Radiotherapy Planning Using Statistical Tumor Probability Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current manual methods for determining radiotherapy treatment plans are cumbersome and prone to errors, particularly in identifying and treating unidentified tumor tissue, as they do not consider the probability of tumor occurrence in unrepresented body regions.
Innovation Solution
A data processing method using a computer to determine a radiotherapy treatment plan by combining medical image data with statistical models of tumor distribution from multiple patients, allowing for the identification of irradiation regions and doses based on probability maps, and integrating these with patient-specific medical image data to create a precise treatment plan.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual determination of treatment plans is used, then flexibility in handling individual medical cases is maintained, but reliability and completeness of tumor identification deteriorate
Solution Approach 1:
The patent introduces statistical models and probability maps as intermediary tools between the user and the treatment planning process. These models, derived from population data, serve as mediators that automatically highlight high-probability tumor regions, reducing reliance on manual identification while maintaining system usability. The intermediary processing layer combines automated analysis with user oversight, resolving the contradiction between reliability improvement and system complexity.
2Reliability
If manual treatment planning is used, then treatment customization for individual cases is achieved, but errors and omissions in identifying all tumor regions increase
Solution Approach 1:
The patent applies preliminary action by pre-computing statistical models and probability maps from population data before individual treatment planning. These pre-established models contain accumulated knowledge about tumor distribution patterns, which are then rapidly applied to individual patient cases. This preliminary preparation reduces the time required for accurate tumor identification in each case, as the system doesn't need to analyze all possible tumor patterns from scratch for each patient.
Solution Approach 2:
The patent uses copying by transferring statistical patterns and probability distributions from population data to individual patient images. The probability maps, derived from analyzing multiple cases, are copied and applied to highlight likely tumor regions in the current patient's imaging data. This copying approach allows rapid identification of tumor regions without requiring manual analysis of every possible tumor presentation, thereby reducing planning time while maintaining accuracy.
3Measurement precision
If population-based statistical models are integrated, then identification of unidentified tumor tissue improves, but data processing complexity increases
Solution Approach 1:
The patent applies local quality by focusing the statistical model analysis on specific high-probability regions rather than uniformly processing the entire imaging dataset. The probability maps identify and highlight only those regions with elevated tumor likelihood, allowing the system to concentrate processing resources on critical areas. This localized approach improves measurement precision for tumor location while reducing overall data processing complexity by avoiding exhaustive analysis of all image regions.
Data Source
AI summary
The invention relates to a method of determining a radiotherapy treatment plan for radiotherapy treatment of a treatment body part of a patient's body. The method can include acquiring treatment target position data comprising treatment target position information describing the position of a treatment target to be treated by radiotherapy in the treatment body part. Statistic model target region position data is acquired, which describes the position of a model target region in a model body part corresponding to the treatment body part. Based on the treatment target data and the statistic model target region position data, irradiation region position data is determined that describes the position of an irradiation region to be treated by irradiation with treatment radiation in the treatment body part.