A Watershed-Based Intelligent Scissors Approach for Interactive Semi-Automated Pulmonary Lobes Segmentation

Abstract

The computational detection of lung lobes from computed tomography (CT) images is a challenging segmentation problem with important respiratory healthcare applications, including emphysema, chronic bronchitis, and asthma. This paper proposes a watershed-based intelligent scissors (IS) approach for interactive semi-automated pulmonary lobes segmentation. First, our model performs automated segmentation of the lung lobes in a watershed method. Second, we present a reliable, accurate, and interactive lobe segmentation approach based on IS for improved accuracy. We evaluate our model using 93 chest CT scans from the central hospital affiliated with Shenyang Medical College (CHASMC). Compared with the traditional watershed algorithm, the proposed algorithm significantly increased efficiency.