Detection of Benign and Malignant Skin Cancer from Dermoscopic Images using Modified Deep Residual Learning Model

Authors : Mustafa Said KARTAL, Özlem POLAT

Pages : 10-18

View : 73 | Download : 7

Publication Date : 2022-10-01

Article Type : Research Paper

Abstract :Skin cancer is caused by the uncontrolled proliferation of cells on the skin surface due to damaged DNA structures of them and is among the most common cancer types in the world. If malignant skin cancer is not detected early, it can result in death. For this reason, early and high accuracy detection of skin cancer is important in terms of increasing the chance of survival of patients. In this study, ResNet101 architecture, which is one of the deep residual learning models, is suggested for the detection of malignant skin cancer from dermoscopy images. The model was trained and tested on a dataset of 3297 dermoscopic images from the ISIC 2017 archive. As a result of 10 experiments, average 90,67% and maximum 91,36% accuracy values were reached. In this study, a better performance was obtained compared to previous studies using the same dataset in the literature. In conclusion, the proposed approach has promise in the field of medicine and can help dermatologists diagnose skin cancer.
Keywords : skin cancer, classification, deep residual learning, pattern recognition, machine learning

ORIGINAL ARTICLE URL