Towards a Knowledge Graph for the Visual Recognition of Skin Cancer

The evolution of Knowledge Graphs (KGs), during the last two decades, has encouraged developers to create more and more context related KGs. This advance is extremely important because Artificial Intelligence (AI) applications can access open domain specific information in a semantically rich, machine understandable format. In this paper, we present a KG for the various types of Skin Cancer, which can represent information about the symptoms and dangers to provoke, of the most common, based on cases, types of Skin Cancer. Moreover, we provide a data integration mechanism that can map information from various datasets with skin cancer cases into the skin cancer ontology. A use case scenario in which the KG can be used as a decision support system by doctors, is provided, in which a Computer Vision (CV) simulates a doctor. The CV mechanism in the cases that is not able to classify the case it can consult the KG to retrieve similar cases based on the characteristics of the one at hand.