AUTHOR=Hu Ling , Jin Peile , Xu Wen , Wang Chao , Huang Pintong TITLE=Clinical and radiomics integrated nomogram for preoperative prediction of tumor-infiltrating lymphocytes in patients with triple-negative breast cancer JOURNAL=Frontiers in Oncology VOLUME=Volume 14 - 2024 YEAR=2024 URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2024.1370466 DOI=10.3389/fonc.2024.1370466 ISSN=2234-943X ABSTRACT=Objectives Tumor-infiltrating lymphocytes (TILs) have become a promising biomarker for predicting immunotherapy response in triple-negative breast cancer (TNBC). This study aimed to develop a radiomics nomogram based on conventional ultrasound (CUS) to preoperatively distinguish high TILs and low TILs in TNBC patients.A retrospective analysis of 145 TNBC patients confirmed by pathology was conducted. Pathological evaluation of TILs in the hematoxylin and eosin sections was set as the gold standard. The patients were divided randomly into training and validation datasets with a 7:3 ratio. Clinical features (age and CUS features) and radiomics features were collected. Then, the Rad-score model was constructed after the radiomics feature selection. The clinical features model and clinical features plus Rad-score (Clin+RS) model were built using logistic regression analysis. The models were assessed using the receiver operating characteristic (ROC) curve analysis, calibration curve, and decision curve analysis (DCA). Results Twenty-five radiomics features were selected using univariate analysis and LASSO regression from 837 radiomics features and Rad-score was calculated. The Clin+RS integrated model, which incorporated posterior echo and Rad-score, achieved an AUC value of 0.848 in the training dataset and 0.847 in the validation dataset, outperforming the predictive performance of both the Rad-score model and clinical model. Conclusion The Clin+RS integrated model, incorporating posterior echo and Rad-score, showed a satisfactory preoperative prediction of the TIL level. The Clin+RS integrated nomogram holds tremendous potential for preoperative individualized prediction of the TIL level in TNBC.