Tumor hypoxia has been shown to have prognostic value in clinical trials involving radiation, chemotherapy, and surgery. Tumor oxygenation studies at microvascular levels can provide understanding of oxygen transport on scales at which oxygen transfer to tissue occurs. To fully grasp the significance of blood oxygen delivery and hypoxia at microvascular levels during tumor growth and angiogenesis, the spatial and temporal relationship of the data must be preserved and mapped. Using tumors grown in window chamber models, hyperspectral imaging can provide serial spatial maps of blood oxygenation in terms of hemoglobin saturation at the microvascular level. We describe our application of hyperspectral imaging for in vivo microvascular tumor oxygen transport studies using red fluorescent protein (RFP) to identify all tumor cells, and hypoxia-driven green fluorescent protein (GFP) to identify the hypoxic fraction. 4T1 mouse mammary carcinoma cells, stably transfected with both reporter genes, are grown in dorsal skin-fold window chambers. Hyperspectral imaging is used to create image maps of hemoglobin saturation, and classify image pixels where RFP alone is present (tumor cells), or both RFP and GFP are present (hypoxic tumor cells). In this work, in vivo calibration of the imaging system is described and in vivo results are shown.