Shape-Based Initialization for Progressive Radiation Therapy Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current radiation therapy planning is time-consuming and labor-intensive, particularly in automating intensity-modulated radiation therapy (IMRT) and volumetric-modulated arc therapy (VMAT) optimization, due to the lack of tools for writing logical expressions and loops, and the subjective nature of defining optimal plans which results in excessive user flexibility and complexity.
Innovation Solution
A computer-implemented method using shape-based optimization parameters with progressive tuning to capture trade-offs and drive optimization parameters to their limits, reducing the need for general optimization goals and providing fast plan generation and quality assurance, by integrating shape-based DVH predictions and machine learning algorithms to generate optimal radiation treatment plans.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual radiation therapy planning is used, then plan quality can be customized for each patient, but the process is time-consuming and labor-intensive
Solution Approach 1:
The system performs preliminary actions by pre-calculating and storing optimal beam arrangements, dose distributions, and treatment parameters in a database from previous treatment plans. When creating a new plan, the system retrieves and adapts these pre-computed parameters, eliminating the need to perform all calculations from scratch and significantly reducing planning time while maintaining quality.
Solution Approach 2:
The system creates copies of previously successful treatment plans and their associated parameters. By copying proven beam arrangements, dose distributions, and optimization settings from the database, the system provides a fast starting point for new plans that can be quickly adapted to patient-specific anatomy, reducing both time and manual effort.
2Productivity
If automation tools are introduced, then planning time is reduced, but the ability to handle complex logical expressions and loops is limited
Solution Approach 1:
The system introduces an intermediary component - a database storing structured treatment plan parameters and optimization data - that bridges the gap between automated plan generation and complex clinical requirements. This intermediary allows the system to retrieve and adapt pre-computed parameters without needing complex programming logic, while still achieving high productivity through efficient parameter retrieval and adaptation.
3Adaptability or versatility
If user flexibility is increased to define optimal plans, then plan customization is improved, but system complexity increases
Solution Approach 1:
The system manages complexity by organizing treatment plan parameters into structured categories (beam arrangements, dose distributions, optimization settings) stored in the database. Users can customize plans by selecting and modifying specific parameters from predefined options, rather than dealing with unstructured system complexity. This parameter-based approach maintains flexibility while controlling system complexity through structured data organization.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system and method for automatically generating radiation therapy treatment plans including one or more processors configured to capture geometries of organs at risk and a target volume specific to a subject, and use a shape-based algorithm to mine (152) a knowledgbase (38) of previously constructed treatment plans for similar geometries to the subject. The system and method interfaces (154) dosimetric information from a plan with a similar geometry as a patient specific starting point for a progressive tuning optimization algorithm resulting in fewer iterations. The progressive tuning algorithm (156, 158, 162) generates an optimized treatment plan. The optimized plan is evaluated against treatment goals. Trade-off plans are generated (164) to create alternative plans according to unmet treatment goals.