This systematic review assesses and analyzes the imaging-based screening methods and histopathological correlations that are available for the early detection of metastatic brain tumors. It reviews the critical role that MRI and CT play as primary diagnostic tools, while advanced modalities like PET-MRI, MRS, and DTI help in tumor characterization, metabolic profiling, and treatment surveillance. The integration of artificial intelligence and machine learning has greatly enhanced image segmentation accuracy, classification precision, and survival prediction but still suffers from limitations related to dataset dependency, computational complexity, lack of interpretability, and clinical validation. The histopathological examination is considered the gold standard since it provides crucial information on tumor origin as well as immunohistochemistry molecular subtype and prognostic markers through genomic profiling. Radio genomics trends are emerging more prominently with biomarker analytics to highlight how close imaging is converging with molecular diagnostics toward precision medicine in neuro-oncology. By looking at literature between 2020-2025 this review brings out existing research gaps and stresses the importance of multimodal frameworks driven by AI integrating imaging pathology plus molecular data for better early detection as well as personalized treatment concerning metastatic brain tumors.