BIGPICTURE will accelerate the development of AI in pathology by providing a large repository of high-quality annotated pathology data, accessible in a responsible, inclusive and sustainable way.
BIGPICTURE will set up the first European, ethical- and General Data Protection Regulation-compliant, quality-controlled and community-based platform, in which both large-scale data and AI algorithms will coexist.
BIGPICTURE’s vision is to become the catalyst in the digital transformation of Pathology.
The development of AI in Pathology will accelerate the discovery and validation of biomarkers to better diagnose and predict diseases. It will also improve both the quality and efficiency of toxicity studies and in turn, boost drug development for the benefit of patients.
BIGPICTURE aims to:
- Develop a sustainable secure and scalable infrastructure to store pathology data.
- Collect >3 million nonclinical and clinical high-quality pathology images with associated technical and biological information.
- Develop tools to enable and enhance the use of the repository, such as morphological search tools.
- Develop generic AI building blocks to promote the development of AI models.
- Advance the regulatory, legal and ethical framework around AI in non-clinical safety testing and clinical use.
To achieve its goals, the BIGPICTURE project will first create the infrastructure needed to store, share and process millions of image files. Secondly, it will address legal and ethical issues to ensure patient privacy and data confidentiality issues are fully respected. The project is divided into four main aspects that concern the large-scale collection of data:
- An infrastructure (hardware and software) to store, share and process millions of annotated pathology images that can be gigabytes each.
- Legal and ethical requirements to ensure adequate usage of data while fully respecting patients’ privacy and data confidentiality.
- An initial set of 3 million digital pathology slides collected and stored into the repository to provide data for the development of AI tools.
- Functionalities to aid the use of the repository as well as the processing of images for diagnostic and research purposes.
BIGPICTURE Key Figures
32 319 825 €
Start 1 Feb 2021
37 762 082 €
Duration 6 years
BIGPICTURE is a public-private partnership funded by the EU Innovative Medicines Initiative (IMI) bringing together academic institutions, small- and medium-sized enterprises, public organisations, pharmaceutical companies, and a large network of partners contributing images.
Coordinators: Jeroen van der Laak and Katrien Grünberg (Radboud University Medical Centre, The Netherlands).
Project leads: Pierre Moulin (Novartis, Switzerland) and Anna-Lena Frisk (Janssen, Belgium).
Consortium partners: Discover the BIGPICTURE community