Skin cancer detection and classification using machine learning M. Krishna Monika a , N. Arun Vignesh a , Ch. Usha Kumari a,⇑ , M.N.V.S.S. Kumar b , E. Laxmi Lydia c a Gokaraju Rangaraju Institute of Engineering and Technology, Hyderabad, India b Aditya Institute of Technology and Management, Srikakulam, Andhra Pradesh, India c Vignan’s Institute of Information Technology, Visakhapatnam, Andhra Pradesh, India article info Article history: Received 10 July 2020 Accepted 15 July 2020 Available online xxxx Keywords: Dermoscopic images Dull razor method Filters Feature extraction ABCD method GLCM method Classification MSVM abstract Skin cancer is considered as one of the most dangerous types of cancers and there is a drastic increase in the rate of deaths due to lack of knowledge on the symptoms and their prevention. Thus, early detection at premature stage is necessary so that one can prevent the spreading of cancer. Skin cancer is further divided into various types out of which the most hazardous ones are Melanoma, Basal cell carcinoma and Squamous cell carcinoma. This project is about detection and classification of various types of skin cancer using machine learning and image processing tools. In the pre-processing stage, dermoscopic images are considered as input. Dull razor method is used to remove all the unwanted hair particles on the skin lesion, then Gaussian filter is used for image smoothing. For noise filtering and to preserve the edges of the lesion, Median filter is used. Since color is an important feature in analyzing the type of cancer, color-based k-means clustering is performed in segmentation phase. The statistical and texture feature extraction is implemented using Asymmetry, Border, Color, Diameter, (ABCD) and Gray Level Co- occurrence Matrix (GLCM). The experimental analysis is conduted on ISIC 2019 Challenge dataset consist- ing of 8 different types of dermoscopic images. For classification purpose, Multi-class Support Vector Machine (MSVM) was implemented and the accuracy obtained is about 96.25. Ó 2020 Elsevier Ltd. All rights reserved. Selection and peer-review under responsibility of the scientific committee of the International Confer- ence on Nanotechnology: Ideas, Innovation and Industries. 1. Introduction Skin cancer rates as the 6th most types of cancer that are increasing globally. Generally, skin consists of cells and these cells comprise tissues. Thus, cancer is caused due to the abnormal or uncontrolled growth of the cells in the corresponding tissues or to the other adjacent tissues. Exposure to UV rays, depressed immune system, family history, etc., maybe the reason for the occurrence of cancer. This type of irregular pattern of cell growth can be given as either benign or malignant. Benign tumors are can- cer type and generally, they are considered as moles, which are not harmful. Whereas, malignant tumors are treated as cancer which is threatening to life. They can also damage the other tissues of the body. The layer of the skin consists of three types of cells: Basal cell, Squamous cell, and Melanocyte. These are responsible for the tissues to become cancerous. There are different types of skin cancers, of which Melanoma, Basal cell carcinoma (BCC), Squamous cell carcinoma (SCC), which are considered as dangerous types. And the other types include Melanocytic nevus, Actinic keratosis (AK), Benign keratosis, Dermatofibroma, Vascular lesions. Of all the types, Melanoma is the most dangerous type and can grow back even after removal. Australia and the United States are the most affected by skin cancer. This paper uses the most suitable techniques to categorize all the types of cancer that are mentioned above. Dull Razor method and Gaussian filter are used for image enhancement and Median filter is used for noise removal. The above steps are considered as preprocessing stage. Color-based k- means clustering is used to segment the preprocessed images. To extract the features from the segmented images, two methods known as the ABCD method and GLCM methods are used. Features from both the methods are combined for further classification. Lastly, to achieve high accu- racy MSVM classifier is used for classification purposes. 2. Related work In this paper [1], classification of two types of skin cancer whether melanoma or non-melanoma was performed. Rather than using color or gray image alone, the combination of both was used https://doi.org/10.1016/j.matpr.2020.07.366 2214-7853/Ó 2020 Elsevier Ltd. All rights reserved. Selection and peer-review under responsibility of the scientific committee of the International Conference on Nanotechnology: Ideas, Innovation and Industries. ⇑ Corresponding author. E-mail address: ushakumari.c@gmail.com (Ch. Usha Kumari). Materials Today: Proceedings xxx (xxxx) xxx Contents lists available at ScienceDirect Materials Today: Proceedings journal homepage: www.elsevier.com/locate/matpr Please cite this article as: M. K. Monika, N. Arun Vignesh, C. Usha Kumari et al., Skin cancer detection and classification using machine learning, Materials Today: Proceedings, https://doi.org/10.1016/j.matpr.2020.07.366