Impact of a Radiologic and Immunologic Signature on Cerebral Efficacy of Treatments in Lung Cancers With Brain Metastasis

Non-small cell lung cancer frequently spreads to the brain, and brain metastases are associated with poor prognosis and limited treatment response. This retrospective study will investigate whether quantitative features extracted from brain magnetic resonance imaging (MRI), known as radiomic features, are associated with the immune characteristics of brain metastases assessed by bulk RNA sequencing. The main objective is to identify relationships between MRI-based radiomic signatures and tumor immune profiles. A secondary objective is to determine whether radiomic, transcriptomic, or combined radio-transcriptomic signatures can help predict cerebral progression during immunotherapy. The study hypothesis is that MRI-based radiomic signatures may reflect the immune environment of brain metastases and could provide a non-invasive approach for predicting treatment response.