Raysearch Laboratories Ab

Raysearch Laboratories Ab (publ)

Fredrik Löfman

Kjell Eriksson

Rasmus Bokrantz

Hanna Gruselius

Marco Trincavelli

Giorgio Ruffa

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

Better Pareto dose distributions for multi-criteria optimization of treatment plans can be obtained by obtaining at least one reference dose function designed to result in an acceptable reference dose distribution, defining a multi-criteria optimization problem including the at least one reference dose function as at least one optimization function, performing at least two optimization procedures based on the multi-criteria optimization problem to generate a set of at least two possible treatment plans, obtaining a treatment plan to be used for treating the patient, based on the set of possible treatment plans, by selecting one plan or by combining plans.

System, computer program product and method for radiation therapy treatment planning

Growing community of inventors

Lidingö, Sweden

Fredrik Löfman