Automated Radiation Therapy Planning Using Multi-Parametric Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The current radiation therapy treatment planning process is time-consuming and prone to variability due to manual delineation of tumors and organs at risk, leading to potential underdosing or overdosing, especially with multiple organs at risk, and may not adhere to the latest medical standards.
Innovation Solution
A system that uses multi-parametric input data and machine learning techniques to recommend or select a treatment modality by generating metrics for different treatment modalities, allowing for automated selection and configuration of treatment parameters based on patient-specific data, ensuring standardized and efficient treatment planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual delineation of tumors and organs at risk is used, then treatment planning can be performed, but the process is time-consuming and prone to variability
Solution Approach 1:
The system enables automated self-service treatment planning by using machine learning models to automatically delineate tumors and organs at risk, eliminating the need for manual contouring while maintaining or improving accuracy. The automated system processes patient data and generates treatment plans independently, significantly reducing planning time and variability.
Solution Approach 2:
The patent replaces the manual mechanical process of physician delineation with an automated computational system using machine learning algorithms. This substitution transforms the treatment planning from a manual, time-consuming task to an automated, efficient process that reduces variability and improves consistency.
2Adaptability or versatility
If multiple organs at risk are present, then treatment complexity increases, but manual planning becomes even more time-consuming and error-prone
Solution Approach 1:
The system changes the parameters of the planning process by using machine learning models that can simultaneously process and analyze multiple organs at risk. The automated system adjusts dosimetric parameters and treatment constraints for each OAR efficiently, handling complex scenarios without proportionally increasing planning time or errors.
3Ease of operation
If manual treatment planning is used, then flexibility in customization is maintained, but adherence to medical standards and consistency are compromised
Solution Approach 1:
The system incorporates feedback mechanisms where machine learning models are trained on established medical standards and guidelines. The automated planning process continuously references these standards, providing feedback to ensure compliance while maintaining consistency. The system can also provide feedback to physicians for review and adjustment when needed.
Data Source
AI summary
Systems and methods are disclosed for performing operations comprising: receiving multi-parametric input data representing data associated with a patient; receiving an indication of a disease associated with the patient; processing the multi-parametric input data to generate one or more metrics corresponding to a plurality of different modalities for treating the disease associated with the patient; selecting, based on the one or more metrics, a given modality from the plurality of different modalities to treat the disease associated with the patient; and configuring parameters of the given modality based on a portion of the multi-parametric input data.