Robust Dose Mimicking for Radiotherapy Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated radiotherapy treatment planning is sensitive to poor input data quality and has limited ability to absorb and utilize errors in patient data, leading to suboptimal treatment delivery when patient position changes significantly between imaging and treatment.
Innovation Solution
A method that includes a dose inference stage followed by a robust optimization process in the dose mimicking stage, which considers multiple uncertainty scenarios related to patient data uncertainties, ensuring the treatment plan is consistent with the inferred spatial dose and robust to data errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated treatment planning is used to reduce manual effort, then planning efficiency is improved, but sensitivity to poor input data quality increases
Solution Approach 1:
The system performs preliminary actions by generating multiple uncertainty scenarios and computing robust treatment plans that account for potential data errors before actual treatment delivery. This proactive approach ensures the plan remains effective even if input data quality deteriorates during treatment.
Solution Approach 2:
The system applies beforehand cushioning by incorporating margin scenarios and uncertainty buffers into the treatment plan optimization. These pre-computed cushions protect against data quality fluctuations without requiring manual intervention during treatment delivery.
2Reliability
If margin-based error handling is used to ensure robustness, then reliability is improved, but total dose to patient increases
Solution Approach 1:
The system changes parameters by optimizing treatment plans across multiple uncertainty scenarios simultaneously, adjusting beam angles, intensities, and timing to maintain robustness while minimizing total dose. This parameter optimization replaces crude margin-based approaches with precise, scenario-aware control.
Solution Approach 2:
The system applies dynamics by making the treatment plan adaptive to different uncertainty scenarios. The optimized plan dynamically adjusts delivery parameters based on pre-computed scenario analyses, ensuring robustness without static dose escalation.
3Reliability
If straightforward margin-based error handling is applied, then robustness is improved, but treatment plan precision deteriorates
Solution Approach 1:
The system changes parameters by optimizing multiple treatment parameters simultaneously across uncertainty scenarios, replacing single-parameter margin adjustments with multi-parameter optimization that maintains both robustness and precision.
Solution Approach 2:
The system applies feedback by using pre-computed scenario outcomes to refine and optimize the treatment plan. This feedback loop ensures that robustness measures do not compromise dose delivery precision to targets and organs-at-risk.
Data Source
AI summary
A method (100) for generating a treatment plan specifying an irradiation of a patient, the method comprising: a dose inference stage (112), including using a model to infer a spatial dose from patient data; a dose mimicking stage (116), including executing a robust optimization process to generate a deliverable treatment plan which is consistent with the inferred spatial dose, wherein the robust optimization considers a plurality of scenarios relating to patient data uncertainty.