Detection of lung cancer using CT images based on novel PSO clustering

Lung cancer is one of the most dangerous diseases that cause a large number of deaths. Early detection and analysis can be very helpful for successful treatment. Image segmentation plays a key role in the early detection and diagnosis of lung cancer. K-means algorithm and classic PSO clustering are the most common methods for segmentation that have poor outputs. In this article, we propose a new that of K-means and classic PSO clustering. The obtained results show that the new PSO clustering has better results as compared to the other methods. Comparison between the proposed method and classic PSO, in terms of fitness function and convergence of fitness function indicate that the proposed method is more effective in detecting lung cancer.