Segmentation of pulmonary nodules of various densities with morphological approaches and convexity models

The segmentation algorithm consists of six stages: voxel-wise transformation, figure-ground separation, localization of a nodule core, region growing, surface extraction, and convex hull. Inputs to the system are a sub-volume that contains the nodule and a click point in the vicinity of the nodule. The output of the system is a binary map that provides the segmentation of the nodule. [Display omitted] ► A new computationally efficient pulmonary nodule segmentation algorithm is presented. ► It is applicable to nodules of any density types. ► It can separate a nodule from other anatomical structures effectively. ► It only requires a click point placed inside the nodule from the user. ► The performance of the algorithm was evaluated with LIDC1, LIDC2 and additional multi-vendor data set. Accurate segmentation of a pulmonary nodule is an important and active area of research in medical image processing. Although many algorithms have been reported in literature for this problem, those that are applicable to various density types have not been available until recently. In this paper, we propose a new algorithm that is applicable to solid, non-solid and part-solid types and solitary, vascularized, and juxtapleural types. First, the algorithm separates lung parenchyma and radiographically denser anatomical structures with coupled competition and diffusion processes. The technique tends to derive a spatially more homogeneous foreground map than an adaptive thresholding based method. Second, it locates the core of a nodule in a manner that is applicable to juxtapleural types using a transformation applied on the Euclidean distance transform of the foreground. Third, it detaches the nodule from attached structures by a region growing on the Euclidean distance map followed by a procedure to delineate the surface of the nodule based on the patterns of the region growing and distance maps. Finally, convex hull of the nodule surface intersected with the foreground constitutes the final segmentation. The performance of the technique is evaluated with two Lung Imaging Database Consortium (LIDC) data sets with 23 and 82 nodules each, and another data set with 820 nodules with manual diameter measurements. The experiments show that the algorithm is highly reliable in segmenting nodules of various types in a computationally efficient manner.