Analysis of EPID Transmission Fluence Maps Using Machine Learning Models and CNN for Identifying Position Errors in the Treatment of GO Patients

Abstract

PurposeTo find a suitable method for analyzing electronic portal imaging device (EPID) transmission fluence maps for the identification of position errors in the in vivo dose monitoring of patients with Graves’ ophthalmopathy (GO).MethodsPosition errors combining 0-, 2-, and 4-mm errors in the left-right (LR), anterior-posterior (AP), and superior-inferior (SI) directions in the delivery of 40 GO patient radiotherapy plans to a human head phantom were simulated and EPID transmission fluence maps were acquired. Dose difference (DD) and structural similarity (SSIM) maps were calculated to quantify changes in the fluence maps. Three types of machine learning (ML) models that utilize radiomics features of the DD maps (ML 1 models), features of the SSIM maps (ML 2 models), and features of both DD and SSIM maps (ML 3 models) as inputs were used to perform three types of position error classification, namely a binary classification of the isocenter error (type 1), three binary classifications of LR, SI, and AP direction errors (type 2), and an eight-element classification of the combined LR, SI, and AP direction errors (type 3). Convolutional neural network (CNN) was also used to classify position errors using the DD and SSIM maps as input.ResultsThe best-performing ML 1 model was XGBoost, which achieved accuracies of 0.889, 0.755, 0.778, 0.833, and 0.532 in the type 1, type 2-LR, type 2-AP, type 2-SI, and type 3 classification, respectively. The best ML 2 model was XGBoost, which achieved accuracies of 0.856, 0.731, 0.736, 0.949, and 0.491, respectively. The best ML 3 model was linear discriminant classifier (LDC), which achieved accuracies of 0.903, 0.792, 0.870, 0.931, and 0.671, respectively. The CNN achieved classification accuracies of 0.925, 0.833, 0.875, 0.949, and 0.689, respectively.ConclusionML models and CNN using combined DD and SSIM maps can analyze EPID transmission fluence maps to identify position errors in the treatment of GO patients. Further studies with large sample sizes are needed to improve the accuracy of CNN.

Research progress and application of artificial intelligence in thyroid associated ophthalmopathy

“…Their AUC values were all above 0.90 for position error detection and relatively lower (0.76, 0.80, and 0.91) for direction identification. The research team classified all the position and direction errors into three types ( Dai et al, 2021 ). The aforementioned ML models plus a CNN model were also applied to recognize these errors using radiomics data from EPID transmission maps as inputs.…”

Relevant Characteristics Analysis Using Natural Language Processing and Machine Learning Based on Phenotypes and T-Cell Subsets in Systemic Lupus Erythematosus Patients With Anxiety

“…We matched clinical information, laboratory indicators, disease phenotypes, and cell subpopulation data separately to construct five types of original data sets. Then, the use of the original data sets was compared and the oversampling and the algorithm of Syntic priority oversampling technology (SMOTE) methods (22) which was used to make up for the imbalance in the number of cases included in the data set on various models, including Lasso regression (LR) (23), Random Forest (RF) (22) and XGBoost (24). When applying the oversampling and SMOTE method, the (see Supplementary Table 1).…”

The innovative model based on artificial intelligence algorithms to predict recurrence risk of patients with postoperative breast cancer

“…Furthermore, artificial neural networks (ANN) comprise a fundamental component of deep learning algorithms, demonstrating great potential in building high prediction accuracy (12)(13)(14)(15). Currently, AI algorithms have proven successful in processing clinical image data, obtaining desired prediction results (16)(17)(18). For example, a two-stage convolutional neural network (CNN) model was proposed to predict the occurrence of myocardial infarction and localize the site of infarction based on vectorcardiogram signals (19).…”