Anatomy Contouring via Structured Click Points and Self-Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional contouring techniques in medical imaging, both manual and intelligent, are inefficient and often fail to converge accurately, requiring numerous user inputs and being time-consuming.
Innovation Solution
A computer-implemented method using structured user click points to generate contours, where the contour inference algorithm updates in real-time based on user input, allowing users to confirm accuracy with visual indicators and fix segments, ensuring convergence and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional click-point based contouring techniques are used, then precise contouring can be achieved, but the number of user inputs required increases significantly making the process time-consuming
Solution Approach 1:
The system performs self-correction by automatically detecting and fixing contour leakages without requiring additional user inputs. The contouring algorithm continuously monitors its own accuracy and autonomously repairs errors, reducing the need for extensive manual verification and correction by the user.
Solution Approach 2:
The system implements feedback mechanisms where the contouring algorithm continuously evaluates the accuracy of generated contours against the medical image data, and uses this feedback to iteratively improve contour precision. User confirmations provide additional feedback loops that refine the contouring results.
2Productivity
If intelligent contouring algorithms are used with limited user inputs, then processing speed improves, but the algorithm may fail to converge to accurate contours
Solution Approach 1:
The system performs preliminary actions by pre-processing the medical image data to enhance relevant features and pre-identifying potential contour regions before the main contouring process begins. This preliminary preparation enables the algorithm to converge more accurately with fewer user inputs.
Solution Approach 2:
The contouring algorithm autonomously monitors its own convergence status and automatically performs corrections when accuracy thresholds are not met, without requiring additional user inputs. This self-service capability ensures accurate convergence while maintaining high efficiency.
3Manufacturing precision
If more user inputs are provided to intelligent editing, then contour accuracy may improve, but editing efficiency decreases due to increased interaction requirements
Solution Approach 1:
The system automatically detects contour inaccuracies and performs corrections without requiring users to provide additional inputs for each correction. The self-service mechanism maintains high contour accuracy while preserving editing efficiency by eliminating redundant user interactions.
Solution Approach 2:
The system implements automated feedback loops that continuously evaluate contour accuracy and trigger corrections only when necessary. This feedback mechanism ensures high accuracy while maintaining efficiency by avoiding unnecessary user interactions and processing steps.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A computer-implemented method for generating contours of anatomy based on user click points includes a computer displaying an image comprising an anatomical structure and receiving a first user selection of a first click point at a first position on an outward facing edge of the anatomical structure. The computer applies a contour inference algorithm to generate an inferred contour around the outward facing edge based on the first position. Following generation of the inferred contour, the computer receives a second user selection of a second click point at a second position on the image. Then, the computer creates a visual indicator on a segment of the inferred contour between the first position and the second position as indicative of the user's confirmation of accuracy of the segment.