Automatic Image Selection for Contour Extraction in Diagnostic Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for radiation treatment planning require manual selection of images for contour creation, which can be operator-dependent and time-consuming, lacking an automated technique for selecting the optimal image from multiple types for accurate dose control.
Innovation Solution
A diagnostic imaging support apparatus and method that automatically selects an image for contour extraction based on image information, using a selection unit to determine the image with the largest gradient magnitude from a superimposed image of different types, such as CT, MR, and PET images, and extracts the contour using a contour extraction unit.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual selection of images for contour extraction is performed by operators, then flexibility in selecting appropriate images for different tumors and organs is maintained, but the process becomes time-consuming and operator-dependent with varying selection quality
Solution Approach 1:
The system performs automatic image selection for contour extraction without requiring operator intervention. The selection unit autonomously evaluates multiple images of different types and selects the most appropriate image based on image quality metrics, eliminating the time-consuming manual selection process while maintaining objective consistency in selection criteria
Solution Approach 2:
The system changes the selection criterion from subjective operator judgment to objective image quality parameters. By calculating image quality based on quantitative metrics such as gradient magnitude, contrast, and signal-to-noise ratio, the system objectively determines the best image for contour extraction, resolving the contradiction between manual flexibility and time efficiency
2Measurement precision
If multiple images of different types are used for contour extraction, then the accuracy of contour creation is improved, but the complexity of selecting and processing multiple images increases
Solution Approach 1:
The system extracts only the most suitable image from multiple images of different types for contour extraction. The selection unit identifies and extracts the single best image based on image quality metrics, simplifying the processing workflow while still leveraging the benefits of having multiple image types available for evaluation
Solution Approach 2:
The selection unit acts as an intermediary between the multiple available images and the contour extraction process. It evaluates all images using objective quality criteria and selects the optimal one, thereby managing the complexity of multiple images while ensuring the highest accuracy for contour creation
3Productivity
If automatic image selection based on image information is implemented, then the speed and consistency of image selection are improved, but the requirement for image processing algorithms and computational resources increases
Solution Approach 1:
The system replaces the mechanical/manual process of image selection with an automated computational system. Image processing algorithms automatically evaluate image quality metrics such as gradient magnitude and contrast, eliminating manual intervention and significantly increasing selection speed while maintaining objective consistency
Solution Approach 2:
The system performs self-evaluation of image quality using automated algorithms. The selection unit independently calculates image quality metrics and makes selection decisions without external intervention, achieving high-speed automated selection while managing computational requirements through efficient algorithm design
Data Source
AI summary
With a diagnostic imaging support apparatus, a diagnostic imaging support method, and a diagnostic imaging support program, an optimum image for extracting a contour can be automatically selected from a superimposed image obtained by superimposing a plurality of images of different types. A diagnostic imaging support apparatus 1 includes: an accepting unit 22 that accepts a specification of the position of a predetermined defined region R on a superimposed image G obtained by superimposing a plurality of images of different types including a target image G0 that is a target on which a contour is created; a selection unit 23 that selects an image for extracting a contour on the basis of image information about regions R0, R1, and R2, in the plurality of images of different types, each corresponding to the accepted defined region R; and a contour extraction unit 24 that extracts the contour from the selected image.