CT-based radiomics analysis for differentiation between thymoma and thymic carcinoma

Area of Science:

• Radiology
• Medical Imaging
• Oncology

Background:

• Thymic epithelial tumors (TETs) encompass thymoma and thymic carcinoma, requiring accurate differentiation for treatment.
• Distinguishing between thymoma and thymic carcinoma based on imaging can be challenging.

Purpose of the Study:

• To differentiate thymoma from thymic carcinoma using radiomics analysis of computed tomography (CT) features.
• To identify optimal radiomics features for predicting thymic carcinoma.

Main Methods:

• Analysis of contrast-enhanced CT images from 61 patients with TETs.
• Extraction and filtering of 61 radiomics features using least absolute shrinkage and selection operator (LASSO) regression.
• Logistic regression and receiver-operating characteristic (ROC) curve analysis to evaluate diagnostic performance.

Main Results:

• Thymic carcinoma was more prevalent in men.
• Key radiomics features for predicting thymic carcinoma included solidity and GLCM-energy.
• Multivariate analysis identified solidity and GLCM-energy as independent predictors, yielding an adjusted area under the curve (AUC) of 0.921.

Conclusions:

• Solidity and GLCM-energy are significant texture features for predicting thymic carcinoma.
• Radiomics analysis demonstrates high diagnostic performance in differentiating thymic carcinoma from thymoma.