Publication

Abstract : Melanoma is one of the most fatal type of skin cancer. Among the 2–3 million skin cancer diagnosed around the world each year, around 5% is affected with melanoma. Early detection of melanoma can save a life. A computer vision aided system with reasonable accuracy was developed for the early diagnosis of melanoma. The analysis was done using dermoscopic images downloaded from publically available database. After preprocessing, the features capable of melanoma identification, viz., ABCD parameters: Asymmetry, Border, Color, and Diameter are extracted. The analysis includes a comparative study between conventional machine learning techniques and deep learning. The learning techniques: Total Dermoscopic Score, K-Nearest Neighbor, Support Vector Machine and Convolutional Neural Networks were used for classification. The results of the study showed that deep learning-based method gives more accurate and precise detection of melanoma compared to conventional supervised learning techniques.