Patents by Inventor Mats HOLMSTROM

Mats HOLMSTROM has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20250108233
    Abstract: The present disclosure relates to the use of machine learning for determining initial machine setting parameters for radiotherapy treatment planning. A machine-learning system is trained on data sets including a dose distribution and a set of machine parameter settings resulting from that dose distribution. The trained system can be used for determining machine parameter settings based on a desired dose distribution, which may be used as initial machine parameter settings for radiation treatment optimization.
    Type: Application
    Filed: February 7, 2023
    Publication date: April 3, 2025
    Inventors: Rasmus HELANDER, Mats HOLMSTROM
  • Patent number: 12201851
    Abstract: A method (100) for generating a treatment plan specifying an irradiation of a patient, the method comprising: a dose inference stage (112), including using a model to infer a spatial dose from patient data; a dose mimicking stage (116), including executing a robust optimization process to generate a deliverable treatment plan which is consistent with the inferred spatial dose, wherein the robust optimization considers a plurality of scenarios relating to patient data uncertainty.
    Type: Grant
    Filed: November 18, 2021
    Date of Patent: January 21, 2025
    Assignee: Raysearch Laboratories AB (publ)
    Inventors: Albin Fredriksson, Hanna Gruselius, Mats Holmstrom, David Andersson
  • Patent number: 11931599
    Abstract: An estimated or predicted dose for radiotherapy treatment may be generated based on a partial dose map including dose information only for one or more regions of interest within a treatment site, by use of a properly trained machine learning system such as a U-Net or a V-Net. Said partial dose map typically set to fulfil clinical goals. A method of training such a machine learning system is also disclosed.
    Type: Grant
    Filed: November 29, 2021
    Date of Patent: March 19, 2024
    Assignee: Raysearch Laboratories AB (publ)
    Inventors: Mats Holmstrom, David Andersson, Gabriel Carrizo, Adnan Hossain
  • Publication number: 20240033539
    Abstract: An estimated or predicted dose for radiotherapy treatment may be generated based on a partial dose map including dose information only for one or more regions of interest within a treatment site, by use of a properly trained machine learning system such as a U-Net or a V-Net. Said partial dose map typically set to fulfil clinical goals. A method of training such a machine learning system is also disclosed.
    Type: Application
    Filed: November 29, 2021
    Publication date: February 1, 2024
    Inventors: Mats HOLMSTROM, David ANDERSSON, Gabriel CARRIZO, Adnan HOSSAIN
  • Publication number: 20230381539
    Abstract: A method (100) for generating a treatment plan specifying an irradiation of a patient, the method comprising: a dose inference stage (112), including using a model to infer a spatial dose from patient data; a dose mimicking stage (116), including executing a robust optimization process to generate a deliverable treatment plan which is consistent with the inferred spatial dose, wherein the robust optimization considers a plurality of scenarios relating to patient data uncertainty.
    Type: Application
    Filed: November 18, 2021
    Publication date: November 30, 2023
    Inventors: Albin FREDRIKSSON, Hanna GRUSELIUS, Mats HOLMSTROM, David ANDERSSON
  • Patent number: 10850125
    Abstract: The present disclosure generally relates to the field of radiation treatment. More specifically, the present disclosure generally relates to methods and radiation treatment systems for generating a radiation treatment plan. According to one example embodiment, a method may comprise dividing at least one dose characteristic related to a dose distribution for a ROI into a plurality of subintervals. The method may further comprise partitioning the ROI into a plurality of different partitions based on the subintervals. All voxels of the ROI with values within the same subinterval are partitioned into the same partition. For each of the plurality of different partitions, the method may comprise establishing a weight and specifying an optimization function for an obtainable dose distribution based on the respective subinterval of dose characteristics. The method may further comprise generating the radiation treatment plan based on said established weights and specified optimization functions.
    Type: Grant
    Filed: December 31, 2019
    Date of Patent: December 1, 2020
    Assignee: RaySearch Laboratories AB
    Inventors: Albin Fredriksson, Mats Holmström, Kjell Eriksson
  • Publication number: 20200215352
    Abstract: The present disclosure generally relates to the field of radiation treatment. More specifically, the present disclosure generally relates to methods and radiation treatment systems for generating a radiation treatment plan. According to one example embodiment, a method may comprise dividing at least one dose characteristic related to a dose distribution for a ROI into a plurality of subintervals. The method may further comprise partitioning the ROI into a plurality of different partitions based on the subintervals. All voxels of the ROI with values within the same subinterval are partitioned into the same partition. For each of the plurality of different partitions, the method may comprise establishing a weight and specifying an optimization function for an obtainable dose distribution based on the respective subinterval of dose characteristics. The method may further comprise generating the radiation treatment plan based on said established weights and specified optimization functions.
    Type: Application
    Filed: December 31, 2019
    Publication date: July 9, 2020
    Applicant: RaySearch Laboratories AB
    Inventors: Albin FREDRIKSSON, Mats HOLMSTRÖM, Kjell ERIKSSON