Machine-learning modeling to generate virtual bolus attributes

A system comprising:

• a server comprising a processor and a non-transitory computer-readable medium containing instructions that when executed by the processor causes the processor to perform operations comprising:
• executing a machine-learning model using a medical image not used to train the machine-learning model to predict an attribute of a non-anatomical region for the medical image, the non-anatomical region being located on an outer surface of a patient, wherein the machine-learning model has been trained using a set of medical images corresponding to a set of previously performed radiation therapy treatments, each medical image comprising at least one planning target volume and an added non-anatomical region for its respective radiation therapy treatment.