K-Means Clustering using Fuzzy C-Means Based Image Segmentation for Lung Cancer

Lung lesion segmentation refers to the process of partitioning an image into mutually exclusive regions. This study gives a new approach to K-means clustering technique (K-CT) integrated with Fuzzy C-means algorithm for lung segmentation. In the study, large number of images with various types of segmentation was selected and examined. It is followed by thresholding and level set segmentation stages to provide an accurate region growing detection. The method starts with lung segmentation based on region growing and standard image processing techniques. K-means clustering technique Segmentation is an important process to cluster information from complex lung lesion. Image Segmentations refers to the process of fuzzy c means an image into groups of pixels which are standardized with some criteria. Fuzzy C-means algorithms are area oriented instead of pixel oriented. The result of lung segmentation is the splitting up of the image into connected region growing. Thus segmentation is concerned with dividing an image in to meaningful regions. The proposed technique can get benefits of the Kmeans clustering for lung lesion segmentation in the aspects of minimal computation time. In addition, it can get advantages of the Fuzzy C-means in the aspects of accuracy. The method starts with lung segmentation based on region growing and standard image processing techniques. *Reviewed by ICETSET'16 organizing committee