The project "DOSIMETReye: A GenAI-based tool for 3D dosimetry from 2D imaging for preclinical studies" aims to develop a tool based on generative artificial intelligence and explainable artificial intelligence (GenAI, XAI), Monte Carlo simulations, and high-performance computing (HPC) to facilitate preclinical studies.
More specifically, the project aims to develop the first dosimetry tool based on Artificial Intelligence, which will provide real-time analysis of absorbed doses with image acquisition.
The tool will offer a highly innovative digital solution for dosimetry assessment (the measurement and calculation of ionizing radiation dose) during medical imaging of radiopharmaceuticals, with the possibility of further expansion for clinical purposes.
The benefit offered by the tool's innovation lies in the use of state-of-the-art technology, as advanced generative Artificial Intelligence algorithms will create three-dimensional anatomical models of mice from dynamic 2D images and predict organ-level dosimetry assessment, providing more accurate and effective dosimetry results.
The project is part of the FFPlus program, a European initiative that aims to promote the adoption of HPC by SMEs and start-ups across Europe, with actions aimed at using supercomputing resources to develop productive AI software solutions and services, and solving business challenges through computational methods on HPC systems.
The main role of GRNET is that of a high-performance computing (HPC) expert, offering support and advice on the parallelisation and optimisation of HPC resources.
Participating partners in the project:
- University of Stuttgart (Coordinator)
- BIOEMTECH
- ALETHIA
- National Infrastructures for Research and Technology (GRNET)
The project budget comes from 100% EU funding.
