A rare and hostile cancer mostly affecting the lungs, pleural mesothelioma has an exceedingly unusual but clinically relevant propagation to the brain. Their unusual appearance and low frequency make early diagnosis and accurate characterization of such uncommon brain metastases a diagnostic difficulty. The present research presents a neuroimaging informatics system using hybrid Positron Emission Tomography–Computed Tomography (PET-CT) imaging to examine and explain uncommon brain metastasis patterns in pleural mesothelioma patients. Our methodology combines sophisticated neuroinformatics technologies with AI-driven image processing algorithms to improve hybrid PET-CT scans' spatial and metabolic resolution. While a radiomics pipeline drives out quantitative characteristics like texture, intensity, and shape descriptors, a deep learning (DL)-based segmentation algorithm finds abnormal metabolic activity suggestive of metastatic lesions. Unsupervised clustering and anomaly detection resources help to examine these characteristics and find rare metastatic developments. To assist thorough case analysis, a clinical informatics layer links imaging results with patient demographics, histopathology data, and treatment history. Validated using retrospective PET-CT data from mesothelioma patients with verified brain involvement, the approach shows increased sensitivity and specificity in finding mysterious metastatic foci. This work emphasizes the need for hybrid imaging modalities in monitoring uncommon oncologic events and provides insightful analysis of the brain spread paths of pleural mesothelioma by providing a strong, AI-enhanced neuroimaging framework. The suggested method helps with early identification, and individualized treatment planning helps to clarify metastatic behavior in typical thoracic cancers.