Radiotherapy Dose-Volume Histogram Optimization Using Quantile Regression

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current radiotherapy treatment planning is time-consuming and complex due to the combinatorial nature of dose-volume histogram (DVH) criteria, which are not continuously differentiable and require approximate convex re-formulations, leading to long solution times and suboptimal treatment plans.

Innovation Solution

The use of quantile-based optimization formulation to express dose-volume criteria as inequalities in a nested optimization problem, allowing for improved DVH modeling, computational speed, and accuracy in radiation treatment planning.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional offline treatment planning with manual delineation and optimization is used, then treatment plans can be generated with clinical acceptability, but the process is time-consuming and complex

Engineering Contradiction:

Improveclinical acceptability of treatment planVSAvoidtreatment planning time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical delineation and optimization processes with automated computer-based systems. The system automatically delineates target volumes and OARs from imaging data, and uses automated optimization algorithms to generate treatment plans, eliminating the time-consuming manual trial-and-error process while maintaining clinical acceptability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The treatment planning system performs self-service by automatically processing imaging data to generate treatment plans without requiring continuous manual intervention. The automated system handles delineation, optimization, and plan generation independently, reducing planner workload and planning time

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If the number of organs at risk (OARs) increases, then treatment plan complexity increases, but this makes it more difficult to spare OARs from radiation

Engineering Contradiction:

Improveability to handle multiple OARsVSAvoidtreatment plan complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the treatment planning process into distinct automated components: imaging data processing, target volume delineation, OAR delineation, and optimization. This segmentation allows the system to handle multiple OARs systematically by processing each independently through automated algorithms, reducing the complexity burden of having numerous organs to protect

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system changes the approach from manual parameter adjustment to automated parameter optimization. By using computational algorithms to automatically adjust treatment parameters for multiple OARs simultaneously, the system manages complexity through mathematical optimization rather than manual trial-and-error

Inventive Principle:

Principle #35Parameter changes

3Ease of manufacture

If approximate convex re-formulations are used for DVH criteria, then optimization can be performed, but solution times are prolonged and accuracy is reduced

Engineering Contradiction:

Improveoptimization feasibilityVSAvoidtreatment plan accuracy

Core Design Contradiction:

Ease of manufactureVSManufacturing precision

Solution Approach 1:

The patent replaces approximate mathematical re-formulations with exact optimization methods. The system uses precise algorithms that directly handle DVH criteria without requiring convex approximations, maintaining treatment plan accuracy while achieving computational efficiency through modern optimization techniques

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Reliability

If traditional optimization techniques are used for DVH criteria, then treatment plans can be generated, but the combinatorial nature leads to long solution times

Engineering Contradiction:

Improvetreatment plan qualityVSAvoidplan generation speed

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent substitutes traditional combinatorial optimization approaches with modern computational optimization algorithms. The system uses efficient mathematical programming techniques that avoid the exponential complexity of traditional methods, achieving both high treatment plan quality and fast generation speeds through algorithmic innovation

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12458815B2Dose volume histogram optimization based on quantile regression

Publication Date: 2025.11.04 ELEKTA INSTRUMENT AB

AI summary

Dose-volume criteria may be equivalently expressed in terms of quantiles. This re-formulation of a dose-volume criteria allows incorporation of dose-volume criteria into a full optimization problem. Radiotherapy treatment techniques are described that may apply optimization-based formulation of quantiles to express dose-volume criterion as an inequality involving an optimization problem, which may improve DVH modeling, improve computational speed and accuracy of radiation treatment planning, and improve the delivery accuracy and efficacy of radiation doses to a patient undergoing radiotherapy treatment.