IP Library Granted Patent US 12,728,285
Granted Patent B2
US 12,728,285 · App. 18/689,175 · Granted Sep 8, 2026

Generative model of phase space

Inventors: Jens Olof Sjolund (Uppsala, SE); Carl Axel Håkan Nordström (Stockholm, SE)
Assignee: Elekta AB (publ)
A61N5/1031A61N5/1039A61N5/1071A61N5/1081G16H20/40G16H50/50A61N2005/1034A61N2005/1041A61N2005/1074A61N2005/1087A61N2005/1089
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,728,285
App. No.
18/689,175
Granted
Sep 8, 2026
Kind
B2
Abstract

Systems and methods are disclosed for simulating dose deposition. The systems and methods perform operations comprising: receiving a set of training data representing phase space of a radiotherapy treatment device comprising propagation and scattering of particles inside the radiotherapy treatment device; training a generative machine learning model based on the set of training data to generate one or more samples of the phase space of the radiotherapy treatment device; and simulating dose deposition at a particular region of interest based on the one or more samples of the phase space generated by the generative machine learning model.

Claims (53)

1 . A computer-implemented method comprising:

receiving a set of training data representing a phase space of a radiotherapy treatment device comprising propagation and scattering of particles inside the radiotherapy treatment device;

training a generative machine learning model based on the set of training data to generate one or more samples of the phase space of the radiotherapy treatment device; and

simulating a dose deposition at a particular region of interest based on the one or more samples of the phase space of the radiotherapy treatment device generated by the generative machine learning model, wherein a radiotherapy treatment plan for a patient is generated based on the simulated dose deposition.

2 . The computer-implemented method of claim 1 , wherein the set of training data describes position and momentum vectors of relevant particles within a set of regions of the radiotherapy treatment device.

3 . The computer-implemented method of claim 1 , wherein the generative machine learning model comprises a neural network comprising at least one of a generative adversarial network (GAN), a variational autoencoder (VAE), a normalizing flow network, or a diffusion model.

4 . The computer-implemented method of claim 1 , wherein the set of training data represent the phase space of the radiotherapy treatment device as a collection of samples from a probability distribution.

5 . The computer-implemented method of claim 1 , further comprising:

generating the set of training data by performing a Monte Carlo simulation, wherein the set of training data is stored and retrieved from a non-volatile storage device or is computed in real time.

6 . The computer-implemented method of claim 1 , wherein the set of training data comprises a multi-dimensional surface representing physical information about the particles inside the radiotherapy treatment device.

7 . The computer-implemented method of claim 1 , wherein the trained generative machine learning model is stored on a same processing device that simulates the dose deposition when simulating the dose deposition to avoid accessing the one or more samples of the phase space of the radiotherapy treatment device from a remote storage location.

8 . The computer-implemented method of claim 1 , further comprising:

generating a three-dimensional (3D) volume of the dose deposition based on an interaction between the one or more samples of the phase space of the radiotherapy treatment device and an image detector, and wherein the generative machine learning model is part of a radiotherapy system that includes the image detector.

9 . The computer-implemented method of claim 1 , further comprising:

generating a three-dimensional (3D) volume of the dose deposition based on an interaction between the one or more samples of the phase space of the radiotherapy treatment device and an image detector, and wherein the generative machine learning model is separate from a radiotherapy system that includes the image detector.

10 . The computer-implemented method of claim 1 , wherein:

the generative machine learning model comprises a generative adversarial network (GAN) configured to train a generative model using a discriminative model; and

values applied by the generative model and the discriminative model are established using adversarial training between the discriminative model and the generative model.

11 . The computer-implemented method of claim 10 , wherein:

the adversarial training between the discriminative model and the generative model comprises:

training the generative model to generate a first synthetic sample of the phase space of the radiotherapy treatment device from a distribution of the particles inside the radiotherapy treatment device; and

training the discriminative model to classify the first synthetic sample as a synthetic or a real training particle inside the radiotherapy treatment device; and

an output of the generative model is used for training the discriminative model and an output of the discriminative model is used for training the generative model.

12 . The computer-implemented method of claim 11 , further comprising:

obtaining a particle from the set of training data; and

computing a training loss for the discriminative model based on a result of comparing an output of the discriminative model with the particle obtained from the set of training data.

