Deformation Vector Field Correction for Contour Propagation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In fractionated radiation therapy, manual and semi-automated contouring processes for tumor and critical structure delineation in IMRT are prone to errors and do not accurately account for changes over time, leading to potential misalignment of radiation beams and increased exposure to healthy tissues.
Innovation Solution
An automated method involving the computation of a deformation vector field (DVF) for spatial registration of planning and treatment images, with user correction capabilities that allow feedback to refine the DVF, ensuring accurate contour propagation and radiation therapy planning adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated contour propagation using non-rigid registration is employed, then productivity is improved, but manufacturing precision deteriorates due to errors in contour accuracy
Solution Approach 1:
The system implements feedback by detecting contour errors through comparison with reference contours and correcting the deformation vector field (DVF) based on these errors. The correction process uses the detected errors to refine the DVF, which then improves the accuracy of contour propagation while maintaining automated efficiency.
2Manufacturing precision
If manual contour correction is performed, then manufacturing precision is improved, but productivity deteriorates due to intensive manual work
Solution Approach 1:
The system introduces an intermediary automated correction mechanism that acts as a mediator between manual contouring and final contour propagation. The correction system automatically detects errors and adjusts the DVF without requiring manual intervention for each correction, thereby maintaining high precision while improving productivity.
3Adaptability or versatility
If non-rigid spatial registration is used for treatment images, then adaptability is improved to account for organ changes, but device complexity increases
Solution Approach 1:
The system changes parameters of the deformation vector field to adapt to anatomical variations between planning and treatment images. By adjusting DVF parameters based on detected contour errors, the system achieves adaptability to organ changes while managing complexity through automated parameter optimization rather than complex manual registration procedures.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Adeformation vector field (DVF) (22)is computed that relatively spatially registers a first image (16)and a second image (14). A contour (26)delineating a structure in the first image is adapted using the DVF to generate an initial contour (52)for the structure in the second image. A final contour (56)is received for the structure in the second image. The DVF is corrected based on the initial and final contours for the structure in the second image to generate a corrected DVF (32).The correction may comprise computing an adjustment DVF (62)relating the initial and final contoursand combining the DVF and the adjustment DVF to generate the corrected DVF.The final contour may be received by displaying the second image overlaid with the initial contour, and receiving user adjustments of the overlaid contour withthe overlaid contour updated for each received user adjustment.