To develop a radiomics model based on contrast-enhanced CT (CECT) to predict the lymphovascular invasion (LVI) in esophageal squamous cell carcinoma (ESCC) and provide decision-making support for clinicians.
This retrospective study enrolled 334 patients with surgically resected and pathologically confirmed ESCC, including 96 patients with LVI and 238 patients without LVI. All enrolled patients were randomly divided into a training cohort and a testing cohort at a ratio of 7:3, with the training cohort containing 234 patients (68 patients with LVI and 166 without LVI) and the testing cohort containing 100 patients (28 patients with LVI and 72 without LVI). All patients underwent preoperative CECT scans within 2 weeks before operation. Quantitative radiomics features were extracted from CECT images, and the least absolute shrinkage and selection operator (LASSO) method was applied to select radiomics features. Logistic regression (Logistic), support vector machine (SVM), and decision tree (Tree) methods were separately used to establish radiomics models to predict the LVI status in ESCC, and the best model was selected to calculate Radscore, which combined with two clinical CT predictors to build a combined model. The clinical model was also developed by using logistic regression. The receiver characteristic curve (ROC) and decision curve (DCA) analysis were used to evaluate the model performance in predicting the LVI status in ESCC.
In the radiomics model, Sphericity and gray-level non-uniformity (GLNU) were the most significant radiomics features for predicting LVI. In the clinical model, the maximum tumor thickness based on CECT (cThick) in patients with LVI was significantly greater than that in patients without LVI (P<0.001). Patients with LVI had higher clinical N stage based on CECT (cN stage) than patients without LVI (
The combined model incorporating radiomics features and clinical CT predictors may potentially predict the LVI status in ESCC and provide support for clinical treatment decisions.