13 . The computer-implemented method of claim 11 , wherein the first synthetic sample is generated based on a random point within the phase space or a specified region within the phase space.

14 . The computer-implemented method of claim 1 , wherein the generative machine learning model comprises a normalizing flow network, further comprising:

obtaining a particle from the set of training data;

computing a training loss based on a likelihood of the particle obtained from the set of training data based on a distribution provided by the normalizing flow network; and

updating the distribution provided by the normalizing flow network based on the training loss.

15 . The computer-implemented method of claim 14 , further comprising:

computing a new particle based on a distribution provided by the normalizing flow network, wherein the new particle is computed based on a random point within the phase space or a specified region within the phase space of the radiotherapy treatment device.

16 . A system for generating one or more radiotherapy treatment plans, the system comprising:

one or more processors configured to perform operations comprising:

receiving a set of training data representing a phase space of a radiotherapy treatment device comprising propagation and scattering of particles inside the radiotherapy treatment device;

training a generative machine learning model based on the set of training data to generate one or more samples of the phase space of the radiotherapy treatment device; and

simulating a dose deposition at a particular region of interest based on the one or more samples of the phase space of the radiotherapy treatment device generated by the generative machine learning model, wherein a radiotherapy treatment plan for a patient is generated based on the simulated dose deposition.

17 . The system of claim 16 , wherein the set of training data describes position and momentum vectors of relevant particles within a set of regions of the radiotherapy treatment device.

18 . The system of claim 16 , wherein the generative machine learning model comprises a neural network comprising at least one of a generative adversarial network (GAN), a variational autoencoder (VAE), a normalizing flow network, or a diffusion model.

19 . A non-transitory computer-readable medium comprising non-transitory computer-readable instructions for performing operations of claim 1 .

20 . A computer-implemented method comprising:

accessing a generative machine learning model that has been trained based on a set of training data to generate one or more samples of a phase space of a radiotherapy treatment device, the set of training data comprising propagation and scattering of particles inside the radiotherapy treatment device; and

simulating a dose deposition at a particular region of interest based on the one or more samples of the phase space of the radiotherapy treatment device generated by the generative machine learning model, wherein a radiotherapy treatment plan for a patient is generated based on the simulated dose deposition.

21 . The computer-implemented method of claim 20 , wherein the set of training data describes position and momentum vectors of relevant particles within a set of regions of the radiotherapy treatment device.

22 . The computer-implemented method of claim 20 , wherein:

the generative machine learning model comprises a generative adversarial network (GAN) configured to train a generative model using a discriminative model; and

values applied by the generative model and the discriminative model are established using adversarial training between the discriminative model and the generative model.

23 . The computer-implemented method of claim 22 , wherein:

the adversarial training between the discriminative model and the generative model comprises:

training the generative model to generate a first synthetic sample of the phase space of the radiotherapy treatment device from a distribution of the particles inside the radiotherapy treatment device; and

training the discriminative model to classify the first synthetic sample as a synthetic or a real training particle inside the radiotherapy treatment device; and

