Leukemia Nucleus Image Segmentation Using Covering-Based Rough K-Means Clustering Algorithm
13 Pages Posted: 7 Mar 2018
Date Written: November 15, 2017
Abstract
Image Segmentation plays an important role in leukemia diagnosis. Blast and non-blast cells are identified based on the shape and size of the leukemia nucleus. Accurate and efficient segmentation technique is essential for earlier prediction of leukemia. In recent years, rough set based clustering has become a user-friendly technique employed to segment the cancerous cells in medical image processing. In this paper, Covering-based Rough K-Means (CRKM) clustering algorithm is proposed to segment the image of leukemia nucleus. In this method, covering-based approximation is used instead of rough approximation. The robustness of the proposed method is compared with the existing clustering-based segmentation techniques, such as, K-means clustering, Fuzzy C-means (FCM) clustering and Rough K-means (RKM) clustering. The result reveals that the proposed CRKM clustering algorithm is robust in segmenting the image of the nucleus.
Keywords: Clustering, Covering Rough Set, Leukemia, Segmentation
Suggested Citation: Suggested Citation