Prediction of treatment response in patients with brain metastasis receiving stereotactic radiosurgery based on pre-treatment multimodal MRI radiomics and clinical risk factors: A machine learning model

Peng Du; Xiao Liu; Li Shen; Xuefan Wu; Jiawei Chen; Lang Chen; Aihong Cao; Daoying Geng

doi:10.3389/fonc.2023.1114194

Prediction of treatment response in patients with brain metastasis receiving stereotactic radiosurgery based on pre-treatment multimodal MRI radiomics and clinical risk factors: A machine learning model

Front Oncol. 2023 Mar 13:13:1114194. doi: 10.3389/fonc.2023.1114194. eCollection 2023.

Authors

Peng Du^{1

2}, Xiao Liu³, Li Shen⁴, Xuefan Wu⁵, Jiawei Chen², Lang Chen¹, Aihong Cao¹, Daoying Geng²

Affiliations

¹ The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China.
² Huashan Hospital, Fudan University, Shanghai, China.
³ School of Computer and Information Technology, Beijing, China.
⁴ Department of Radiology, Jiahui International Hospital, Shanghai, China.
⁵ Department of Radiology, Shanghai Gamma Hospital, Shanghai, China.

Abstract

Objectives: Stereotactic radiosurgery (SRS), a therapy that uses radiation to treat brain tumors, has become a significant treatment procedure for patients with brain metastasis (BM). However, a proportion of patients have been found to be at risk of local failure (LF) after treatment. Hence, accurately identifying patients with LF risk after SRS treatment is critical to the development of successful treatment plans and the prognoses of patients. To accurately predict BM patients with the occurrence of LF after SRS therapy, we develop and validate a machine learning (ML) model based on pre-treatment multimodal magnetic resonance imaging (MRI) radiomics and clinical risk factors.

Patients and methods: In this study, 337 BM patients were included (247, 60, and 30 in the training set, internal validation set, and external validation set, respectively). Four clinical features and 223 radiomics features were selected using least absolute shrinkage and selection operator (LASSO) and Max-Relevance and Min-Redundancy (mRMR) filters. We establish the ML model using the selected features and the support vector machine (SVM) classifier to predict the treatment response of BM patients to SRS therapy.

Results: In the training set, the SVM classifier that uses a combination of clinical and radiomics features demonstrates outstanding discriminative performance (AUC=0.95, 95% CI: 0.93-0.97). Moreover, this model also achieves satisfactory results in the validation sets (AUC=0.95 in the internal validation set and AUC=0.93 in the external validation set), demonstrating excellent generalizability.

Conclusions: This ML model enables a non-invasive prediction of the treatment response of BM patients receiving SRS therapy, which can in turn assist neurologist and radiation oncologists in the development of more precise and individualized treatment plans for BM patients.

Keywords: brain metastasis; machine learning; multimodal MRI; radiomics; stereotactic radiosurgery; treatment response.

Grants and funding

This work was supported by research grants from Clinical Research Plan of SHDC (grant numbers SHDC2020CR3020A). Science and Technology Commission of Shanghai Municipality (grant numbers 22TS1400900).