Medical image analysis is today mainly done through deep learning. Training deep models require large datasets and advanced GPU hardware, especially when 3D models are used, and for foundation models, GANs and diffusion models. Access to large datasets is in medical imaging hindered by ethics and regulations like GDPR. In this project we will therefore explore federated learning to make it easier to train deep models without having a large dataset on a single computer. In federated learning smaller datasets are available at each node in a federation. No data are shared between nodes, but a global model is trained by instead sharing model weights between each node and a global server. We will explore using novel aggregation functions, i.e. how to combine the local models into a global model in each round of the federated training. This will be compared to standard local and centralized training. We will especially develop novel methods for heterogeneous and inconsistent data. Our NAISS project will simulate federated learning by running several nodes at the same time.