Automated Lung CT Image Segmentation Using Kernel Mean Shift Analysis

With improvement technology in medical science,using methods based on machine vision technics become moreconsiderable. Automatic methods in clinical practice provide fastand accurate analysis of scanned images indisease diagnosing.Within these methods, medical image segmentation plays moreimportant role in separation of defective cellular from healthyorgans. By performing an accurate segmentation, medicines candetect indistinguishable parts of scanned images, classify themand search over a database to find similar cases.In this paper; weproposed an efficient and adaptive method for segmentation oflung CT images. The proposed algorithm uses adaptive meanshift method that estimate the bandwidth parameter by usingfixed bandwidth estimation.Because of close dependency ofkernel density estimation method to the bandwidth parameter,Particle Swarm Optimization algorithm is used to optimize thisparameter. This method is achieved better segmentation that cancarry out small lung nodules and detecting regions within an CTimage. Experimental results on a large dataset of diverse lung CTimages prove that the proposed algorithm accurately andefficiently detects the borders and regions of lung images

کلیدواژه ها:

mean shift ، segmentation ، lung CT ، shape analysis