User-guided Segmentation of Thoracic Computed Tomography Data for Electrical Impedance Tomography Image Reconstruction

Electrical Impedance Tomography (EIT) is a promising technique to visualize lung function, but it suffers from inaccurate thorax models. To easily generate such models in the presence of severe lung damage, we propose an interactive segmentation workflow that utilizes expert knowledge. Body shape, lung, ribs, heart and pathological lung tissue are segmented from CT scans to allow multi-material body models for EIT image reconstruction. \ \ The workflow includes histogram-based thresholding, body shape extraction, ribcage and heart segmentation and uses well-known techniques like Connected Component Analysis and morphological operations as well as interactive algorithms like Geodesic Segmentation.