Automatic Segmentation of Lung Nodule From CT Images Using Fuzzy C-Means Clustering Algorithm and Active Contour Model

Abstract

Lung nodule segmentation is an important part in computer-aided diagnosis (CAD) system for lung cancer detection and diagnosis. The key issue in CAD of lung nodule is to correct and accelerate rapid segmentation of diseased tissue. This paper provides a novel approach method to develop a region based active contour model and Fuzzy C-Means clustering technique for segmentation of lung nodules. Computed Tomography (CT) imaging is an efficient medical screening test used for lung cancer diagnosis and detection. Fuzzy c-means clustering algorithm (FCM) is sensitive to noise, local spatial information is often introduced to improve the robustness of the FCM algorithm for image segmentation. The methodology involves image acquisition, seeks the contour of the object using active contour model and segment the lung nodule using fuzzy c-means clustering algorithm. The experimental results of this method show that it is superior to other typical algorithms in the segmentation of lung nodules.