Abstract P5-02-35: Radiomic biomarkers to predict the efficacy of anti-PD-1 immunotherapy-based combinational treatment in advanced breast cancer: a multi-center study

Abstract

Abstract Introduction: Immunotherapy, especially immune checkpoint inhibitors, is regarded as one of the major breakthroughs in breast cancer treatment. However, it is an important challenge to accurately locate the patients who benefit from immunotherapy, because there is still a lack of universal and robust predictors of the efficacy of immunotherapy. Radiomics can extract quantitative imaging features in a highthroughput manner and assess tumor microenvironment and heterogeneity. This study investigated the correlation between deep learning radiomic biomarkers, including its predictive value for immunotherapy response in advanced breast cancer (ABC) patients. Methods: 240 patients with metastatic breast cancer treated with anti-PD-1 immunotherapy in three institutions from February 2018 to January 2022 were studied retrospectively, among which, the data of 61 patients were collected through prospective clinical trials. For these data, 189 ABC patients from prospective clinical trials and Sun Yat-sen University Cancer Center were evaluated as a training set to establish a radiomic model to predict value of immunotherapy, then this model was independently validated with 51 ABC patients from Sun Yat-sen Memorial Hospital. The CE-CT (contrast enhanced computed tomography) images of patients within one month before immunotherapy were were delineated with regions of interest (ROI) and radiomics features extraction. Data dimension reduction, feature selection and radiomic model construction were carried out with multilayer perceptron (MLP) deep learning. Combined with the radiomics signatures, independent clinical characteristics and pathological risk factors, the predictive model was established by multivariable logistic regression analysis. ROC curve (receiver operator area under receiver operator area, AUC) and Delong test were used to evaluate and compare the prediction performance of the model. Finally, decision curve analysis (DCA) is used to determine the net benefits predicted by the model. Results: The radiomic biomarker performed well in predicting response to immunotherapy, reflflected by the AUCs in the training set(AUC=0.885, 95% CI: 0.829-0.941) and validation set (AUC=0.871, 95% CI: 0.752-0.991), respectively. The accuracy of this radiomics model was better than those of clinical indicators, including PD-L1 expression. Conclusions: By combining deep learning technology and CT images and PD-L1 expression, we developed an independent predictive model that could identify MBC patients most likely to benefifit from immunotherapy, and may effectively improve more precise and individualized decision support. Citation Format: Jieqiong Liu, Jianli Zhao, Zhixian Sun, Yunfang Yu, Zhongyu Yuan, Herui Yao, Ying Wang. Radiomic biomarkers to predict the efficacy of anti-PD-1 immunotherapy-based combinational treatment in advanced breast cancer: a multi-center study [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P5-02-35.