PURPOSE Gamma Knife radiosurgery (GKRS) is a non-invasive procedure for the treatment of brain metastases. This study sought to determine whether radiomic features of brain metastases derived from pre-GKRS magnetic resonance imaging (MRI) could be used in conjunction with clinical variables to predict the effectiveness of GKRS in achieving local tumor control. METHODS We retrospectively analyzed 161 patients with non-small cell lung cancer (576 brain metastases) who underwent GKRS for brain metastases. The database included clinical data and pre-GKRS MRI. Brain metastases were demarcated by experienced neurosurgeons, and radiomic features of each brain metastasis were extracted. Consensus clustering was used for feature selection. Cox proportional hazards models and cause-specific proportional hazards models were used to correlate clinical variables and radiomic features with local control of brain metastases after GKRS. RESULTS Multivariate Cox proportional hazards model revealed that higher zone percentage (hazard ratio, HR 0.712; P = .022) was independently associated with superior local tumor control. Similarly, multivariate cause-specific proportional hazards model revealed that higher zone percentage (HR 0.699; P = .014) was independently associated with superior local tumor control. CONCLUSIONS The zone percentage of brain metastases, a radiomic feature derived from pre-GKRS contrast-enhanced T1-weighted MRIs, was found to be an independent prognostic factor of local tumor control following GKRS in patients with non-small cell lung cancer and brain metastases. Radiomic features indicate the biological basis and characteristics of tumors and could potentially be used as surrogate biomarkers for predicting tumor prognosis following GKRS.

中文翻译：

---

放射线学是伽马刀放射外科治疗脑转移的预后因素。

目的伽玛刀放射外科手术（GKRS）是用于治疗脑转移的非侵入性手术。这项研究试图确定源自GKRS前磁共振成像（MRI）的脑转移的放射学特征是否可以与临床变量结合使用，以预测GKRS在实现局部肿瘤控制方面的有效性。方法我们回顾性分析了接受GKRS脑转移的161例非小细胞肺癌（576例脑转移）患者。该数据库包括临床数据和GKRS之前的MRI。由经验丰富的神经外科医生划定脑转移灶，并提取每个脑转移灶的放射学特征。共识聚类用于特征选择。使用Cox比例风险模型和特定原因的比例风险模型将GKRS后的临床变量和放射学特征与脑转移的局部控制相关联。结果多元Cox比例风险模型显示较高的区域百分比（风险比，HR 0.712； P = .022）与上级局部肿瘤控制独立相关。同样，多因素成因比例风险模型显示较高的区域百分比（HR 0.699； P = .014）与优越的局部肿瘤控制独立相关。结论发现非小细胞肺癌和脑转移患者GKRS后脑转移的区域百分比是GKRS前对比增强的T1加权MRI的放射学特征，是局部肿瘤控制的独立预后因素。 。