Region-Based Clustering for Lung Segmentation in Low-Dose CT Images

Lung segmentation in thoracic computed tomography scans is essential for the development of computer-aided diagnostic methods for identifying the lung diseases. Low-dose CT scans are increasingly utilized in lung studies, but segmenting them with traditional threshold segmentation algorithms often yields less than satisfying results. In this paper we present a hybrid framework to lung segmentation which joints region-based information based on watershed transform with clustering techniques. The proposed method eliminates the task of finding an optimal threshold and the over-segmentation produced by watershed. We have applied our approach on several pulmonary low-dose CT images and the results reveal the robustness and accuracy of this method.