Interactive Lung Segmentation Algorithm for CT Chest Images Based on Live-Wire Model and Snake Model

In this paper, an interactive lung parenchyma segmentation algorithm is put forward with improved Live-Wire model, Snake model and contour interpolation, which takes full advantage of lung contours´ slow change in adjacent CT image layers and operators´ professional knowledge. Firstly, we manually select key slices of lung parenchyma in serial CT images, then draw the lung´s contours in key slices by Live-Wire model, get the lung´s contours in other slices by contour interpolation, finally segment lung´s accurate contours in all slices by Snake model and manual modification. Experiments showed that this algorithm can segment lung parenchyma in serial CT images quickly and accurately.