CT Imaging-based Radiomics Predicts the Therapeutic Efficacy of 89 Sr in Treating Tumor-Induced Bone Metastases

Abstract

Abstract Background Bone metastasis is a frequent complication in advanced malignancies, leading to severe pain and reduced quality of life. Radiopharmaceuticals like Strontium-89 (89Sr) are commonly used to treat bone pain and metastasis. This study explores the potential of radiomics analysis in predicting the effectiveness of 89Sr treatment for patients with bone metastases. Methods The study analyzed clinical and imaging data from 146 patients with bone metastases, specifically focusing on two types of lesions: osteolytic and osteoblastic. Pain relief is judged by the ladder on which the patient takes painkillers. For osteolytic lesions, a Bagging Decision Tree machine learning model was employed for outcome prediction, while the XGBOOST model was utilized for osteoblastic lesions. Both models leveraged radiomics features extracted from these lesions to improve predictive accuracy. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, and calibration curves. Results In this study, the effective rate of osteolytic metastasis was 58.33%, and the treatment rate of osteolytic metastasis was 62.16%.The Bagging Decision Tree model demonstrated excellent performance in the training set for osteolytic lesions, achieving an AUC of 0.991, though it showed a slightly reduced AUC of 0.889 in the test set. For osteoblastic lesions, the XGBOOST model yielded robust results, with AUC of 0.970 in the training set and 0.958 in the test set. Conclusion 89Sr is not only effective for osteoblastic bone metastasis, but also for osteolytic bone metastasis. This study demonstrates the value of radiomics analysis in accurately predicting the efficacy of 89Sr treatment in bone metastases. This approach aims to more precisely forecast treatment responses, aiding in the optimization of patient care strategies.