Noninvasive Screening and Discrimination of Skin Images for Early Melanoma Detection

This paper describes a method that helps in detection of sun tanned or precancerous skin using gross-overall image segmentation and boundary tracing to localize three layers in human skin tissue. Skin cancer can become highly invasive and lethal if not treated at the earliest possible stage. The undertaken research herein aims to eliminate the need for a patient to undergo biopsy as a means of basic diagnosis for melanoma. When compared to the normal skin, the structure of abnormal skin has an irregular outer epidermal layer as well as the inner dermal layer. The current trend of non-invasive diagnosis analyses the entire mole. This paper detects skin cancer by processing the cross-section of the skin sample. There are three different skin samples considered to this end; namely, normal skin, sun tanned skin and precancerous skin. In this work, optimal histogram-based segmentation and boundary tracing are used as a means of classifying a sample tissue. Experimental results have shown that the Otsu thresholding is highly effective to assist separating the three layers of the skin sample leading to a highly robust discrimination of normal, sun tanned and melanoma type skin samples.