Description:
Objective. The aim of this work is an AI based approach to reduce the volume effect of ionizationchambers used to measure high energy photon beams in radiotherapy. In particular for profilemeasurements, the air-filled volume leads to an inaccurate measurement of the penumbra. Approach.The AI-based approach presented in this study was trained with synthetic data intended to cover awide range of realistic linear accelerator data. The synthetic data was created by randomly generatingprofiles and convolving them with the lateral response function of a Semiflex 3D ionization chamber.The neuronal network was implemented using the open source tensorflow.keras machine learningframework and a U-Net architecture. The approach was validated on three accelerator types (VarianTrueBeam, Elekta VersaHD, Siemens Artiste) at FF and FFF energies between 6 MV and 18 MV atthree measurement depths. For each validation, a Semiflex 3D measurement was compared against amicroDiamond measurement, and the AI processed Semiflex 3D measurement was compared againstthe microDiamond measurement. Main results. The AI approach was validated with datasetcontaining 306 profiles measured with Semiflex 3D ionization chamber and microDiamond. In 90%of the cases, the AI processed Semiflex 3D dataset agrees with the microDiamond dataset within 0.5mm/2% gamma criterion. 77% of the AI processed Semiflex 3D measurements show a penumbradifference to the microDiamond of less than 0.5 mm, 99% of less than 1 mm. Significance. This AIapproach is the first in the field of dosimetry which uses synthetic training data. Thus, the approach isable to cover a wide range of accelerators and the whole specified field size range of the ionizationchamber. The application of the AI approach offers an quality improvement and time saving formeasurements in the water phantom, in particular for large field sizes