Tackling the problem of diffusion in Fricke gels dosimeters through a physics informed neural network algorithm

The use of radiation in medical applications demands accurate dose measurements, particularly with the advent of high-dose rates and mini-beam fields. In this context, Fricke gels (FGs) are gaining interest for their tissue-equivalent properties. FGs rely on Fe2+ to Fe3+ oxidation upon radiation exposure, that can be quantified by MRI or optical absorption (OA) spectroscopy, enabling access to 3D dose distributions (DD). Ion diffusion brings to blurring effects in the recorded DD, limiting FG’s clinical utility. The process is governed by the diffusion equation and reconstructing the backward time DD leads to a challenging inverse problem. A promising solution is given by the physics-informed neural networks (PINNs), which integrate physical laws with machine learning to solve partial differential equations. In this study, we trained PINNs to predict pre-diffusion DD in 1D, 2D, and 3D FG models, exploiting diffused data up to 100 hours post-irradiation. Predictions were compared with OA data from irradiated PVA-GTA gel and simulated data. Predictions MSE (10−6–10−4 OD2) and gamma analysis (90–100% passing rate at 3%/2 mm) indicate the PINNs potential in overcoming FG limitations.