Feasibility of Spatial Model Checking for Nevus Segmentation

Recently developed spatial and spatio-temporal model checking techniques have a wide range of application domains, among which large scale distributed systems as well as signal and image analysis. In the latter domain, automatic and semi-automatic contouring in Medical Imaging has shown to be a very promising and versatile application that may facilitate the work of professionals in this domain, while supporting explainability, easy replicability and exchange of medical image analysis methods. In recent work, spatial model-checking has been applied to the 3D contouring of brain tumours and related oedema in magnetic resonance images of the brain. In the present paper we address the contouring of 2D images of nevi. One of the challenges of contouring nevi is that they show considerable inhomogeneity in shape, colour, texture and size. In addition these images often include also extraneous elements such as hairs, patches and rulers. To deal with this challenge we explore the use of a texture similarity operator in combination with spatial logic operators. We investigate the feasibility of our technique on images of a large public database. We compare the results with associated ground truth segmentation provided by domain experts; the results are very promising, both from the quality and from the performance point of view.