ExaMode Research Project Starts with a Kick off in Sierre

Friday, February 15, 2019

Ontotext, together with 20 researchers from all over Europe, took part in the kick-off meeting for the European H2020 research project ExaMode at the Techno-Pôle Centre in Sierre, Switzerland. The meeting’s agenda included presentation of the consortium partners, overview of the project work packages, detailed planning for the first year project activities, discussions of the exploitation strategy and fine-tuning of the project roadmap.

EXtreme-scale Analytics via Multimodal Ontology Discovery & Enhancement (ExaMode for short) is a Big Data project for Healthcare. Its objective is to develop new prototypes for processing large volumes of healthcare data on exascale computing facilities. One of the best high performance computers will be used as part of the project’s infrastructure. The data can then be used to analyze large quantities of histopathological images, including thin-slice images taken with a microscope required for cancer biopsies and other pathologies.

By using artificial intelligence algorithms, the project revolutionizes pathological diagnosis. It applies deep learning to build semantic representations of entities and relations in multimodal data. Enriching text with semantic metadata and the extraction of homogeneous features from heterogeneous images will lead to better knowledge discovery results. This knowledge will be applied to compress, segment and classify medical images and will be exploited in decision making by hospitals.

Sirma AI will lead the work on Multimodal Knowledge Management. The company will support semantics integration of multimodal knowledge in the project, using GraphDB and domain ontologies. Sirma AI will use text analysis to extract structured data from medical records in several European languages and annotated histopathological images. Then they will be fused with available structured knowledge.

Sirma AI will also take the overall responsibility for communicating developments and outcomes of the project to the business community and the general public. In addition, Sirma AI will contribute to the definition of the semantic model of the domain.

ExaMode is a very important research and innovation project with challenging objectives. It has a 4-year duration and is coordinated by the Institute of Information Systems of the HES-SO Valais-Wallis. Besides Sirma AI, five other universities, hospitals and companies from Italy, the Netherlands and Poland form the project consortium.

For more information about ExaMode, visit the official website at: https://www.examode.eu/


For more information, contact Doug Kimball, Chief Marketing Officer at Ontotext