MRI feature-based radiomics models to predict treatment outcome after stereotactic body radiotherapy for spinal metastases

Abstract

Objective: This study aimed to extract radiomics features from MRI using machine learning (ML) algorithms and integrate them with clinical features to build response prediction models for patients with spinal metastases undergoing stereotactic body radiotherapy (SBRT).

Methods: Patients with spinal metastases who were treated using SBRT at our hospital between July 2018 and April 2023 were recruited. We assessed their response to treatment using the revised Response Evaluation Criteria in Solid Tumors (version 1.1). The lesions were categorized into progressive disease (PD) and non-PD groups. Radiomics features were extracted from T1-weighted image (T1WI), T2-weighted image (T2WI), and fat-suppression T2WI sequences. Feature selection involved intraclass correlation coefficients, minimal-redundancy-maximal-relevance, and least absolute shrinkage and selection operator methods. Thirteen ML algorithms were employed to construct the radiomics prediction models. Clinical, conventional imaging, and radiomics features were integrated to develop combined models. Model performance was evaluated using receiver operating characteristic (ROC) curve analysis, and the clinical value was assessed using decision curve analysis.

Results: We included 194 patients with 142 (73.2%) lesions in the non-PD group and 52 (26.8%) in the PD group. Each region of interest generated 2264 features. The clinical model exhibited a moderate predictive value (area under the ROC curve, AUC = 0.733), while the radiomics models demonstrated better performance (AUC = 0.745-0.825). The combined model achieved the best performance (AUC = 0.828).

Conclusion: The MRI-based radiomics models exhibited valuable predictive capability for treatment outcomes in patients with spinal metastases undergoing SBRT.

Critical relevance statement: Radiomics prediction models have the potential to contribute to clinical decision-making and improve the prognosis of patients with spinal metastases undergoing SBRT.

Key points: • Stereotactic body radiotherapy effectively delivers high doses of radiation to treat spinal metastases. • Accurate prediction of treatment outcomes has crucial clinical significance. • MRI-based radiomics models demonstrated good performance to predict treatment outcomes.

Keywords: MRI; Neoplasm metastasis; Radiosurgery; Spine; Treatment outcome.

Fig. 1

The workflow of prediction model construction. a Tumor segmentation was performed on T1WI, T2WI, and FS-T2WI. b Quantitative features were extracted from each ROI. c Feature selection was conducted to reduce feature dimensionality and enhance prediction performance. d and e Three types of prediction models were constructed and evaluated

Fig. 2

Inclusion and exclusion flowchart

Fig. 3

The ROC curves of the three models in test set. The radiomics and combined models outperform the clinical model significantly, with the combined model showing a slight improvement over the radiomics model

Fig. 4

Decision curves for three models in the test set. Decision curve analysis demonstrates that the curves of the clinical, radiomics, and combined models all appear above the reference lines, indicating that these models provide a net benefit to improve clinical decision-making for patients. The radiomics and combined models exhibit higher net benefit compared with that of the clinical model