Smoothing lung segmentation surfaces in 3D x-ray CT images using anatomic guidance

Abstract

Several methods for automatic lung segmentation in volumetric computed tomography (CT) images have been proposed. Most methods distinguish the lung parenchyma from the surrounding anatomy based on the difference in CT attenuation values. This can lead to an irregular and inconsistent lung boundary for the regions near the mediastinum. This paper presents a fully automatic method for the 3D smoothing of the lung boundary using information from the segmented human airway tree. First, using the segmented airway tree we define a bounding box around the mediastinum for each lung, within which all operations are performed. We then define all generations of the airway tree distal to the right and left mainstem bronchi to be part of the respective lungs, and exclude all other segments. Finally, we perform a fast morphological closing with an ellipsoidal kernel to smooth the surface of the lung. This method has been tested by processing the segmented lungs from eight normal datasets. The mean value of the magnitude of curvature of the contours of mediastinal transverse slices, averaged over all the datasets, is 0.0450 before smoothing and 0.0167 post smoothing. The accuracy of the lung contours after smoothing is assessed by comparing the automatic results to manually traced smooth lung borders by a human analyst. Averaged over all volumes, the root mean square difference between human and computer borders is 0.8691 mm after smoothing, compared to 1.3012 mm before. The mean similarity index, which is an area overlap measure based on the kappa statistic, is 0.9958 (SD 0.0032).