TY - GEN
T1 - Skin lesions identification using deep convolutional neural network
AU - Alkarakatly, Tasneem
AU - Eidhah, Shatha
AU - Al-Sarawani, Miaad
AU - Al-Sobhi, Alaa
AU - Bilal, Mohsin
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/2
Y1 - 2020/2
N2 - Skin cancer is a serious public health problem due to its increasing incidence and subsequent high mortality rate. Deep learning is one of the most important approaches in image analysis used to detect melanoma skin cancer. In this paper, we propose a 5-layer Convolutional Neural Network (CNN) for classifying skin lesions of three categories, including melanoma belonging to deadly skin cancer. The CNN based classifier trained and tested on the PH2 dataset of Dermoscopic images, which is developed for research and benchmarking purposes. The proposed model was evaluated by four well-known performance measures namely, classification accuracy, sensitivity, specificity and area under the curve (AUC). It achieved almost 95% accuracy, 94% sensitivity, 97% specificity, and 100% AUC on the test set. Moreover, in one case of the experiment, the proposed model achieved 100% accuracy.
AB - Skin cancer is a serious public health problem due to its increasing incidence and subsequent high mortality rate. Deep learning is one of the most important approaches in image analysis used to detect melanoma skin cancer. In this paper, we propose a 5-layer Convolutional Neural Network (CNN) for classifying skin lesions of three categories, including melanoma belonging to deadly skin cancer. The CNN based classifier trained and tested on the PH2 dataset of Dermoscopic images, which is developed for research and benchmarking purposes. The proposed model was evaluated by four well-known performance measures namely, classification accuracy, sensitivity, specificity and area under the curve (AUC). It achieved almost 95% accuracy, 94% sensitivity, 97% specificity, and 100% AUC on the test set. Moreover, in one case of the experiment, the proposed model achieved 100% accuracy.
KW - Convolutional neural network (CNN)
KW - Dermoscopy images
KW - Melanoma detection
KW - Skin lesion classification
UR - http://www.scopus.com/inward/record.url?scp=85092399164&partnerID=8YFLogxK
U2 - 10.1109/AECT47998.2020.9194205
DO - 10.1109/AECT47998.2020.9194205
M3 - Conference contribution
AN - SCOPUS:85092399164
T3 - 2019 International Conference on Advances in the Emerging Computing Technologies, AECT 2019
BT - 2019 International Conference on Advances in the Emerging Computing Technologies, AECT 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 International Conference on Advances in the Emerging Computing Technologies, AECT 2019
Y2 - 10 February 2020
ER -
