Methods and system related to radiotherapy treatment planning
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.
1 . A computer-based method, executed on a radiotherapy treatment planning system, comprising:
inputting to a machine learning system a plurality of historical data sets, each data set including a dose distributions and a corresponding set of machine parameter settings used to deliver the dose distributions;
training the machine learning system, based on the historical data sets, to generate machine parameter settings from a reference dose distribution, wherein the machine parameter settings correspond to initialization values used by a radiotherapy treatment plan optimization algorithm;
generating, using the trained machine learning system, an initial set of machine parameter settings from a reference dose distribution associated with a patient, the initial set being directly usable as initialization values for the radiotherapy treatment plan optimization algorithm;
automatically initializing, using the generated initial machine parameter settings, a radiotherapy treatment plan optimization algorithm that simulates radiation beam paths using the initialization values and adjusts machine parameters to satisfy patient-specific dosimetric objectives and constraints; and
outputting the optimized radiotherapy treatment plan, including the adjusted machine parameter settings, in a format executable by a radiotherapy apparatus to deliver the prescribed dose distribution to the patient.
2 . A machine learning system which has been trained according to claim 1 , the machine learning system being arranged to take input data in the form of one or more desired reference dose distributions and output a set of machine parameter settings including at least one machine parameter setting that is suitable for producing the one or more desired reference dose distribution by the radiotherapy delivery apparatus.
3 . A computer-based method for determining machine parameter settings for a radiotherapy delivery apparatus, using a machine learning system according to claim 2 , the method comprising:
inputting one or more reference dose distributions into the machine learning system;
initializing parameters, by the machine learning system; and
outputting, from the machine learning system, a set of machine parameter settings for the radiotherapy delivery apparatus.
4 . The method of claim 3 , wherein the set of machine parameter settings includes Multi Leaf Collimator leaf settings.
5 . The method of claim 3 , wherein the set of machine parameter settings includes Monitor Unit settings.
6 . The method of claim 3 , wherein the set of machine parameter settings includes one or more of spot placement, spot weights and beam energy.
7 . A method for computer-based radiotherapy treatment plan optimization method including, before performing the plan optimization, performing the method of determining machine parameter settings according to claim 3 and using the resulting at least one machine parameter setting as an initial setting for that machine parameter in the radiotherapy treatment plan optimization.
8 . The method of claim 7 , wherein the plan optimization is performed by optimizing an optimization problem.
9 . The method of claim 8 , wherein the plan optimization is performed by dose mimicking.
10 . A computer program product comprising computer-readable code means which, when run in a computer will cause the computer to perform the method of claim 1 .
11 . A computer program product comprising non-transitory storage means having stored thereon computer-readable code means which, when run in a computer will cause the computer to perform the method of claim 1 .
12 . A computer system comprising a processor and a program memory, the program memory having stored thereon a computer program product according to claim 10 .