The method for evaluating the symmetry of the globule pattern in artificial intelligence systems for the diagnosis of skin neoplasms

Methods for an early non-invasive diagnosis of melanoma using computer vision systems are considered. The existing computer vision systems using neural networks for classifying dermoscopic images do not allow tracking which diagnosis features are used to assign images to a particular class, reducing physicians’ trust in the results. As an alternative, an image analysis algorithm is proposed with the ability to provide justifications for the decisions made at each processing stage. The implementation of this algorithm is based on the medical algorithm of modified globular pattern analysis. A significant sign of malignancy in a neoplasm is its asymmetry. This criterion is widely used by physicians when performing visual assessment of skin neoplasms. However, up to now, the issues of evaluating the symmetry of globular patterns in artificial intelligence systems have not been fully studied and described. A method for evaluating the symmetry of globular patterns in artificial intelligence systems for diagnosing skin neoplasms has been developed. A dataset of dermoscopic images was formed, containing 50 images of each type of neoplasms with symmetrically and asymmetrically arranged globular patterns. Methods for isolating the neoplasm area and globules are described. A classification system based on a set of 12 quantitative symmetry characteristics has been developed. The Random Forest algorithm was used to classify images based on symmetry features. In the conducted experiment, a classification accuracy of 85% was achieved. The presented results contribute to the development of computer vision methods in dermatology and demonstrate the possibility of using the proposed method in clinical decision-making support systems when performing a modified analysis of dermoscopic patterns to diagnose skin neoplasms.