Tumor are complex ecosystems composed by malignant and non-malignant cells supported by the extracellular matrix (ECM). Cell-cell/ECM interactions occur in 3D cellular neighborhoods (CN) and control molecular phenotypes in the tumor microenvironment. Despite their inhibition can stop tumor progression, routine molecular tumor profiling cannot capture cellular interactions in CN. Conversely, single cell-resolved spatial transcriptomic methods (ST) hold great promise to profile receptor-ligand interactions but are limited to 2D tissue sections and lack ECM readouts. Here, we profile one clinical lung carcinoma combining 3D ST and ECM imaging in serial sections to systematically investigate molecular states, cell-cell interactions, and ECM remodeling in CN. Our integrative analysis pinpointed known immune escape and tumor invasion mechanisms, revealing several druggable drivers of tumor progression in the patient under study. In this proof-of-principle study, we showcase the utility of in-depth CN profiling in a routine clinical sample to inform microenvironment directed therapies.