EP-4741004-A1 - UTILITY FUNCTIONS IN RADIATION TREATMENT PLANNING

EP4741004A1EP 4741004 A1EP4741004 A1EP 4741004A1EP-4741004-A1

Abstract

A method (300) for computer-assisted radiation therapy treatment planning, comprising: receiving (310) a desired baseline dose distribution based on dose distributions used in radiation therapy treatment planning for one or more past patients that are similar to a new patient; receiving or defining (320) a set of clinical goals; using the baseline dose distribution to calibrate (340) a utility function or cost function based on the set of clinical goals; and using the utility function or cost function to optimise (350) a treatment plan.

Inventors

KUUSELA, ESA
PELTOLA, JARKKO

Assignees

Siemens Healthineers International AG

Dates

Publication Date: 20260513
Application Date: 20241111

Claims (15)

A method for computer-assisted radiation therapy treatment planning, comprising: receiving a desired baseline dose distribution based on dose distributions used in radiation therapy treatment planning for one or more past patients that are similar to a new patient; receiving or defining a set of clinical goals; using the baseline dose distribution to calibrate a utility function or cost function based on the set of clinical goals; and using the utility function or cost function to optimise a treatment plan.
The method of claim 1, wherein the received desired baseline dose distribution comprises a dose distribution used for a past patient similar to the new patient.
The method of claim 1 or claim 2, further comprising: selecting a dose prediction model constructed for past patients similar to the new patient, from a library of dose prediction models; using the selected dose prediction model to generate the desired baseline dose distribution.
The method of any preceding claim, further comprising: selecting a template utility function or a template cost function constructed for past patients similar to the new patient, from a library of template utility functions or template cost functions; and using the selected template utility function or template cost function to generate the desired baseline dose distribution.
The method of any preceding claim, wherein the received desired baseline dose distribution is partially or wholly defined by a human user.
The method of any preceding claim, wherein the received desired baseline dose distribution is further modified by a human user.
The method of any of claim 1 to claim 4, wherein the received desired baseline dose distribution is partially or wholly defined by a computer-implemented method.
The method of any preceding claim, wherein the baseline dose distribution is generated based on relaxed machine parameter constraints.
The method of any preceding claim, further comprising receiving information defining one or more of: a relative priority of each clinical goal; significant deviations from clinical goals, and/or insignificant deviations from clinical goals; and using the baseline dose distribution and the received information defining the relative priority of each clinical goal, significant deviations from clinical goals, and/or insignificant deviations from clinical goals to calibrate the utility function or cost function.
The method of claim 9, wherein the information defining clinical goal priorities, significant deviations from clinical goals and/or insignificant deviations from clinical goals is received from a library of templates defining clinical goal priorities, significant deviations from clinical goals and/or insignificant deviations from clinical goals in past similar patients.
The method of claim 9 or claim 10, wherein the information defining clinical goal priorities, significant deviations from clinical goals and/or insignificant deviations from clinical goals is at least partially received from a human user.
The method of any preceding claim, wherein the cost function comprises a sum of quadratic terms, each quadratic term penalising a deviation from a corresponding clinical goal, and optionally wherein each quadratic term is normalised by significance; and/or: wherein the utility function or cost function comprises a piecewise linear function.
The method of any preceding claim, wherein the utility function or cost function is assessed by determining a rating that depends on the extent to which the desired baseline dose distribution is achieved; and optionally wherein: the rating is a maximal value when all clinical goals are achieved; the rating is a minimal value when one or more of achieved metrics deviate from corresponding clinical goals by more than a significant amount; the rating is between the maximal value and the minimal value in all other cases.
A radiation treatment planning computer system comprising a memory and a processor configured to perform the method as defined in any one of claims 1-13.
A computer program product comprising a non-transitory, computer readable storage medium encoded with instructions operable for execution by a processor to perform the method as defined in any one of claims 1-13.

Description

TECHNCAL FIELD This invention relates to radiation therapy treatment planning, and in particular, to methods and systems for construction of a utility or cost function usable to develop a radiation therapy treatment plan. BACKGROUND The use of energy to treat medical conditions comprises a known area of prior art endeavour. For example, radiation therapy comprises an important component of many treatment plans for reducing or eliminating unwanted tumours. Unfortunately, applied energy does not inherently discriminate between unwanted material and adjacent tissues, organs, or the like that are desired or even critical to continued survival of the patient (such adjacent tissues may be referred to as "organs at risk", OARs). As a result, energy such as radiation is ordinarily applied in a carefully administered manner to at least attempt to restrict the energy to a given target volume. A so-called radiation treatment plan often serves in the foregoing regards. A radiation treatment plan typically comprises specified values for each of a variety of treatment-platform "machine" parameters during each of a plurality of sequential fields. For example, machine parameters of a radiotherapy system may include the angle of irradiation of the treatment beam, or the configuration of the leaves of a multileaf collimator. Treatment plans for radiation treatment sessions are often automatically generated through a so-called optimisation process. As used herein, "optimisation" will be understood to refer to improving a candidate treatment plan without necessarily ensuring that the optimised result is, in fact, the singular best solution. Such optimisation often includes automatically adjusting one or more physical treatment machine parameters (often while observing one or more corresponding limits in these regards) and mathematically calculating a likely corresponding treatment result (such as a level of dosing) to identify a given set of treatment parameters that represent a good compromise between the desired therapeutic result and avoidance of undesired collateral effects. In some cases, optimisation proceeds as a function of multiple different criteria. This may involve the use of a cost function comprising a mathematical model that attempts to balance conflicting clinical goals to produce a treatment plan with the least "cost". Clinical goals generally take the form of a particular metric being required to be greater or smaller than a threshold value. For example, a clinical goal may require that a certain percentage of the volume of an OAR receives less than a certain amount of dose. As a further example, a clinical goal may require that a certain percentage of the planning target volume (PTV) receives at least a certain amount of dose. A cost function may be a sum of terms relating to deviations from the clinical goals. As an alternative to a cost function, a utility function may be used to attempt to balance the clinical goals. A utility function is similar to a cost function, except that the optimisation attempts to produce a treatment plan with the highest "utility", rather than the lowest "cost". For the rest of this disclosure, the maximisation of a utility function or the minimisation of a cost function reflect complementary mathematical methods that can be used in similar ways. A computer-implemented optimiser is generally used to iteratively maximise (or minimise) the utility function (or cost function). In general, the process of optimisation involves finding a set of machine parameters (also referred to as "control points") that maximise a given utility function (or minimise the cost function). Traditionally, a utility function or cost function is developed on the basis of a desired dose distribution. However, the choice of a dose distribution that is used as a starting point for the optimisation process is usually based on an idealised dose to each of the regions of interest, which may be difficult to achieve. Further, while the concept of prioritisation of clinical goals during the optimisation process is known, conventional methods do not take into account what may be clinically insignificant deviations from a goal, or what may be clinically significant deviations from the goal. SUMMARY OF THE INVENTION According to a first aspect of the invention, there is provided a method for computer-assisted radiation therapy treatment planning as defined by claim 1. According to a second aspect of the invention, there is provided a radiation treatment planning computer system as defined by claim 14. According to a third aspect of the invention, there is provided a computer program product as defined by claim 15. Optional features are defined by the dependent claims. According to the first aspect of the invention, there is provided a method for computer-assisted radiation therapy treatment planning, comprising: receiving a desired baseline dose distribution based on dose distributions used in radiation therapy treat