Answers are grounded in this paper and cite their sources.
Cancer is an imminent health disease affecting millions of humans of all the age groups and genders. Skin cancer is one of the prevalent health problem among all the nations around the world and it has become the most challenging technique in the development of automatic detection of skin lesions. The accurate diagnosis of skin cancer specifically between the different types of skin lesions Melanoma (mel), Melanocytic Nevi (mn), Benign Keratosis Lesion (bkl), Actinic keratosis intraepithelial carcinoma (akiec), Dermeto Fibrona (df), Squamous Cell Carcinoma (scc), Vascular Lesions (vasc), Basal Cell Carcinoma (bcc) is most demanding chore in the field of medical diagnosis. The aim of our research work is to build an efficient framework for skin cancer classification using Convolutional Neural Network(CNN) integrated with Data Augmentation. The experimental work is carried on publicly available dataset HAM10000(Human Against Machine with 10000 training images). The obtained macro average precision and weighted average precision are recorded as 62.0 and 77.0 respectively. The results reveal training accuracy of 86.54% and testing accuracy of 77.91%.
No takes yet. Share an insight, caveat, or question.
Shobha et al. (2022) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: