Measurement of linear accelerator spectra, reconstructed from percentage depth dose curves by neural networks.

Purpose Linear accelerator (linac) spectra, used to improve the accuracy of dose calculation and to produce a complete description of beam quality, among other aspects, are relevant in radiotherapy and linear accelerator physics. Methods In this work we apply neural networks in solving an ill-conditioned system of linear equations, to indirectly measure the linear accelerator spectra via the percentage depth dose curves. The photon beam spectra are related to radiation doses through a Fredholm integral equation. To address our problem we measured the percentage depth dose curve in water and solved a discretized Fredholm equation using artificial neural network. After analysing the typology of our physical problem we selected a MultiLayer Perceptron Neural Network and designed the most suitable neural network architecture. Results The reconstructed spectra were compared with spectra from three linacs, two of them obtained by us through simulations and the third produced by another author, achieving a concordance between 92 % and 96 %. Conclusions Therefore, the spectrum of any accelerator can be quickly and easily reconstructed from measured percent depth dose curves, applying a trained artificial neural network.

A novel and fast methodology to calculate doses in LDR brachytherapy.

We present the concept of a new methodology for faster simulation of the doses in brachytherapy with permanent implants, based on the knowledge of the seeds arrangement, adding previously simulated doses in an equivalent medium in terms of the atomic composition of the organ in question. To perform the doses calculations we use Monte Carlo simulations. We simulated a cylindrical I-125 seed and compared our results against published data. Our proposal is to have the doses simulated previously in different arrangement of seed-absorbents, and then, considering the spacial positions of the seeds after the implants, these doses can be directly added, obtaining a very fast computation of the total dose. Two phantoms of prostates with permanent implant seeds in 2D and 3D arrangements were simulated. The results of the proposed methodology were compared with two complete Monte Carlo simulations in 2D and 3D designs. Differences in doses were analysed, obtaining statistical discrepancies of less than 1% and reducing the simulation time by more than 4 orders of magnitude. With the proposed methodology, it is possible to perform rapid dose calculations in brachytherapy, using laptop or desktop computers.