Extraction of Abnormal Skin Lesion from Dermoscopy Image using VGG-SegNet
Seifedine Kadry, David Taniar, Robertas Damaševičius, V. Rajinikanth, Isah A. Lawal
Abstract
Skin is one of the vital and well-known sensory organs in human physiology and due to various reasons, the abnormality in skin arises. Skin Melanoma (SM) is one of the medical crisis in humans and the untreated SM will cause various abnormalities, such as skin irritation, spreading the cancerous cells through the blood stream, etc. Efficient assessment of the SM is essential to identify the severity of the disease and hence the proposed work implemented a Convolutional-Neural-Network (CNN) based approach to support the automated SM examination. This work employed the VGG-SegNet scheme to extract the SM section from the Digital-Dermoscpy-Image (DDI). After the extraction, a relative assessment between the segmented SM and the Ground-Truth (GT) is executed and the essential performance indices are then computed. The proposed scheme is tested and validated using the benchmark ISIC2016 database and the average result attained with the proposed study helped to achieve a better values of Jaccard-Index, Dice, and Accuracy for the DDI with and without the artifacts. These results confirm that, proposed technique is significant in evaluating the clinical grader DDI.