Abstract:
Cancer is one of the deadliest diseases in the world. Among all the cancers, skin cancer is often unnoticed and as a result, the death rates are rising day by day. If ski...Show MoreMetadata
Abstract:
Cancer is one of the deadliest diseases in the world. Among all the cancers, skin cancer is often unnoticed and as a result, the death rates are rising day by day. If skin cancer is detected early the survival rate increases, but most people are deprived of it as the detection takes time, money, and pain. A smartphone-based skin cancer detection system can serve a lot of people in this regard. Image processing has brought many revolutionary changes in recent times. Moreover, CNN (Convolutional Neural Network) has performed well these days in terms of image pattern analysis and classification. In this study, the corroboration of image processing has been established with CNN in a smartphone-based skin cancer detection system to detect skin cancer from skin lesion images. The proposed method has achieved 85% of accuracy with an F1-score of 86% on test data with Cohen's kappa coefficient of 0.70 and Matthews correlation coefficient of 0.71.
Published in: 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT)
Date of Conference: 06-08 July 2021
Date Added to IEEE Xplore: 03 November 2021
ISBN Information: