Radiotherapy Treatment Planning with Relaxed Objective Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The generation of radiation treatment plans in radiotherapy is time-consuming and complex, particularly when multiple treatment-planning objectives are involved, leading to variable results based on user input and prolonged processing times.
Innovation Solution
A method and system that employs an optimisation procedure with a first pass to achieve a solution and, if it does not meet the reference objective, applies a relaxation value to obtain a relaxed objective, which is then used to determine the radiotherapy system configuration, reducing the need for further user input and improving convergence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple treatment-planning objectives are involved in radiation treatment planning, then the quality and reliability of the treatment plan is improved, but the time required for plan generation increases and the process becomes more complex
Solution Approach 1:
The treatment planning process is segmented into multiple passes (first pass optimization, second pass optimization) where different objectives are addressed in sequence. This allows the system to handle multiple treatment-planning objectives systematically without requiring all objectives to be processed simultaneously, thereby reducing overall computation time while maintaining plan quality.
Solution Approach 2:
The first pass optimization performs preliminary action by optimizing certain parameters and objectives before the second pass optimization. This preliminary optimization establishes a baseline solution that reduces the complexity of subsequent optimization steps, enabling faster convergence when multiple objectives are involved.
2Reliability
If multiple treatment-planning objectives are involved in radiation treatment planning, then the quality and reliability of the treatment plan is improved, but the complexity of the optimization process increases
Solution Approach 1:
The optimization process is segmented into distinct passes with specific focuses. The first pass optimization handles initial parameter optimization, while the second pass optimization refines the solution for remaining objectives. This segmentation reduces the complexity of each individual optimization step compared to handling all objectives simultaneously.
Solution Approach 2:
The system dynamically adjusts the optimization approach by using different relaxation values in different passes. The relaxation value is adjusted based on the convergence status and objective priorities, allowing the system to adaptively manage the complexity of the optimization process while maintaining reliability.
3Adaptability or versatility
If user input is required for treatment plan generation, then the adaptability and customization of the plan is improved, but the time required for plan generation increases
Solution Approach 1:
The system performs self-service by automatically adjusting relaxation values and proceeding through multiple optimization passes without requiring continuous user intervention. The treatment planning system autonomously handles the optimization process, reducing the time users need to spend on manual adjustments while maintaining the ability to customize plans through initial parameter settings.
Solution Approach 2:
The system automatically changes parameters such as relaxation values between optimization passes to improve convergence and handle different objectives. This automatic parameter adjustment reduces the need for user input while maintaining adaptability, as the system dynamically optimizes parameters based on the treatment planning objectives and convergence status.
4Reliability
If relaxation value is applied to obtain relaxed objective, then the convergence of optimization procedure is improved, but the number of iterations required may increase
Solution Approach 1:
The system applies relaxation values partially, only when needed to improve convergence. By using relaxation selectively in the optimization process rather than always applying maximum relaxation, the system maintains optimization speed while improving convergence reliability when necessary.
Solution Approach 2:
The relaxation value is dynamically changed between optimization passes and adjusted based on convergence status. This parameter change allows the system to balance convergence reliability and optimization speed by using stronger relaxation only when convergence difficulties arise, rather than applying fixed relaxation throughout the process.
Data Source
AI summary
A method for radiation treatment planning for delivering radiation therapy by a radiotherapy system, the method comprising: receiving a reference objective, the reference objective representing a goal to be achieved by the radiotherapy system; performing an optimisation procedure, according to the received reference objective, to determine a set of parameters, the set of parameters relating to characteristics of radiation to be delivered by the radiotherapy system, wherein the optimisation procedure comprises: optimising the set of parameters to obtain an achieved value, and responsive to the achieved value not meeting the reference objective, obtaining a relaxed objective using the achieved value and a relaxation value, and determining a configuration of the radiotherapy system using the optimised set of parameters and the relaxed objective.