Skin Lesion Segmentation Using K-means Clustering with Removal Unwanted Regions

Authors : Nechirvan Asaad ZEBARİ, Emin TENEKECİ

Pages : 519-529

Doi:10.54365/adyumbd.1112260

View : 61 | Download : 19

Publication Date : 2022-12-31

Article Type : Research Paper

Abstract :The segmentation of skin lesions is crucial to the early and accurate identification of skin cancer by computerized systems. It is difficult to automatically divide skin lesions in dermoscopic images because of challenges such as hairs, gel bubbles, ruler marks, fuzzy boundaries and low contrast. We proposed an effective method based on K-means and trainable machine learning system to segment Region of Interest insert ignore into journalissuearticles values(ROI); in skin cancer images. The proposed method was implemented based into several stages including image conversion into grayscale, contrast image enhancement, removing artifacts with noise reduction, segmentation skin lesion from image using K-means clustering, segmenting ROI from unwanted objects based on a trainable machine learning system. The proposed model has been evaluated using ISIC 2017 publicly available dataset. The proposed method obtained a 90.09 accuracy outperforming several methods in the literature.
Keywords : Skin Cancer, Computer Aided Detection, Segmentation, Machine learning, K means Clustering

ORIGINAL ARTICLE URL