AI-Driven Radiotherapy Planning Parameter Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current radiotherapy treatment planning systems require extensive time and computational resources to optimize treatment plans, as users must manually adjust multiple parameters to find optimal settings, often with little foresight into the impact of these adjustments on treatment quality criteria.
Innovation Solution
A computer-implemented method using Artificial Intelligence (AI) to predict the dependency of radiotherapy quality criteria on adjustments to planning parameters, streamlining the optimization process by identifying promising parameter settings before full optimization is performed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual adjustment of multiple planning parameters is performed to find optimal settings, then treatment plan optimization quality is improved, but time consumption and computational resources increase significantly
Solution Approach 1:
The AI model performs preliminary analysis of patient geometry data before the full optimization process, predicting which planning parameters will have significant impact on treatment quality criteria. This preliminary action allows users to focus manual adjustment efforts only on the most relevant parameters, avoiding time-consuming trial-and-error on parameters with minimal impact.
Solution Approach 2:
An AI-based intermediary system is introduced between the patient data input and the optimization process. This intermediary analyzes patient-specific geometry information and provides predictive guidance on parameter importance, acting as a mediator that streamlines the workflow between data acquisition and treatment plan generation.
2Measurement precision
If extensive parameter adjustments are made to explore all possible settings, then optimal treatment plan quality is improved, but computational resources required increase
Solution Approach 1:
The AI model identifies local regions in the parameter space that are most relevant for each specific patient case. Instead of uniformly exploring all parameter combinations, the system focuses computational efforts on locally important parameters determined by patient-specific geometry characteristics, thereby reducing overall computational resource requirements.
3Loss of information
If users manually try multiple slider positions to understand parameter impact, then understanding of parameter-criterion relationships is improved, but time required increases significantly
Solution Approach 1:
The AI system provides immediate feedback to users about the predicted impact of adjusting specific planning parameters on treatment quality criteria. Based on patient geometry analysis, the system informs users which parameters are most likely to influence outcomes, enabling informed decision-making without requiring extensive manual experimentation.
Data Source
AI summary
By using the Al module, the method of the present invention calculates, i.e. predicts, the dependency Ci (pi) of a radiotherapy (RT) quality criterion C, from an adjustment of such a radiotherapy planning parameter pi. In this way, the decision making process in RT treatment plan optimization is streamlined by prediction of promising settings of one or more radiotherapy planning parameters p, before the actual time intensive iterative optimization process is carried out. This is achieved by applying an Al module, which has been trained to predict the specific behaviour of the dose optimization algorithm, i.e. the optimizer, with respect to geometric patient data, dose prescription and treatment indication data. Thus, a computer-implemented medical method of predicting a dependency Ci (pi) of a radiotherapy (RT) quality criterion Ci from an adjustment of a radiotherapy planning parameter p, is presented. The method comprises the following steps of providing geometric patient data geometrically describing an area of a patient, which is to be irradiated according to a radiotherapy treatment plan (step S1), providing dose prescription data and treatment indication data for said patient (step S2), and predicting with a trained Artificial Intelligence (Al) module the dependency Ci (pi) of the radiotherapy quality criterion Ci from the radiotherapy planning parameter p, when adjusting said radiotherapy planning parameter pi, thereby using the geometric patient data, the dose prescription data and the treatment indication data as input for the Al module (step S3).