BIGPICTURE, a new era in the field of pathology

Researchers from the Montefiore Institute (School of Engineering) and the Faculty of Medicine of the University of Liège are joining the European BIGPICTURE project. Funded 70 million euros and  part of the IMI (Innovative Medicines Initiative), this project - which brings together the main European research centres, hospitals and the pharmaceutical industry - aims to develop a digital repository for sharing pathology data using artificial intelligence.

B

ased on the examination of tissue samples (slides) under a microscope, pathology is the cornerstone of the treatment of many diseases such as cancer and autoimmune diseases, as well as post-transplant monitoring. However, despite its central role, this discipline still relies heavily on the qualitative interpretation of a qualified pathologist. While the microscope symbolizes the profession, the digitalisation of slides in recent years ignited a revolution: not only images can now be shared and accessed from distant locations, they can also be processed by computers. This opens the door for artificial intelligence (AI) applications to assist the pathologist and help study diseases, find better treatments and contribute to the 3Rs (replace, reduce, and refine animal use in research). However, the development of robust AI applications requires large amounts of data, which in the case of pathology means a huge collection of digital slides and the medical data necessary for their interpretation. Sharing these has so far remained challenging due to the data storage capacity required to host a sufficiently large collection and to concerns regarding the confidential character of the medical information.

To allow the fast development of AI in pathology, the BIGPICTURE project - in which the University of Liège is taking part - aims to create the first European, ethical and GDPR-compliant (General Data Protection Regulation), quality-controlled platform, in which both large-scale data and AI algorithms will coexist. The BIGPICTURE platform will be developed in a sustainable and inclusive way by connecting communities of pathologists, researchers, AI developers, patients, and industry parties.

The project is divided into four main aspects that concern the large-scale collection of data. First, an infrastructure (hardware and software) must be created to store, share and process millions of images that can be gigabytes each. Second, legal and ethical constraints must be put in place to ensure adequate usage of data while fully respecting patient’s privacy and data confidentiality. Then, an initial set of 3 million digital slides from humans and laboratory animals will be collected and stored into the repository to provide data for the development of pathology AI tools. Finally, functionalities that aid the use of the database as well as the processing of images for diagnostic and research purposes will be developed.

"The involvement of the University of Liège lies in the development of open-source software tools  for the management of large sets of high-resolution images of pathology (including the development of new interactive interfaces for online viewing and annotation), explains Raphaël Marée, researcher at the Montefiore Institute (School of Engineering) and project coordinator for the University of Liège. And we are also involved in research into generic artificial intelligence algorithms for the automatic recognition and classification of tissues for biomedical research and diagnostic assistance. "The developments will be based on previous research work by the team of computer scientists and engineers who will work in close collaboration with the company Cytomine, which exploits the result of previous research carried out at the University of Liège and which provides products and services related to the open source software of the same name. "The aim is for these developments to be at the heart of the BigPicture platform (whose servers will be installed by the ELIXIR consortium) and accessible to as many people as possible. "This team will be joined by Professor Philippe Delvenne, a pathologist at the Faculty of Medicine and the University Hospital of Liège, who will provide thousands of images of pathological tissues which will be part of the collection of several million images accessible to the scientific community via this platform.

BIGPICTURE

BIGPICTURE is a public-private partnership funded by IMI, with representation from academic institutions, small- and medium-sized enterprises (SMEs), public organisations and pharmaceutical companies, together with a large network slide contributing partners. The consortium partners involved in the project are :

Academic institutions: Radboud University Medical Center (NL), Linköping University (SE), Leeds Teaching Hospitals NHS Trust (UK), University Medical Centre Utrecht (NL), Uppsala University (SE, ELIXIR node), Haute Ecole Spécialisé de Suisse Occidentale (CH), Eindhoven University of Technology (NL), University of Warwick (UK), Technical University of Munich (DE), Medical University Graz (AT), Institut Pasteur (FR), Université de Liège (BE), University of Semmelweis (HU), National Cancer Institute (NL), Region Östergötland (SE), Medical University Vienna (AT), University of Marburg (DE), Helsingin ja Uudenmaan sairaanhoitopiirin kuntayhtymä (FI),

Pharmaceutical companies: Novartis Pharma AG (CH), Janssen Pharmaceutica NV (BE), Bayer AG (DE), Boehringer Ingelheim International GmbH (DE), Novo Nordisk A/S (DK), Pfizer Ltd (GB), Roche (CH), Sanofi Aventis recherche et Développement (FR), Institut de Recherches Internationales Servier (FR), and UCB Biopharma SRL (BE).

Other public & private organisations: CSC – IT Center for Science Finland (FI, ELIXIR node), Biobanks and biomolecular resources research infrastructure (AT), Azienda Ospedaliera Per L’Emergenza Cannizzaro (IT), Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.(DE), Deutsches Institut für Normung E.V. (DE), European Institute for Innovation through Health Data (BE), European Society of Pathology (BE), Digital pathology association (US), GBG Forschungs Gmbh (DE), ttopstart (NL), Sectra AB (SE), Cytomine SCRLFS (BE), Stichting Lygature (NL), Owkin (FR), Deciphex (IE), MedicalPhit (NL), Timelex (BE).