Saturation Transfer Imaging Radiomics using Machine Learning Improves Differentiation of Tumour Progression from Radiation Necrosis in Brain Metastases

Objectives This study aimed to develop a machine learning classifier that integrates, along with structural MRI, radiomic features from saturation transfer (ST) MRI techniques, including magnetization transfer (MT) and chemical exchange saturation transfer (CEST), to distinguish tumour progression (TP) from radiation necrosis (RN) in brain metastases following stereotactic radiosurgery (SRS). Methods 174 lesions from 88 patients were analyzed, extracting 2823 radiomic features from T1-, T2-, FLAIR-, and magnetization transfer ratio (MTR)-based images at APT and NOE offsets. After applying feature selection, a 20-feature subset composed mainly of high B1-saturation MTR metrics and quantitative T1 map features was identified. Classifier performance was assessed using cross-validation, with sensitivity and specificity as primary metrics. Results The best performing classifier was Extra Trees, achieving a sensitivity of 0.91 and a specificity of 0.85. Highly ranked features included those derived from MTR maps at higher saturation amplitudes (2.5 µT) and quantitative T1 maps. With the exclusion of MTR-based features, accuracy dropped from 88% to 73% and AUC from 0.89 to 0.77, with a corresponding increase in false positives. Conclusions Results demonstrated that integrating CEST-derived radiomics with conventional MRI provides robust diagnostic performance in differentiating TP from RN. Features derived from MTR maps—especially at higher saturation amplitudes—and quantitative T1 mapping were among the most discriminative, with their exclusion resulting in significantly lower classification performance. This combined radiomics approach may offer a clinically feasible and non-invasive means of guiding treatment decisions to improve patient management for brain metastases post-SRS.