tomographic images acquired by performing tomosynthesis imaging for an object. A setting unit sets the displayed tomographic image as having been displayed.