Prediction of Dose Length Product for chest CT Examinations using Artificial Neural Networks (ANN)

Abstract

This study aimed to design an Artificial Neural Network modelling to estimate the remarkable dose length product (DLP) value during the chest computed tomography (CT) examinations for quality assurance in a retrospective, cross-sectional study. The structure of artificial neural networks model was designed considering various input parameters, namely patient weight, patient size, body mass index, mean CT dose index, scanning length, kVp, mAs, exposure time per rotation and pitch factor. The examination details of 1897 chest CT scans were used as retrospective data. Different types of learning algorithms such as Levenberg-Marquardt, Bayesian and Scaled-Conjugate Gradient were checked in terms of the accuracy of the test data. The R-value or the test data was representing the correlation coefficient for the real system and system output is given as 0.97328, 0.82263 and 0.90574 for the Levenberg-Marquardt, Bayesian and Scaled-Conjugate Gradient algorithms, respectively. The findings showed that the Levenberg-Marquardt algorithm comprehensively detects DLP values for chest CT examinations. To meet CT efficiency standards, it may be an effective to use simplified methodology. It can be deduced that artificial intelligence methods can be used to perform high precision DLP on the chest CT exams where the radiation-related risks are particularly great or highly relevant for patients. This type of approaches are effective instruments and can be applied to risk evaluations in the field of diagnostic radiology.

Investigating the Effect of Patient-Related Factors on Computed Tomography Radiation Dose Using Regression and Correlation Analysis

“…For example, the work in [35] explored deriving SSDE from BMI. Moreover, artificial neural networks (ANNs) were used to estimate the DLP in chest CT examinations [36], while convolutional neural networks (CNNs) were used to estimate SSDE in CT medical examinations [37]. In [22], several regression predictive models were used to predict the patient's CT dose in various CT protocols.…”