Corrections of photon beam profiles of small fields measured with ionization chambers using a three‐layer neural network

Abstract

The purpose of this work is to study the feasibility of photon beam profile deconvolution using a feedforward neural network (NN) in very small fields (down to 0.56 × 0.56 cm 2 ). The method's independence of the delivery and scanning system is also investigated. Lateral beam profiles of photon fields between 0.56 × 0.56 cm 2 and 4.03 × 4.03 cm 2 were collected on a Siemens Artiste linear accelerator. Three scanning ionization chambers (SNC 125c, PTW 31021, and PTW 31022) of sensitive volumes ranging from 0.016 cm 3 to 0.108 cm 3 were used with a PTW MP3 water phantom. A reference dataset was also collected with a PTW 60019 microDiamond detector to train and test individual NNs for each ionization chamber. Further testing of the trained NNs was performed with additional test data collected on an Elekta Synergy linear accelerator using a Sun Nuclear 3D Scanner. The results were evaluated with a 1D gamma analysis (0.5 mm/0.5%). After the deconvolution, the gamma passing rates increased from 54.79% to 99.58% for the SNC 125c, from 57.09% to 99.83% for the PTW 31021, and from 91.03% to 96.36% for the PTW 31022. The delivery system, the scanning system, the scanning mode (continuous vs. step-by-step), and the electrometer had no significant influence on the results. This study successfully demonstrated the feasibility of using NN to correct the beam profiles of very small photon fields collected with ionization chambers of various sizes. Its independence of the delivery and scanning system was also shown.

Artificial intelligence based deconvolving on megavoltage photon beam profiles for radiotherapy applications

“…However, the neural network was trained exactly on the accelerator and the training data was a subset of the data used for validation. The same applies to the publications by Mund et al (2020Mund et al ( , 2021, Schönfeld et al (2021). Also in these studies, direct measurement data were used for training.…”

“…The other approach to solve the penumbra problem is an AI-based solution. Several studies (Liu et al 2018, Mund et al 2020, Schönfeld et al 2021 have demonstrated an AI-based approach where an AI was trained with a training dataset of profile data measured with an ionization chamber as well as undisturbed profile measurements measured with a silicon detector. However, this approach requires a huge amount of training data, which has to cover many different conditions, such as energy, depth, accelerator type to avoid overfitting.…”

Monte Carlo modeling of the 160 MLC on the Siemens Artiste linac and IMRT dose calculations with MCNPX

“…Thus, several researchers have modelled various linac machines using MC simulation. For these simulations, general purpose MC software like EGSnrc [33][34][35], GEANT4 [36][37][38][39], PENELOPE [40][41][42], MCNP [43][44][45][46], … have been widely used [47][48][49][50].…”

“…Artiste linac offers a comprehensive collection of advanced capabilities including image-guided protocols and treatment delivery modalities. Although Siemens left the radiotherapy market, this machine is still used in many radiotherapy departments [49][50][51] especially in the west Asia and other developing countries. Many radiotherapy and oncology centers in our region are currently using this model of linear accelerator to perform their clinically routine treatments [52][53][54].…”

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

“…Recently, the recovery of the dose profile from measured signal profile using a feed-forward artificial neural network (NN) has been demonstrated (Liu et al 2018). The application of NN has been generalized to other beam qualities (Mund et al 2020) and smaller field sizes (Schönfeld et al 2021) showing promising results. Nevertheless, large dataset is usually necessary to feed the training process of these NN.…”