Search

CN-122006143-A - Utility function in radiation therapy planning

CN122006143ACN 122006143 ACN122006143 ACN 122006143ACN-122006143-A

Abstract

The present invention relates to utility functions in radiation treatment planning. A method (300) of computer-aided radiation therapy treatment planning includes receiving (310) a desired baseline dose distribution based on a dose distribution used in radiation therapy treatment planning for one or more past patients 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 optimize (350) the treatment plan.

Inventors

  • E. Quisera
  • J. PELTOLA

Assignees

  • 西门子医疗国际股份有限公司

Dates

Publication Date
20260512
Application Date
20251107
Priority Date
20241111

Claims (15)

  1. 1. A method of computer-assisted radiation therapy treatment planning, comprising: receiving a desired baseline dose profile based on dose profiles used in a radiation therapy treatment plan for one or more past patients similar to the new patient; receiving or defining a set of clinical goals; using the baseline dose distribution to calibrate a utility function or a cost function based on the set of clinical goals, and The utility function or cost function is used to optimize a treatment plan.
  2. 2. The method of claim 1, wherein the received expected baseline dose profile comprises a dose profile of a past patient similar to the new patient.
  3. 3. The method of claim 1 or 2, further comprising: selecting a dose prediction model constructed for a past patient similar to the new patient from a library of dose prediction models; The desired baseline dose distribution is generated using the selected dose prediction model.
  4. 4. The method of any of the preceding claims, further comprising: selecting a template utility function or template cost function constructed for a past patient similar to the new patient from a template utility function library or template cost function library, and The desired baseline dose distribution is generated using the selected template utility function or template cost function.
  5. 5. The method of any preceding claim, wherein the received desired baseline dose profile is defined in part or in whole by a human user.
  6. 6. The method according to any of the preceding claims, wherein the received desired baseline dose profile is further modified by a human user.
  7. 7. The method of any one of claims 1 to 4, wherein the received desired baseline dose profile is defined in part or in whole by a computer-implemented method.
  8. 8. The method of any preceding claim, wherein the baseline dose distribution is generated based on loose machine parameter constraints.
  9. 9. The method of any of the preceding claims, further comprising: Receiving information defining one or more of a relative priority of each clinical objective, a significant deviation from a clinical objective, and/or an insignificant deviation from a clinical objective, and The utility function or cost function is calibrated using the baseline dose distribution and the received information defining the relative priority of each clinical target, significant deviations from clinical targets, and/or insignificant deviations from clinical targets.
  10. 10. The method of claim 9, wherein the information defining clinical objective priorities, significant deviations from clinical objectives, and/or insignificant deviations from clinical objectives is received from a template library defining clinical objective priorities, significant deviations from clinical objectives, and/or insignificant deviations from clinical objectives in similar patients in the past.
  11. 11. The method of claim 9 or 10, wherein the information defining clinical objective priority, significant deviation from clinical objective, and/or insignificant deviation from clinical objective is received at least in part from a human user.
  12. 12. The method according to any of the preceding claims, Wherein the cost function comprises a sum of quadratic terms, each quadratic term penalizing a deviation from a corresponding clinical objective, and optionally wherein each quadratic term is normalized according to significance, and/or Wherein the utility function or cost function comprises a piecewise linear function.
  13. 13. A method according to any one of the preceding claims, wherein the utility function or cost function is assessed by determining a rating which depends on the extent to which the desired baseline dose distribution is achieved, and Optionally wherein: The rating is maximum when all clinical goals are achieved; the rating is a minimum when one or more of the realized metrics deviate from the corresponding clinical goal by more than a significant amount; in all other cases, the rating is located between the maximum value and the minimum value.
  14. 14. A radiation treatment planning computer system comprising a memory and a processor configured to perform the method of any one of claims 1 to 13.
  15. 15. A computer program product comprising a non-transitory computer readable storage medium encoded with instructions executable by a processor to perform the method of any of claims 1-13.

Description

Utility function in radiation therapy planning Technical Field The present invention relates to radiation therapy treatment planning and, in particular, to methods and systems for constructing utility or cost functions for developing radiation therapy treatment planning. Background The use of energy to treat diseases is a known area of prior art effort. For example, radiation therapy includes an important component of many treatment plans that reduce or eliminate harmful tumors. Unfortunately, the energy applied cannot by itself distinguish unwanted substances from neighboring tissues, organs, etc., which are desirable or even critical for the continued survival of the patient (these neighboring tissues may be referred to as "organs at risk", OAR). Thus, energy, such as radiation, is typically applied in a discreet manner to at least attempt to confine the energy within a given target volume. So-called radiation treatment planning generally serves the above-mentioned function. Radiation treatment plans typically include specified values for each of various treatment table "machine" parameters during each of a plurality of consecutive fields. For example, the machine parameters of the radiotherapy system may include the radiation angle of the therapeutic beam or the configuration of the leaves of the multi-leaf collimator. Treatment plans for radiation treatment sessions are typically automatically generated by a so-called optimization process. As used herein, "optimization" is understood to mean improving a candidate treatment plan, without necessarily ensuring that the result of the optimization is in fact the only best solution. Such optimization typically involves automatically adjusting one or more physical therapy machine parameters (typically while observing one or more corresponding limitations in these aspects) and mathematically calculating the likely corresponding therapy results (e.g., dose levels) to identify a set of given therapy parameters that represent a good compromise between desired therapy results and avoidance of adverse side effects. In some cases, the optimization is performed according to a number of different criteria. This may involve using a cost function that contains a mathematical model that attempts to balance conflicting clinical goals to produce a treatment plan with the lowest "cost". Clinical goals often take the form of specific indicators that are required to be greater or less than a threshold. For example, a clinical goal may require that a certain percentage of the volume of the OAR receive less than a certain amount of dose. As another example, a clinical goal may require that a certain percentage of a Planned Target Volume (PTV) receive at least a certain amount of dose. The cost function may be the sum of terms related to clinical target deviation. Instead of a cost function, a utility function may be used to attempt to balance clinical goals. The utility function is similar to the cost function, except that the optimization attempts to produce a treatment plan with the highest "utility" rather than the lowest "cost". For the remainder of this disclosure, maximization of the utility function or minimization of the cost function reflects complementary mathematical methods that may be used in a similar manner. Computer-implemented optimizers are typically used to iteratively maximize (or minimize) a utility function (or cost function). Generally, an optimization process involves finding a set of machine parameters (also referred to as "control points") that maximize a given utility function (or minimize a cost function). Traditionally, utility functions or cost functions are developed according to the desired dose distribution. However, the selection of the dose distribution used as a starting point for the optimization process is typically based on the idealized dose for each region of interest, which may be difficult to achieve. Furthermore, while solutions are known to prioritize clinical targets during the optimization process, conventional approaches do not take into account which may be clinically insignificant deviations from the target, or which may be clinically significant deviations from the target. Disclosure of Invention According to a first aspect of the present invention there is provided a method of computer-assisted radiotherapy treatment planning according to the present invention. According to a second aspect of the invention there is provided a radiation treatment planning computer system according to the invention. According to a third aspect of the invention, a computer program product according to the invention is provided. Optional features are defined by the specification. According to a first aspect of the invention there is provided a method of computer-assisted radiation therapy treatment planning comprising receiving a desired baseline dose distribution based on a dose distribution used in radiation therapy treatment planning for one or