Requirements Federated Learning and mUlti-party computation Techniques for prostatE cancer, published by HL7 Europe. This guide is not an authorized publication; it is the continuous build for version 0.1.0 built by the FHIR (HL7® FHIR® Standard) CI Build. This version is based on the current content of https://github.com/hl7-eu/flute-requirements/ and changes regularly. See the Directory of published versions

3.1 Methodology

The image processing and synthetic data generation requirements are based on stakeholder analysis, brainstorming with professional researchers in the field of generative algorithms, in particular colleagues from UPC, and discussions with potential users, including VHIR and IRST. The three target groups - developers, researchers and end users - each have different requirements.

Some possible use cases may include:

• A medical professional looking for data to complement their database and improve their prediction results in prediction.
• An AI professional aiming to retrain a generative algorithm with different hyper-parameters or with new added data as owner
• A developer that might want to modify or add modules of the FLUTE platform.

In the first two cases, the users will have to ensure and validate the quality of the generated synthetic data using the available metrics.