Automatic Classification of Specific Melanocytic Lesions Using Artificial Intelligence

Background. Given its propensity to metastasize, and lack of effective therapies for most patients with advanced disease, early detection of melanoma is a clinical imperative. Different computer-aided diagnosis (CAD) systems have been proposed to increase the specificity and sensitivity of melanoma detection. Although such computer programs are developed for different diagnostic algorithms, to the best of our knowledge, a system to classify different melanocytic lesions has not been proposed yet. Method. In this research we present a new approach to the classification of melanocytic lesions. This work is focused not only on categorization of skin lesions as benign or malignant but also on specifying the exact type of a skin lesion including melanoma, Clark nevus, Spitz/Reed nevus, and blue nevus. The proposed automatic algorithm contains the following steps: image enhancement, lesion segmentation, feature extraction, and selection as well as classification. Results. The algorithm has been tested on 300 dermoscopic images and achieved accuracy of 92% indicating that the proposed approach classified most of the melanocytic lesions correctly. Conclusions. A proposed system can not only help to precisely diagnose the type of the skin mole but also decrease the amount of biopsies and reduce the morbidity related to skin lesion excision.

Novel Method for Border Irregularity Assessment in Dermoscopic Color Images

Background. One of the most important lesion features predicting malignancy is border irregularity. Accurate assessment of irregular borders is clinically important due to significantly different occurrence in benign and malignant skin lesions. Method. In this research, we present a new approach for the detection of border irregularities, as one of the major parameters in a widely used diagnostic algorithm the ABCD rule of dermoscopy. The proposed work is focused on designing an efficient automatic algorithm containing the following steps: image enhancement, lesion segmentation, borderline calculation, and irregularities detection. The challenge lies in determining the exact borderline. For solving this problem we have implemented a new method based on lesion rotation and borderline division. Results. The algorithm has been tested on 350 dermoscopic images and achieved accuracy of 92% indicating that the proposed computational approach captured most of the irregularities and provides reliable information for effective skin mole examination. Compared to the state of the art, we obtained improved classification results. Conclusions. The current study suggests that computer-aided system is a practical tool for dermoscopic image assessment and could be recommended for both research and clinical applications. The proposed algorithm can be applied in different fields of medical image analysis including, for example, CT and MRI images.