Highlights • The ExaMode ontology models the histopathology diagnostic process by considering 4 diseases: colon cancer, cervix cancer, lung cancer, and celiac disease. In particular, we model the components related to the annotation process of whole slide images (WSIs), storing information about clinical case reports, diagnoses, histopathology images, anatomical locations, and interventions. • The ontology is multilingual (all components have labels in 3 languages: English, Italian, and Dutch) and the design followed a bottom-up approach starting from anonymized clinical reports provided by 2 European medical centers. For modeling the ontology, we followed an iterative co-design process with continuous feedback and validation from pathologists and clinicians. To ease interoperability, we designed the ExaMode ontology to meet the OBO principles and we defined some basic guidelines to adopt when representing each component to guarantee semantic consistency. • The ExaMode ontology is currently being used as a common semantic layer in: (i) an entity linking tool for the automatic annotation of medical records; (ii) a web-based collaborative annotation tool for histopathology text reports; and (iii) a software platform for building holistic solutions integrating multimodal histopathology data.
【저자키워드】 computational pathology, Histopathology, Ontology, Semantic integration,