Deep learning-based and BI-RADS guided radiomics model for automatic tumor-infiltrating lymphocytes evaluation in breast cancer.

Abstract

To investigate an interpretable radiomics model consistent with clinical decision-making process and realize automatic prediction of tumor-infiltrating lymphocytes (TILs) levels in breast cancer (BC) from ultrasound (US) images. A total of 378 patients with invasive BC confirmed by pathological results were retrospectively enrolled in this study. Radiomics features were extracted guided by the BI-RADS lexicon from the regions of interest(ROIs) segmented with deep learning models. After features selected using the least absolute shrinkage and selection operator(LASSO) regression, four machine learning classifiers were used to establish the radiomics signature(Rad-score). Then, the integrated model was developed on the basis of the best Rad-score incorporating the independent clinical factors for TILs levels prediction. Tumors were segmented using the deep learning models with accuracy of 97.2%, sensitivity of 93.4%, specificity of 98.1%, and the posterior areas were also obtained. Eighteen morphology and texture related features were extracted from the ROIs and fourteen features were selected to construct the Rad-score models. Combined with independent clinical characteristics, the integrated model achieved an area under the curve (AUC) of 0.889(95% CI,0.739,0.990) in the validation cohort and outperformed the traditional radiomics model with AUC of 0.756(0.649-0862) depended on hundreds of feature items. This study established a promising model for TILs levels prediction with numerable interpretable features and showed great potential to help decision-making and clinical applications. Imaging-based biomarkers has provides non-invasive ways for TILs levels evaluation in BC. Our model combining the BI-RADS guided radiomics features and clinical data outperformed the traditional radiomics approaches.