Glioblastoma (GBM) is a malignant brain tumor with poor prognosis despite aggressive treatment. The biological behavior of cells at their invasive edge is of major importance for clinical course and patients’ quality of life. The Mi*EDGE project is based on existing mathematical models of glioma invasion that predict tumor cell behavior based on critical density (“allee-effect”) and local metabolic-driven phenotypic plasticity (“go or grow” decision). It is aiming at predicting whether malignant cells at the margins of surgical resection transform into diffusely invasive or tumor-forming proliferative phenotypes. Considering that tumor cells at the border to normal tissues are interacting with local immune cells, microglia activation and tumor-associated macrophages will be included in the models and repeated cycles of datadriven modelling will clarify the functional role of this crosstalk. To demonstrate the relevance of the resulting predictive computational models for medical practice, the project will translate it to the clinical reality of medical decisions, specifically addressing the questions whether pre-surgical neuroimaging, when included into the model, can predict biological behavior of marginal cells at the tumor edges, and if imaging 3, 6, and 9 months after primary therapy will reflect the prediction with either diffuse tumor invasion, local relapse, or reactive changes (pseudo-progression). The knowledge gained by integrating transnational expertise in neuroradiology, neuropathology, image analysis driven by deep learning, and macrophage biology into validated and iteratively improved versions of existing mathematical models will help to optimize the timing of second-line surgical interventions, radiotherapy and chemotherapy and reposition established anti-cancer therapy in order to reduce risk of early relapse and improve the diagnostic accuracy of neuroradiological findings at the resection margins ofGBM.