Machine Learning Radiotherapy Plan Optimization With Dynamic Medical Variables
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual radiation treatment planning is time-consuming and prone to human error, leading to inconsistent treatment plans and reduced accuracy.
Innovation Solution
A plan optimization method utilizing a computing apparatus and machine learning models to dynamically update medical parameters and adjust treatment manner records based on current medical variables, incorporating causal graph models and continuous time dynamic causal planning graphs to enhance accuracy and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated radiotherapy planning algorithms are used, then time required to develop treatment plan is reduced, but accuracy and reliability may be compromised
Solution Approach 1:
The system implements feedback mechanisms by continuously monitoring treatment outcomes and patient responses, then using this information to refine and update treatment plans. The machine learning model learns from historical data and adjusts parameters dynamically, creating a closed-loop system that improves accuracy while maintaining efficiency.
Solution Approach 2:
The patent employs dynamic treatment planning where parameters are not fixed but adapt over time based on patient response. The system allows for mid-course corrections and adjustments to treatment parameters, transforming static automated planning into a dynamic, responsive process that maintains high accuracy.
2Reliability
If manual radiation treatment planning is performed, then accuracy may be maintained, but time consumption increases and human error occurs
Solution Approach 1:
The system replaces manual mechanical planning processes with automated machine learning-based computational systems. The ML model processes medical images and patient data to generate treatment plans, substituting human manual work with automated algorithms that are both faster and increasingly accurate through continuous learning.
Solution Approach 2:
The system enables self-service automated planning where the machine learning model independently generates and optimizes treatment plans without requiring extensive manual intervention. The model self-corrects and self-improves through continuous learning from data, reducing both time consumption and human error.
3Ease of operation
If fixed treatment plans are used, then implementation is simple, but adaptability to changing patient conditions is reduced
Solution Approach 1:
The system transforms fixed treatment plans into dynamic adaptive plans that automatically adjust to changing patient conditions. The machine learning model continuously monitors patient response and modifies treatment parameters in real-time, maintaining both simplicity of operation through automation and high adaptability to changing conditions.
Solution Approach 2:
The system implements continuous feedback loops where treatment outcomes are monitored and fed back into the planning system. This allows the treatment plan to adapt automatically to changing patient conditions while maintaining operational simplicity through the automated nature of the feedback mechanism.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A plan optimization method, a computing apparatus (10) for optimizing the plan, and a computer-readable medium are provided. Obtain multiple medical variables at the current time, at least one of the medical variables is different from the medical variables at the previous time, and one of those medical variables at the current time corresponds to a previous state at the previous time. By inputting those medical variables at the current time into the machine learning model, plan information is determined, where the plan information includes at least one subplan information, and each piece of subplan information corresponds to at least one treatment manner record at a subsequent time. Therefore, it could improve the inference accuracy of the model.