Model-based machine learning for the recovery of lateral dose profiles of small photon fields in magnetic field.

. To investigate the feasibility to train artificial neural networks (NN) to recover lateral dose profiles from detector measurements in a magnetic field.. A novel framework based on a mathematical convolution model has been proposed to generate measurement-less training dataset. 2D dose deposition kernels and detector lateral fluence response functions of two air-filled ionization chambers and two diode-type detectors have been simulated without magnetic field and for magnetic field = 0.35 and 1.5 T. Using these convolution kernels, training dataset consisting pairs of dose profilesDx,yand signal profilesMx,ywere computed for a total of 108 2D photon fluence profilesψ(x,y)(80% training/20% validation). The NN were tested using three independent datasets, where the second test dataset has been obtained from simulations using realistic phase space files of clinical linear accelerator and the third test dataset was measured at a conventional linac equipped with electromagnets. Main. The convolution kernels show magnetic field dependence due to the influence of the Lorentz force on the electron transport in the water phantom and detectors. The NN show good performance during training and validation with mean square error reaching a value of 1e-6 or smaller. The corresponding correlation coefficientsreached the value of 1 for all models indicating an excellent agreement between expectedDx,yand predictedDpredx,y.The comparisons betweenDx,yandDpredx,yusing the three test datasets resulted in gamma indices (1 mm/1% global) <1 for all evaluated data points.. Two verification approaches have been proposed to warrant the mathematical consistencies of the NN outputs. Besides offering a correction strategy not existed so far for relative dosimetry in a magnetic field, this work could help to raise awareness and to improve understanding on the distortion of detector's signal profiles by a magnetic field.