Automatic Detection of Melanomas: An Application Based on the ABCD Criteria

This paper proposes and describes an automatic software system to detect and diagnose malignant melanomas. Skin melanoma is the most serious type of skin cancer and one of the most malignant tumors in humans. In the last several years increasing melanoma incidence has been observed worldwide. The aim of the present research project was to design, implement and test an application for early diagnosis of malignant melanomas. The system is based on the commonly used dermoscopic criteria scheme called the ABCD rule of dermoscopy (A stands for Asymmetry, B for border irregularity, C for color and D for diameter) and has been tested on a database of 50 lesions (20 benign lesions and 30 malignant lesions). The results of the preliminary experiments show that the image analysis with computer assistance has the potential of more accurately identifying the dermoscopic lesions.