Radiotherapy Arc Sequencing With ML Aperture Refinement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current radiation therapy treatment planning is time-consuming and subjective, often requiring trial-and-error processes to balance target dose and organ-at-risk sparing, with existing methods struggling to efficiently generate high-quality treatment plans that minimize dose to surrounding tissues.
Innovation Solution
The use of a trained machine learning model, such as a neural network, to generate control point images and optimize radiotherapy treatment plans by predicting control point values based on patient anatomy and fluence data, reducing the complexity of arc sequencing and aperture optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional trial-and-error methods are used to create treatment plans, then planners can manually adjust parameters to meet clinical objectives, but the process becomes extremely time-consuming and complex especially when multiple organs at risk are involved
Solution Approach 1:
The patent replaces the manual mechanical trial-and-error adjustment process with an automated machine learning system. The neural network model automatically generates control point values and optimizes treatment plans based on input imaging data, eliminating the need for manual parameter tuning while maintaining or improving plan quality.
Solution Approach 2:
The system enables self-service treatment planning where the machine learning model autonomously generates and optimizes treatment plans without requiring continuous human intervention. The model learns from training data and independently performs the complex optimization task that traditionally required skilled planners to manually adjust parameters over extended periods.
2Adaptability or versatility
If manual delineation and optimization techniques are used, then treatment plans can be customized for individual patients, but the complexity increases significantly with more organs at risk
Solution Approach 1:
The patent changes the fundamental parameters of the treatment planning process by using a machine learning model that directly predicts optimal control point values from imaging data. This approach maintains the ability to customize treatment plans for individual patients while avoiding the exponential complexity increase that occurs with manual methods when multiple organs at risk are involved.
3Ease of manufacture
If conventional arc sequencing and aperture optimization methods are used, then treatment plans can be generated, but the process lacks objectivity and consistency
Solution Approach 1:
The patent implements feedback through the machine learning model that has been trained on extensive treatment plan data. The model learns from historical successful plans and applies this knowledge to generate consistent, high-quality plans for new patients. This feedback mechanism ensures objectivity and reliability by base d on proven patterns rather than subjective manual judgment.
Data Source
AI summary
Systems and methods are disclosed for generating radiotherapy machine parameters used in a radiotherapy treatment plan, based on machine learning prediction. The systems and methods include: obtaining three-dimensional image data which indicates target dose areas and organs-at-risk areas of a subject; generating anatomy projection images from the image data, each anatomy projection image providing a view from a respective beam angle of the radiotherapy treatment; using a trained neural network model (trained with corresponding pairs of anatomy projection images and control point images) to generate control point images, each control point image indicating an intensity and aperture(s) of a control point of the radiotherapy treatment to apply at a respective beam angle; and generating a set of final control points for use in the radiotherapy treatment to control a radiotherapy treatment machine, based on optimization of the control points indicated by the generated control point images.