Integrated Lung Field Segmentation of Injured Regions and Anatomical Structures from Chest CT Images

Abstract

Abstract This work proposes a novel functionality for computerized tomography (CT) based investigation of diffuse lung diseases diagnosis that enables the evaluation of the disease with lung anatomical structures. Automated methods for segmenting several anatomy structures in chest CT are proposed: namely the lungs, airway trees and pulmonary vessels trees. The airway and pulmonary vessels trees are segmented using a failure and recovery algorithm. The algorithm checks intermediary results consistence, backtrack to a history position if a failure is detected. The quality of the result is improved while reducing the processing time even for subjects with lung diseases. The pulmonary vessels are segmented through the same algorithm with different seed points. The seed for the airway segmentation is within the tracheal tube, and the seed for the pulmonary vessels segmentation is within the heart. The algorithm is tested with CT images acquired from three distinct types of subjects: healthy, idiopathic interstitial pneumonias (IIPs) and chronic obstructive pulmonary disease (COPD). The main bronchus are found in the segmented airways and the associated lung lobes are determined. Combining the segmented lung lobes and the diffuse lung diseases classification, it is possible to quantify how much and where of each lobe is injured. The proposed algorithm was evaluated to be robust enough to segment the studied cases.