Adaptive Contouring Apparatus for Radiotherapy Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In radiotherapy treatment planning, users often need to manually modify automated segmentations of body parts, which is tedious and inefficient, as these modifications are not retained or reproducible across sessions or patients.
Innovation Solution
An apparatus and method for adaptive contouring that uses model-based segmentation to store and apply user modifications as deviations from the initial automatic segmentation, allowing for automatic regeneration of modified segmentations in subsequent sessions or for different patients, thereby incorporating user-specific and patient-specific requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated segmentation is used for body parts, then productivity is improved, but manufacturing precision deteriorates due to the need for manual modifications
Solution Approach 1:
The system automatically incorporates user modifications into the segmentation model by computing deviations between manual edits and automated results, then applies these corrections in subsequent segmentations without requiring repeated manual input, enabling the system to self-improve its precision
Solution Approach 2:
User modifications and deviations are captured and stored during the first segmentation session, then automatically applied in advance to subsequent segmentation operations, eliminating the need for repeated manual adjustments and maintaining high precision across multiple sessions
2Manufacturing precision
If manual modifications are made to automated segmentation, then manufacturing precision is improved, but loss of time increases due to repeated manual work
Solution Approach 1:
The system creates a digital copy of user modifications by computing deviation maps that represent the difference between automated and manual segmentation results, then applies these copied deviations to future segmentations, eliminating the need to repeat manual modification work
Solution Approach 2:
Modifications are performed once during an initial segmentation session, and the resulting deviation information is stored and automatically applied in advance to subsequent sessions, preventing the need for repeated manual work and saving time
3Adaptability or versatility
If user modifications are not propagated across sessions, then device complexity is reduced, but adaptability deteriorates as user-specific requirements cannot be retained
Solution Approach 1:
The system modifies the segmentation model by incorporating deviation parameters that quantify the difference between automated and manual results, then applies these parameter changes in subsequent segmentations to maintain user-specific preferences without requiring complex system reconfiguration
Solution Approach 2:
The system implements a feedback loop where user modifications are captured, analyzed as deviations, and automatically fed back into the segmentation process for subsequent sessions, enabling the system to adapt to user preferences while maintaining a relatively simple architecture
Data Source
Figure 1~2
Figure 3
Figure 4a~5c
AI summary
The present invention relates to an apparatus for adaptive contouring of a body part. It is described to provide (210) at least one image; wherein, the at least one image comprises a first image comprising image data of a body part. An initial automatic model based segmentation of image data of the body part in the first image is determined (220). Final segmentation data of the body part is determined (230) in response to a modification of the initial automatic model based segmentation. An updated model based segmentation can be applied (240) on the basis of the initial automatic model based segmentation and the final segmentation data.