Raysearch Laboratories Ab (publ)

Raysearch Laboratories Ab

Hanna Gruselius

Albin Fredriksson

Mats Holmstrom

David Andersson

Giorgio Ruffa

Mats HOLMSTRÖM

A machine learning-based method of generating a radiotherapy treatment plan for a patient, comprises dose prediction and dose mimicking, wherein the dose prediction step involves using a machine learning system that has been trained to consider at least one optimality criterion related to physical or technical restrictions that will affect the delivery of the treatment plan. Thus, at least one of the factors that are normally taken into account in the dose mimicking step is introduced in the dose prediction step. The invention also relates to a method of training such a machine learning system for use in radiotherapy treatment planning, a computer program product and a computer system.

Method of generating a radiotherapy treatment plan for a patient, a computer program product, and a computer system comprising a machine learning system

A method () for generating a treatment plan specifying an irradiation of a patient, the method comprising: a dose inference stage (), including using a model to infer a spatial dose from patient data; a dose mimicking stage (), 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.

Automated treatment planning by dose prediction and robust dose mimicking

Growing community of inventors

BROMMA, Sweden

Hanna Gruselius