Automatic beam modeling based on deep learning

A system for generating a beam model for a radiation therapy treatment plan used to treat a patient via a radiation therapy device, the system comprising:

• a training module configured to:
• access simulated machine scanning data measured in a radiation simulation by the radiation therapy device programmed with known values of a plurality of beam model parameters;
• interpolate or extrapolate the simulated machine scanning data at a finer resolution of depth or a finer resolution of field size;
• construct a set of training data comprising data samples taken from the simulated machine scanning data and the interpolated or extrapolated simulated machine scanning data;
• and
• train a deep learning model using the set of training data and the known values of the plurality of beam model parameters;
• a memory to store the trained deep learning model and the plurality of beam model parameters;
• and
• a processor circuit configured to:
• receive machine scanning data indicative of a configuration or an operation status of the radiation therapy device;
• apply the received machine scanning data to the trained deep learning model to determine values for the plurality of beam model parameters;
• generate a beam model based on the determined values of the plurality of beam model parameters;
• and
• store the beam model in the memory accessible by a user or a treatment planning system.