# US 2023/0264045 A1 · Dose volume histogram optimization based on quantile regression

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0264045 A1
- Document ID: US20230264045A1
- Status: Published application
- Kind: A1
- Application number: 17/651,679
- Filed: 2022-02-18
- Published: 2023-08-24
- Earliest claimed: 2022-02-18
- Assignees: Elekta Instrument AB
- Applicants: Elekta Instrument AB
- Inventors: Jens Olof Sjolund; Carl Axel Håkan Nordström
- Web page: https://patentgrep.com/patent/US20230264045A1

## CPC

- A61N 5/1031: {using a specific method of dose optimization}
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- A61N: ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY (measurement of bioelectric currents A61B; surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body A61B18/00; anaesthetic apparatus in general A61M; incandescent lamps H01K; infrared radiators for heating H05B)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

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.

## Claims

### Claim 1

A computer-implemented method for generating a radiotherapy treatment plan for a patient, the method comprising:
receiving, by processor circuitry, a plurality of treatment planning criteria including at least one dose-volume criterion that corresponds to a quantile of a dose-volume histogram;
determining a first radiotherapy optimization problem based on the received plurality of treatment planning criteria;
determining, for each quantile, a second radiotherapy optimization problem such that a solution to the second radiotherapy optimization problem estimates a radiotherapy dose that corresponds to a specified fractional portion of a volume of the patient, wherein the first radiotherapy optimization problem is based on solutions to at least one of the other second radiotherapy optimization problems;
processing the first radiotherapy optimization problem and the second radiotherapy optimization problems corresponding to each quantile to determine mutually consistent solutions to both the first radiotherapy optimization problem and the second radiotherapy optimization problems corresponding to each quantile; and
processing the determined solutions to the first radiotherapy optimization problem to generate the radiotherapy treatment plan.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the first radiotherapy optimization problem is a bilevel radiotherapy optimization problem including an upper radiotherapy optimization problem and a lower radiotherapy optimization problem, and wherein a solution to the lower radiotherapy optimization problem estimates the radiotherapy dose that corresponds to the specified fractional portion of the volume of the patient.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein the scope of the upper radiotherapy optimization problem includes treatment delivery parameters and radiation doses.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, comprising:
computing the radiation doses based on a multiplication of a dose deposition matrix with a vector of the treatment delivery parameters.

### Claim 5 (depends on 3)

The computer-implemented method of claim 3, wherein the treatment delivery parameters comprise a set of isocenters used for delivery of the radiotherapy treatment plan.

### Claim 6 (depends on 2)

The computer-implemented method of claim 2, wherein the first radiotherapy optimization problem includes an objective function and at least one constraint function.

### Claim 7 (depends on 6)

The computer-implemented method of claim 6, wherein the at least one constraint function comprises a quantile regression problem.

### Claim 8 (depends on 7)

The computer-implemented method of claim 7, comprising:
discretizing the quantile regression problem as a sum of a finite number of terms.

### Claim 9 (depends on 6)

The computer-implemented method of claim 6, wherein the objective function is a weighted sum of terms reflecting treatment complexity and dose-based criteria.

### Claim 10 (depends on 2)

The computer-implemented method of claim 2, wherein the second optimization problems are convex.

### Claim 11 (depends on 10)

The computer-implemented method of claim 10, wherein the set of treatment delivery parameters further comprises timing for delivery of the radiotherapy treatment plan and a collimator sequence for the delivery of the radiotherapy treatment plan.

### Claim 12 (depends on 10)

The computer-implemented method of claim 10, wherein the set of treatment delivery parameters further comprises dwell times and dwell positions for delivery of the radiotherapy treatment plan.

### Claim 13 (depends on 1)

The computer-implemented method of claim 1, comprising:
receiving input defining the at least one dose-volume criterion.

### Claim 14 (depends on 1)

The computer-implemented method of claim 1, wherein processing the first radiotherapy optimization problem and the second radiotherapy optimization problems comprises at least one of (i) replacing the second optimization problems with corresponding first-order optimality conditions and (ii) using a variable splitting technique.

### Claim 15 (depends on 1)

The computer-implemented method of claim 1, wherein processing the first radiotherapy optimization problem and the second radiotherapy optimization problems corresponding to each quantile to determine mutually consistent solutions to both the first radiotherapy optimization problem and the second radiotherapy optimization problems corresponding to each quantile includes:
concurrently processing the second radiotherapy optimization problem for each quantile to determine the solution to the first radiotherapy optimization problem.

