Novel level-set based segmentation method of the lung at HRCT images of diffuse interstitial lung disease (DILD)

In this paper, we propose an algorithm for reliable segmentation of the lung at HRCT of DILD. Our method consists of four main steps. First, the airway and colon are segmented and excluded by thresholding(-974 HU) and connected component analysis. Second, initial lung is identified by thresholding(-474 HU). Third, shape propagation outward the lung is performed on the initial lung. Actual lung boundaries exist inside the propagated boundaries. Finally, subsequent shape modeling level-set inward the lung from the propagated boundary can identify the lung boundary when the curvature term was highly weighted. To assess the accuracy of the proposed algorithm, the segmentation results of 54 patients are compared with those of manual segmentation done by an expert radiologist. The value of 1 minus volumetric overlap is less than 5% error. Accurate result of our method would be useful in determining the lung parenchyma at HRCT, which is the essential step for the automatic classification and quantification of diffuse interstitial lung disease.