Machine Learning Models for the Classification of Skin Cancer
Institute of Electrical and Electronics Engineers Inc.
Skin cancer is a serious illness that requires early identification in order to improve survival rates. Deep learning algorithms for computerized skin cancer detection have now become popular in recent years. These models may increase their performance by having access to additional data, and their prime objective is image categorization. This activity is extremely useful in the realm of health since it may help physicians and experts make the best decisions and accurately assess a patient's condition. Early detection of skin cancer helps patients to receive appropriate treatment and so enhance their survival rate. This proposed methodology is generated to detect and classify skin cancers. In this study, we employed four pre-trained deep learning models (Squeeze net, Alex net, Res net 101, VGG 19) for the classification of four types of skin cancers in more than 6000 skin images including actinic keratoses, intraepithelial carcinoma Bowen's disease (akiec), basal cell carcinoma (bcc), benign keratosis-like lesions (bkl) and melanocytic nevi (nv). The objective was the identification of the best model in the classification of these breast cancer images with highest accuracy. Experimental results reveal that the Squeeze net model achieved an accuracy of 92.5% which is highest when compared with all other models while Alex net, Res net 101, VGG 19 acquired 91.1%, 83.2%, and 90.4% respectively. © 2022 IEEE.
This conference paper is not available at CUD collection. The version of scholarly record of this paper is published in 2022 International Conference on Business Analytics for Technology and Security (ICBATS) (2022), available online at: https://doi.org/10.1109/ICBATS54253.2022.9759054
Computer-aided diagnostic (CAD), Convolutional neural network (CNN), World health organization (WHO)
Arooj, S., Khan, M. F., Khan, M. A., Khan, M. S., & Taleb, N. (2022). Machine learning models for the classification of skin cancer. 2022 International Conference on Business Analytics for Technology and Security (ICBATS). https://doi.org/10.1109/ICBATS54253.2022.9759054