Radiation Therapy Plan Generation Using Image Registration Offsets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current radiation therapy treatment plans are often time-consuming to create, as they require positioning images to be acquired after the patient is positioned, which can lead to inaccuracies due to potential changes in the tumor or organ positions during the treatment stage.
Innovation Solution
A method that generates a treatment plan based on a diagnostic image without positioning information, followed by registration with a positioning image acquired during the treatment stage, updating the plan with rotation and translation offsets to ensure accurate targeting of the tumor or organ at risk.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If a treatment plan is generated based on a diagnostic image without positioning information, then the time needed to create the treatment plan is reduced, but the accuracy of tumor targeting may deteriorate due to potential changes in tumor or organ positions during treatment
Solution Approach 1:
The patent applies preliminary action by generating the treatment plan based on the diagnostic image before acquiring the positioning image. The treatment plan is prepared in advance using available diagnostic data, and then updated after positioning image acquisition to account for any position changes. This allows the planning process to start earlier without compromising final accuracy.
Solution Approach 2:
The patent implements feedback by acquiring the positioning image after the treatment plan is initially generated, comparing the positioning image with the diagnostic image, and updating the treatment plan based on the registration results. This feedback loop ensures that any position changes detected during the treatment stage are incorporated into the final treatment plan, maintaining targeting accuracy.
2Measurement precision
If positioning images are acquired after the patient is positioned, then the treatment plan can be updated with accurate positioning information, but the overall treatment process time increases
Solution Approach 1:
The patent applies preliminary action by generating the initial treatment plan before acquiring the positioning image. This allows the treatment planning to start in advance using diagnostic images, and then be updated later with positioning information from CBCT or other imaging modalities. The preliminary plan generation avoids waiting for positioning images to be acquired before starting the planning process.
Solution Approach 2:
The patent segments the treatment plan generation process into two distinct stages: initial plan generation based on diagnostic images, and subsequent plan update based on positioning images. This segmentation allows the time-consuming positioning image acquisition and registration process to be separated from the initial planning phase, enabling parallel processing and reducing overall workflow time.
3Manufacturing precision
If the treatment plan is updated using registration results with rotation and translation offsets, then the precision of radiation delivery is improved, but the complexity of the treatment planning process increases
Solution Approach 1:
The patent uses registration software as an intermediary tool that automatically processes the positioning image, diagnostic image, and treatment plan. The registration software handles the complex tasks of image alignment, rotation offset calculation, and translation offset determination, reducing the manual complexity of the planning process while maintaining high precision in radiation delivery.
Solution Approach 2:
The patent applies parameter changes by automatically adjusting treatment plan parameters (such as beam angles, isocenter positions, and field sizes) based on the registration results. The system transforms the treatment plan parameters according to the detected rotation and translation offsets, enabling precise radiation delivery without requiring manual re-planning by the physicist.
Data Source
AI summary
The present disclosure discloses a method for generating a treatment plan. The method includes: acquiring a first image of a target object, wherein the first image does not contain positioning information of the target object; generating a first treatment plan for the target object based on the first image; acquiring a second image of the target object, wherein the second image contains the positioning information of the target object; registering the first image and the second image; and generating a second treatment plan by updating the first treatment plan in response to a registration result.


