Modified Rolling-Ball Method for Pulmonary Parenchyma Segmentation

Abstract

Background: Computer-aided detection/diagnosis (CAD) of lung nodules is a practical approach to improve the relative survival of lung cancer patients. Pulmonary parenchyma segmentation is an essential part of the CAD systems for detecting lung cancer. Methods: To solve the problems of improper segmentation and incomplete repair with the traditional rolling-ball method (RBM), we proposed a novel method with a multi-scale rolling-ball for pulmonary parenchyma segmentation. The traditional RBM suffers from the problem that there is often a mismatch between the rolling-ball radius and the size of the boundary defect. Additionally, the shapes of the rolling-ball and lung parenchyma are mismatched, which results in incomplete restoration of the boundary of lung parenchyma. Therefore, to address these issues, a novel multi-scale elliptic RBM (ME-RBM) is proposed for pulmonary parenchyma segmentation in this work. Results: The proposed approach was used to segment the lung parenchyma in 60 computed tomography (CT) images. The results revealed an area overlap measure (AOM) of 96.34%, dice similarity coefficient (DSC) of 97.83% and sensitivity (Sens) of 98.93%. Conclusion: A novel modified rolling-ball method was proposed and developed in this work for pulmonary parenchyma segmentation on chest CT images. The experimental results showed that the proposed approach was accurate and reliable.