In non-small cell lung cancer (NSCLC), accurate staging is critical in deciding between potentially curative surgery and palliative treatment. Image registration, or fusion, combines the unique functional information provided by SPECT imaging with the excellent anatomic detail offered by computed tomography (CT) or magnetic resonance imaging to better characterize the information provided by each separate modality. In this study, we explored the role of fusion of immunoscintigraphy SPECT with CT in the staging of NSCLC. We fused chest CT with 99mTc-labeled IMMU-4 anti-carcinoembryonic antigen Fab' antibody fragment SPECT in 14 patients with NSCLC using a landmark-based algorithm. The algorithm's accuracy was a measure from the center-to-center distance and the percentage overlap of two regions of interest: one drawn on CT and warped onto SPECT, the other drawn directly on the SPECT. We found that the average center-to-center distance was 1.3 +/- 0.8 pixels. Average overlap was 46 +/- 20%. CT-SPECT fusion helped differentiate tumor from normal blood pool, necrotic areas within viable tumor, tumor recurrence from scar, and malignant lymphadenopathy from hyperplasia. We conclude that fusion of CT and SPECT augments the information provided by each separate modality. Future clinical applications of fusion in NSCLC staging using immunoscintigraphy appear promising.