Multi-Criteria Optimization for Radiation Therapy Planning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current radiation therapy treatment planning methods face challenges in effectively generating high-quality treatment plans using multi-criteria optimization (MCO) processes, particularly in balancing radiation dose distribution for tumors while minimizing damage to healthy tissues and organs at risk.

Innovation Solution

The method involves using a computer-implemented process that receives dose-distribution-derived functions, probability distributions, and a loss function to define a multi-criteria optimization problem. This process generates multiple output treatment plans by optimizing two or more objective functions based on these inputs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If multi-criteria optimization is used to generate treatment plans, then treatment plan quality and diversity are improved, but computational complexity and processing time increase

Engineering Contradiction:
Improvetreatment plan qualityVSAvoidoptimization process complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The optimization process is segmented into multiple independent objective functions, each evaluating a specific aspect of treatment plan quality (e.g., tumor dose coverage, organ-at-risk sparing, treatment time). This allows the complex MCO problem to be broken down into manageable components that can be optimized separately and combined to generate diverse treatment plan options

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension to the optimization process by incorporating probability distributions that represent uncertainty and variability in treatment outcomes. This adds a probabilistic dimension to the traditional deterministic optimization, enabling the system to generate treatment plans that account for real-world variability while maintaining computational tractability

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Adaptability or versatility

If multiple objective functions are used in MCO, then treatment plan options and clinical relevance are improved, but computation time and processing resources increase

Engineering Contradiction:
Improvetreatment plan optionsVSAvoidcomputation time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by pre-defining and pre-calculating the objective functions and their weights based on clinical guidelines and patient-specific factors. This preparation allows the actual optimization process to proceed more efficiently, as the framework is already in place and only requires inputting specific patient parameters and solving the optimization problem

Inventive Principle:
Principle #10Preliminary action

3Reliability

If probability distributions are used to represent knowledge from historic treatment plans, then treatment plan reliability is improved, but data processing complexity increases

Engineering Contradiction:
Improvetreatment plan reliabilityVSAvoiddata processing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent uses probability distributions to create a probabilistic copy or representation of historic treatment plan data rather than directly processing the raw historical data. This transformation into probability distributions simplifies the data processing by capturing essential statistical characteristics (mean, variance, skewness) while discarding unnecessary details, thereby reducing processing complexity while maintaining reliability

Inventive Principle:
Principle #26Copying

Data Source

PatentEP3919123B1Radiation therapy treatment planning
Publication Date: 2025.01.22 RAYSEARCH LAB
  • EP3919123B1 patent drawingFigure 1~3
  • EP3919123B1 patent drawingFigure 4~5
  • EP3919123B1 patent drawing

AI summary

A computer-implemented method for generating a radiation therapy treatment plan for a volume of a patient, the method comprising: receiving an image of the volume; receiving at least one dose-distribution-derived function configured to provide a value as an output based on, as input, at least part of a dose distribution defined relative to said image; receiving a first probability distribution and at least a second, different, probability distribution, the first and at least second probability distributions; defining a multi-criteria optimization problem comprising at least a first objective function based on the at least one dose-distribution-derived function, the first probability distribution and a loss function; and a second objective function based on the at least one dose-distribution-derived function, the second probability distribution and the loss function; and performing a multi-criteria optimization process based on said at least two objective functions to generate at least two output treatment plans.