Skin lesion border detection in dermoscopic images

Malignant Melanoma is a disease that death rate is quite high among the skin cancer types. It is very important to do the correct diagnosis of this cancer type whose danger level is high. Asymmetric shape, heterogeneous color, bigger diameter than 6 mm and untidy borders that are used to diagnose melanoma by the dermatologists visually are important parameters. In this study, an automatic skin lesion segmentation and border detection processes are carried out in order to assist the physician for diagnosis and reduce the probable human errors. PH
²
dataset that includes 200 lesion images has been used. The segmented reference lesion images which are shared in the dataset have been used for performance analysis of the proposed segmentation and border detection system. The average volume overlap (VO) and Dice coefficient (DC) are achieved as 0.75±6.2 and 0.88±3.4 respectively. As a result, it is aimed to make easier the diagnosis of melanoma type skin cancer and prevent deaths that arisen out of the result of the wrong diagnosis by using the proposed method.