Application of MLP neural network to predict X-ray spectrum from tube voltage, filter material, and filter thickness used in medical imaging systems

Abstract

The X-ray energy spectrum is crucial for image quality and dosage assessment in mammography, radiography, fluoroscopy, and CT which are frequently used for the diagnosis of many diseases including but not limited to patients with cardiovascular and cerebrovascular diseases. X-ray tubes have an electron filament (cathode), a tungsten/rubidium target (anode) oriented at an angle, and a metal filter (aluminum, beryllium, etc.) that may be placed in front of an exit window. When cathode electrons meet the anode, they generate X-rays with varied energies, creating a spectrum from zero to the electrons’ greatest energy. In general, the energy spectrum of X-rays depends on the electron beam’s energy (tube voltage), target angle, material, filter thickness, etc. Thus, each imaging system’s X-ray energy spectrum is unique to its tubes. The primary goal of the current study is to develop a clever method for quickly estimating the X-ray energy spectrum for a variety of tube voltages, filter materials, and filter thickness using a small number of unique spectra. In this investigation, two distinct filters made of beryllium and aluminum with thicknesses of 0.4, 0.8, 1.2, 1.6, and 2 mm were employed to obtain certain limited X-ray spectra for tube voltages of 20, 30, 40, 50, 60, 80, 100, 130, and 150 kV. The three inputs of 150 Multilayer Perceptron (MLP) neural networks were tube voltage, filter type, and filter thickness to forecast the X-ray spectra point by point. After training, the MLP neural networks could predict the X-ray spectra for tubes with voltages between 20 and 150 kV and two distinct filters made of aluminum and beryllium with thicknesses between 0 and 2 mm. The presented methodology can be used as a suitable, fast, accurate and reliable alternative method for predicting X-ray spectrum in medical applications. Although a technique was put out in this work for a particular system that was the subject of Monte Carlo simulations, it may be applied to any genuine system.

An indirect estimation of x-ray spectrum via convolutional neural network and transmission measurement

“…The proposed CNN-based method is a self-supervised learning method and is easy to implement. Recent studies using deep learning to estimate x-ray energy spectra have been conducted (Zhang et al 2019, Hasegawa et al 2021, He et al 2023, Higuchi and Haga 2023. By utilizing the fact that different spectra result in various CT reconstructed images, a CNN and artificial neural network (ANN) were created to indirectly estimate the spectrum using CT images (Zhang et al 2019, Higuchi andHaga 2023).…”

“…However, this method requires training based on simulating many mPDDs using MC. Utilizing a radial basis function neural network or multilayer perceptron (MLP) neural network to replace MC is a direct way to predict the energy spectrum by inputting tube voltage, filter type, and thickness (He et al 2023. However, the parameters of a real scan head are difficult to obtain, and the real energy spectrum may be affected by other external factors.…”

“…Deep learning provides another viable approach to energy spectrum estimation. This type of method usually used CT images (Zhang et al 2019, Higuchi andHaga 2023), percentage depth dose (PDD) (Hasegawa et al 2021), tube parameters (He et al 2023, or electron beam properties (Li et al 2023) as model inputs, and outputs the desired spectrum via model training. However, these studies require big data to learn comprehensive prior knowledge between inputs and outputs.…”