Magnetic resonance imaging-based radiomics assesses the level of immune cell infiltration in the breast cancer tumor microenvironment

Purpose: The tumor immune microenvironment provides information regarding prognosis and prediction. To screen the immune cells associated with the prognosis of breast cancer (BRCA) patients from the Cancer Genetic Atlas (TCGA) and establish an MRI-based radiomics model for evaluating the level of immune cell infiltration in breast cancer patients. Methods: CIBERSORT was used to assess the level of infiltration of 22 immune cell types from retrospective data of 1096 breast cancer patients from the TCGA database, and univariate and multivariate Cox regressions were applied to assess the prognostic value of the level of immune cell infiltration in BRCA patients to obtain independent prognostic factors for BRCA patients. We extracted imaging features from the Cancer Imaging Archive (TCIA) database for 73 patients with preoperative MRI data. The best imaging features were selected using the Least absolute shrinkage and selection operator (LASSO) to establish an MRI-based radiomics model for evaluating the level of immune cell infiltration in breast cancer patients. Results: M2 macrophages were found to be an independent prognostic factor for BRCA patients based on the results of Cox regression analysis (HR=32.288, 95% CI: 3.100-357.478). A total of nine important features were selected for calculating radscore, A intratumoral model was established with AUCs (95% CI) of 0.662 (0.495-0.802) and 0.678 (0.438-0.901) in the training and testing cohorts, respectively. A peritumoral model was established with AUCs (95% CI) of 0.826 (0.710-0.924) and 0.752 (0.525-0.957). A combined model was established with AUCs (95% CI) of 0.843 (0.723-0.938) and 0.744 (0.491-0.965). The peritumoral model had the highest diagnostic efficacy, with accuracy, sensitivity and specificity of 0.773, 0.727 and 0.818 respectively in its testing cohort. Conclusion: MRI-based radiomics model may evaluate the level of immune cell infiltration in breast cancer and might provide a non-invasive imaging biomarker for the assessment of the tumor microenvironment in breast cancer.