Artificial intelligence-powered spatial analysis reveals distinct tumor-immune microenvironments associated with MET mutations in non-small cell lung cancer

MET alterations, including exon 14 skipping mutations and amplifications, are known oncogenic drivers in non-small cell lung cancer (NSCLC). Their impact on the tumor microenvironment (TME) remains poorly understood. Previous studies have relied on bulk sequencing methods to characterize differences in the TME; however, these methods lack the spatial resolution needed to capture complex interactions between tumor, immune, and stromal cells. Spatial analysis of whole slide images (WSIs) offers a powerful approach to characterize the TME with high resolution, preserving critical information about cellular localization and interactions. This study aimed to leverage artificial intelligence (AI)-powered spatial analysis of WSIs to characterize the immune phenotypes and cellular composition associated with different MET mutation statuses in NSCLC.