an output of the generative model is used for training the discriminative model and an output of the discriminative model is used for training the generative model.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 5, 2024
From: SJOLUND, JENS OLOF; NORDSTRÖM, CARL AXEL HÅKAN
To: ELEKTA AB (PUBL)
Reel/Frame 066651/0950 →
Continuity (1)
Related Publication 20240366962A1 · Nov 7, 2024
References Cited (65)
US 6029079A · Cox · 2000 [cited by examiner]
US 6285969B1 · Svatos · 2001 [cited by examiner]
US 6535837B1 · Schach Von Wittenau · 2003 [cited by examiner]
US 6714620B2 · Caflisch · 2004 [cited by examiner]
US 7197404B2 · Holland · 2007 [cited by examiner]
US 8125813B2 · Nizin · 2012 [cited by examiner]
US 8401148B2 · Lu · 2013 [cited by examiner]
US 9370672B2 · Parsai · 2016 [cited by examiner]
US 9782607B2 · Wiersma · 2017 [cited by examiner]
US 9878181B2 · Russo · 2018 [cited by examiner]
US 10046177B2 · Sjölund · 2018 [cited by examiner]
US 10342994B2 · Kuusela · 2019 [cited by examiner]
US 10346593B2 · Kuusela · 2019 [cited by examiner]
US 10417390B2 · Svatos · 2019 [cited by examiner]
US 10493299B2 · Hissoiny · 2019 [cited by examiner]
US 10565329B2 · Greenwood · 2020 [cited by examiner]
US 10672153B2 · Adler · 2020 [cited by examiner]
US 10737115B2 · Li · 2020 [cited by examiner]
US 10918888B2 · Ramezanzadeh Moghadam · 2021 [cited by examiner]
US 11013936B2 · Cordero Marcos · 2021 [cited by examiner]
US 11020615B2 · Eriksson · 2021 [cited by examiner]
US 11056243B2 · Sjölund · 2021 [cited by examiner]
US 11077320B1 · Hibbard · 2021 [cited by examiner]
US 11083913B2 · Lachaine · 2021 [cited by examiner]
US 11097128B2 · Sjölund · 2021 [cited by examiner]
US 11100632B2 · Han · 2021 [cited by examiner]
US 11141609B2 · Tilly · 2021 [cited by examiner]
US 11167152B2 · Liu · 2021 [cited by examiner]
US 11358003B2 · Sjölund · 2022 [cited by examiner]
US 11433258B2 · Maltz · 2022 [cited by examiner]
US 11517768B2 · Hibbard · 2022 [cited by examiner]
US 11557390B2 · Hibbard · 2023 [cited by examiner]
US 11651848B2 · Kuusela · 2023 [cited by examiner]
US 11679274B2 · Peltola · 2023 [cited by examiner]
US 11717702B2 · Yuan · 2023 [cited by examiner]
US 11813479B2 · Czeizler · 2023 [cited by examiner]
US 11850445B2 · Hibbard · 2023 [cited by examiner]
US 11865362B2 · Nguyen · 2024 [cited by examiner]
US 11931599B2 · Holmstrom · 2024 [cited by examiner]
US 11964170B2 · Li · 2024 [cited by examiner]
US 11992702B2 · Hibbard · 2024 [cited by examiner]
US 12017089B2 · Flaschner · 2024 [cited by examiner]
US 12023518B2 · Weese · 2024 [cited by examiner]
US 12076587B2 · Lansonneur · 2024 [cited by examiner]
US 12121747B2 · Peltola · 2024 [cited by examiner]
US 12128250B2 · Wu · 2024 [cited by examiner]
US 12194311B2 · Bai · 2025 [cited by examiner]
US 12226657B2 · Hibbard · 2025 [cited by examiner]
US 12239853B2 · Shi · 2025 [cited by examiner]
US 12274895B2 · Tilly · 2025 [cited by examiner]
US 12370378B2 · Lofman · 2025 [cited by examiner]
US 12370381B2 · Bose · 2025 [cited by examiner]
US 12383763B2 · Tang · 2025 [cited by examiner]
US 12420112B2 · Chen · 2025 [cited by examiner]
US 12496464B2 · Peri · 2025 [cited by examiner]
US 12502552B2 · Sjölund · 2025 [cited by examiner]
US 12508446B2 · Tilly · 2025 [cited by examiner]
WO WO2023041167A1 · 2023 [cited by applicant]
“International Application Serial No. PCT/EP2021/075541, International Search Report mailed Jun. 9, 22”, 4 pgs. [cited by applicant]
“International Application Serial No. PCT/EP2021/075541, Written Opinion mailed Jun. 9, 2022”, 5 pgs. [cited by applicant]
Libby, B, et al., “Validation of Monte Carlo generated phase-space descriptions of medical linear accelerators”, Medical Physics, AIP, Melville, NY, US, vol. 26, No. 8, (Aug. 1, 1999), 8 pgs. [cited by applicant]
Sarrut, David, et al., “Generative Adversarial Networks (GAN) for compact beam sourcemodelling in Monte Carlo simulations”, arxiv.org, Cornell University Library, 201 Olin Library Cornell University Ithaca, NY 14853, (J… [cited by applicant]
“International Application Serial No. PCT EP2021 075541, International Preliminary Report on Patentability mailed Mar. 28, 2024”, 7 pgs. [cited by applicant]
“European Application Serial No. 21782454.9, Response to Communication Pursuant to Rules 161 and 162 EPC filed Oct. 22, 2024”, 13 pgs. [cited by applicant]
“European Application Serial No. 21782454.9, Communication Pursuant to Article 943 EPC mailed Jan. 15, 2026”, 4 pgs. [cited by applicant]