### Claim 16 (depends on 15)

The computer-implemented method of claim 15, wherein concurrently processing the second radiotherapy optimization problem for each quantile to determine the solution to the first radiotherapy optimization problem includes:
concurrently processing the second radiotherapy optimization problem for each quantile to determine the solution to the first radiotherapy optimization problem by performing an alternating direction method of multipliers algorithm.

### Claim 17 (depends on 1)

The computer-implemented method of claim 1, wherein the at least one dose-volume criterion corresponds to a target or an organ at risk.

### Claim 18 (depends on 1)

The computer-implemented method of claim 1, wherein processing the first radiotherapy optimization problem and the second radiotherapy optimization problems corresponding to each quantile to determine mutually consistent solutions to both the first radiotherapy optimization problem and the second radiotherapy optimization problems corresponding to each quantile comprises:
computing a gradient using automatic differentiation.

### Claim 19

A radiotherapy system for generating a radiotherapy treatment plan for a patient, the radiotherapy system comprising:
a radiation therapy device configured to deliver a dose of radiation to an anatomical region of interest; and
a processor configured to:
receive a plurality of treatment planning criteria including at least one dose-volume criterion that corresponds to a quantile of a dose-volume histogram;
determine a first radiotherapy optimization problem based on the received plurality of treatment planning criteria;
determine, for each quantile, a second radiotherapy optimization problem such that a solution to the second radiotherapy optimization problem estimates a radiotherapy dose that corresponds to a specified fractional portion of a volume of the patient, wherein the first radiotherapy optimization problem is based on solutions to at least one of the other second radiotherapy optimization problems;
process the first radiotherapy optimization problem and the second radiotherapy optimization problems corresponding to each quantile to determine mutually consistent solutions to both the first radiotherapy optimization problem and the second radiotherapy optimization problems corresponding to each quantile; and
process the determined solution to the first radiotherapy optimization problem to generate the radiotherapy treatment plan.

### Claim 20 (depends on 19)

The radiotherapy system of claim 19, wherein the first radiotherapy optimization problem is a bilevel radiotherapy optimization problem including an upper radiotherapy optimization problem and a lower radiotherapy optimization problem, and wherein a solution to the lower radiotherapy optimization problem estimates the radiotherapy dose that corresponds to the specified fractional portion of the volume of the patient.

### Claim 21 (depends on 20)

The radiotherapy system of claim 20, wherein a scope of the upper radiotherapy optimization problem includes treatment delivery parameters and radiation doses.

### Claim 22 (depends on 19)

The radiotherapy system of claim 19, wherein the radiation therapy device includes a linear accelerator (linac) or magnetic resonance (MR)-linac.

### Claim 23 (depends on 22)

The radiotherapy system of claim 22, wherein the radiotherapy treatment plan is to be provided with volumetric-modulated arc therapy (VMAT) or intensity modulated radiation therapy (IMRT), and wherein treatment delivery parameters comprise:
a set of arc control points for one or more arcs, fluence fields, gantry speed, and dose rate along the one or more arcs.

### Claim 24

A computer-readable medium configured to include instructions that, when executed, cause one or more processors to:
receive a plurality of treatment planning criteria including at least one dose-volume criterion that corresponds to a quantile of a dose-volume histogram;
determine a first radiotherapy optimization problem based on the received plurality of treatment planning criteria;
determine, for each quantile, a second radiotherapy optimization problem such that a solution to the second radiotherapy optimization problem estimates a radiotherapy dose that corresponds to a specified fractional portion of a volume of a patient, wherein the first radiotherapy optimization problem is based on solutions to at least one of the other second radiotherapy optimization problems;
process the first radiotherapy optimization problem and the second radiotherapy optimization problems corresponding to each quantile to determine mutually consistent solutions to both the first radiotherapy optimization problem and the second radiotherapy optimization problems corresponding to each quantile; and
process the determined solution to the first radiotherapy optimization problem to generate the radiotherapy treatment plan.

### Claim 25 (depends on 24)

The computer-readable medium of claim 24, wherein the first radiotherapy optimization problem is a bilevel radiotherapy optimization problem including an upper radiotherapy optimization problem and a lower radiotherapy optimization problem, and wherein a solution to the lower radiotherapy optimization problem estimates the radiotherapy dose that corresponds to the specified fractional portion of the volume of the patient.

### Claim 26 (depends on 25)

The computer-readable medium of claim 25, wherein a scope of the upper radiotherapy optimization problem includes treatment delivery parameters and radiation doses.
