[<sup>18</sup>F]FDG PET/CT Radiomics for Predicting Pathological Risk Subtypes of Thymic Epithelial Tumors: A Bicentric Study.
Authors
Affiliations (7)
Affiliations (7)
- Department of Thoracic Surgery, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, Italy.
- Unit of Artificial Intelligence and Computer Systems, Department of Engineering, Università Campus Bio-Medico di Roma, 00128 Rome, Italy.
- Nuclear Medicine Unit, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, Italy.
- Thoracic Surgery Unit, Cardiothoracic and Vascular Department, University Hospital of Pisa, 56124 Pisa, Italy.
- Unit of Diagnostic Imaging and Interventional Radiology, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, Italy.
- Department of Diagnostics and Intervention, Radiation Physics, Biomedical Engineering, Umeå University, 901 87 Umeå, Sweden.
- Unit of Thoracic Surgery, Department of Pharmacy and Health and Nutrition Sciences, University of Calabria, 87036 Rende, Italy.
Abstract
<b>Background:</b> Thymic epithelial tumors (TETs) are rare mediastinal malignancies whose prognosis is largely determined by histology. Current predictive models rely on clinical variables and subjective imaging interpretation, with unsatisfied performance. Non-invasive pre-treatment risk stratification could guide surgical planning and perioperative management in patients with TETs. The role of fluorine-18 (<sup>18</sup>F) fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (CT) in identifying aggressive disease is increasingly recognized. In this bicentric study, we aimed to evaluate a machine learning-based radiomics model using PET and CT images to differentiate between low-risk and high-risk TETs. <b>Methods:</b> Seventy-five patients who underwent PET/CT to evaluate the suspected anterior mediastinal mass and histopathologically diagnosed with TETs were included. On PET/CT images, the tumor was manually segmented by two experienced clinicians. First-order, shape, and texture features were extracted using the PyRadiomics library, resulting in 200 radiomics features (186 intensity/texture features and 14 shape features). In addition, rPET (i.e., tumor SUVmax/Liver SUVmax) parameter was included, yielding a grand total of 201 features. The feature set was reduced to 20 variables using ANOVA, with both selection and model evaluation performed via stratified 5-fold cross-validation. <b>Results:</b> The proposed approach achieved an average balanced accuracy of 0.58 ± 0.07 and an average AUC of 0.71 ± 0.04. Average sensitivity and specificity were 0.48 and 0.68, respectively. The model obtained an average Gmean of 0.57, indicating balanced and stable classification performance. <b>Conclusions:</b> Our ML models trained on PET/CT radiomic features showed moderate discriminatory performance for TET risk stratification.