FAIrPaCT2 - BMFTR

FAIrPACT2 - Federated Multimodal Artificial Intelligence Framework for Pancreatic Cancer outcome Prediction

Funded by:

Bundesministerium für Forschung, Technologie und Raumfahrt (BMFTR) - Krebsdekade

Duration:

2024 - 2026 (24 Month)

Project description:

FAIrPaCT II builts upon the FAIrPaCT I consortium (BMBF funded 2022-2024), comprising the University Medical Center Göttingen, the University Hospital Giessen and Marburg, and the Technical University Munich. Our approach combines three of the largest patient cohorts (KFO5002, KFO325, SFB1321) on pancreatic cancer in Germany.

The initial consortium aimed to create a software system, supported by federated machine learning, facilitating the analysis of clinical information and genetic cancer panel sequencing data from pancreatic cancer patients. Pancreatic cancer, a highly aggressive malignancy, is anticipated to be the second leading cause of cancer-related death by 2030 in the industrialized world. Leveraging state-of-the-art federated artificial intelligence methods, we successfully trained robust high-performance models to estimate the likelihood of success of treatment. In this extension project, our primary objective is to leverage the existing consortium and infrastructure, enhancing our models to incorporate multi-omics data and histopathology images through a multimodal learning approach. Additionally, we aim to broaden our patient cohort to include individuals from the Molecular Tumor Boards at diverse locations.

This expansion of our FAIrPaCT framework enables the identification of crucial genetic, as well as molecular and histopathological parameters, facilitating the prediction of treatment responses. These insights can offer pivotal information on therapy success, aiding the development of enhanced drugs and personalized treatment strategies. To disseminate our findings to the scientific community, including medical researchers, biomedical informaticians, clinical practitioners, and patient communities, all software packages will be released as open-source. Further, we will establish an interactive research platform, fostering the sharing and utilization of the resulting models.