A Novel Image Segmentation Technique for Lung Computed Tomography Images

The aim of this paper is to propose and apply state-of-the-art fuzzy hybrid scatter search for segmentation of lung Computed Tomography (CT) image to identify the lung nodules detection. It utilized fuzzy clustering method with evolutionary optimization of a population size several times lower than the one typically defined with genetic algorithms. The generation of an initial population spread throughout the search space promotes diversification in the search space; the establishment of a systematic solution combination criterion favors the search space intensification; and the use of local search to achieve a faster convergence to promising solutions. With the appropriate preprocessing for lung region extraction, we then conduct the enhanced clustering process with hybrid scatter search evolutionary algorithm (HSSEA) followed with false positive reduction and nodules classification. The proposed approach has been validated with expert knowledge and it achieved up to 80% sensitivity.