Abstract
OBJECTIVES: This study aimed to develop and evaluate multiple machine learning models utilizing contrast-enhanced T1-weighted imaging (T1-CE) to differentiate between low-/high-infiltration of total T lymphocytes (CD3) in patients with rectal cancer. METHODS: We retrospectively selected 157 patients (103 men, 54 women) with pathologically confirmed rectal cancer diagnosed between March 2015 and October 2019. The cohort was randomly divided into a training dataset (n=109) and a test dataset (n=48) for subsequent analysis. Seven radiomic features were selected to generate three models: logistic regression (LR), random forest (RF), and support vector machine (SVM). The diagnostic performance of the three models was compared using the DeLong test. Additionally, Kaplan-Meier analysis was employed to assess disease-free survival (DFS) in patients with high and low CD3+ tumor-infiltrating lymphocyte (TIL) density. RESULTS: The three radiomics models performed well in predicting the infiltration of CD3+ TILS, with area under the curve (AUC) values of 0.871, 0.982, and 0.913, respectively, in the training set for the LR, RF, and SVM models. In the validation set, the corresponding AUC values were 0.869, 0.794, and 0.837, respectively. Among the radiomics models, the LR model exhibited superior diagnostic performance and robustness. The merged model, which integrated radiomics features from the SVM model and clinical features from the clinical model, outperformed the individual radiomics models, with AUCs of 0.8932 and 0.8829 in the training and test cohorts, respectively. Additionally, a lower expression level of CD3+ TILs in the cohort was independently correlated with DFS (P = 0.0041). CONCLUSION: The combined model demonstrated a better discriminatory ability in assessing the abundance of CD3+ TILs in rectal cancer. Furthermore, the expression of CD3+ TILs was significantly correlated with DFS, highlighting its potential prognostic value. ADVANCES IN KNOWLEDGE: This study is the first attempt to compare the predictive TILs performance of three machine learning models, LR, RF, and SVM, based on the combination of radiomics and immunohistochemistry. The MRI-based combined model, composed of radiomics features from the SVM model and clinical features from the clinical model, exhibited better discriminatory capability for the expression of CD3+ TILs in rectal cancer.