Radiotherapy Image Contouring with Adaptive Layer Propagation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The current methods for target volume contouring in radiotherapy are time-consuming and require significant manual effort, especially when dealing with a large number of image layers, necessitating frequent manual fine corrections.
Innovation Solution
An image contouring method and system that automatically and adaptively adjusts contourings of other image layers when a user contours a certain image layer or modifies a contouring of that layer, utilizing reference contouring information to determine target contourings in adjacent slices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automatic target volume segmentation algorithms are used, then the workload of physicians is reduced, but the segmentation results still require further modification and supplementation
Solution Approach 1:
The system implements feedback by detecting user modifications to contouring results and automatically propagating these corrections to other image layers. When a physician modifies the segmentation result on one layer, the system captures this correction and uses it to adjust corresponding regions in adjacent layers, creating a closed-loop system that continuously improves accuracy based on user input.
Solution Approach 2:
The system performs preliminary action by pre-processing the propagation of contouring information across layers. It establishes the spatial relationships and anatomical correspondences between layers in advance, so that when user modifications are made, the system can quickly and automatically apply these corrections to relevant layers without requiring manual intervention on each layer individually.
2Manufacturing precision
If manual fine corrections are performed on each image layer, then the accuracy of contouring is improved, but a lot of time and effort is required
Solution Approach 1:
The system segments the contouring task by layer while maintaining inter-layer connections. Instead of requiring physicians to manually correct every layer independently, the system divides the work into individual layer corrections that can be made separately, while automatically propagating these corrections across the stack of layers. This segmentation approach reduces the total time required while maintaining accuracy.
Solution Approach 2:
The system uses copying by automatically replicating user-made corrections from one image layer to corresponding regions in other layers. When a physician makes a fine correction on one layer, the system copies this correction to anatomically corresponding regions in adjacent layers, eliminating the need to manually repeat the same correction multiple times and significantly reducing time consumption.
3Manufacturing precision
If contouring is performed layer by layer, then the precision of each layer is maintained, but the overall process becomes tedious and time-consuming
Solution Approach 1:
The system merges the individual layer contouring tasks by automatically integrating corrections made on one layer with the contouring results of other layers. Instead of treating each layer as an independent manual task, the system combines them into a unified process where corrections propagate automatically across layers, maintaining precision while simplifying the operational workflow.
Solution Approach 2:
The system implements self-service by automatically adjusting and propagating contouring corrections without requiring continuous manual intervention. Once a user makes a correction on one layer, the system autonomously applies this correction to other layers, making the system serve itself rather than requiring the physician to manually adjust every layer, thus improving ease of operation while maintaining precision.
Data Source
AI summary
The embodiments of the present specification provide an image contouring method and system, and a computer-readable storage medium. The method includes: obtaining a three-dimensional image, the three-dimensional image including a plurality of slice images arranged in sequence; obtaining reference contouring information in a first slice image among the plurality of slice images; and determining, based on the reference contouring information, a target contouring in a second slice image among the plurality of slice images, the second slice image being adjacent to the first slice image.