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

3.3 Image processing and synthetic data generation Requirements

This sub-section contains image processing and synthetic data generation requirements. These requirements separate the ones identified in the previous sub-section into functional and non-functional.

Table 5: Image processing and synthetic data generation – functional requirements

ID	Description	Priority	Category
F-IMSD-1	SD algorithm shall offer a CSV file with the required number of instances of tabular data and each column should be in the expected format (i.e., categorical, numerical etc.).	High	Tabular data
F-IMSD-2	SD algorithm shall offer the possibility to modify some hyper-parameters and GUI shall offer a value reset option to set hyperparameters to their default value	Medium	Algorithms
F-IMSD-3	Synthetic data should be evaluated using various methods and tools.	Medium	Tabular data
F-IMSD-4	Synthetic Images should be evaluated using various methods and tools including human expert validation	Medium	Images
F-IMSD-5	Ability to create error message when error occurs	High	Algorithms
F-IMSD-6	A range of conditions can be forced for some features when synthetic tabular data is generated.	Low	Tabular data
F-IMSD-7	Ability to add structured data by the user	Medium	Tabular data, Images
F-IMSD-8	SD algorithm shall offer a modular structure where each parameter is a module capable of being available or disable	High	Algorithms
F-IMSD-9	SD should take into account that new users will probably need to change units or convert initial data according to specified standards	High	Algorithms, Tabular data
F-IMSD-10	An option for users to save hyperparameters in draft and apply them at later time.	Low	Algorithms
F-IMSD-11	Images input and outputs will be in DICOM format	High	Images
F-IMSD-12	SD algorithm shall have the ability to save a Database (DB) with current CSV file and previous CSVs files proposed	High	Tabular data, Images
F-IMSD-13	SD shall incorporate more than one SD algorithm to perform calculations based on customer choice	High	Tabular data, Images
F-IMSD-14	Data imputation should be considered when historical data is not available, and there is uncertainty or bad quality in the data	Low	Tabular
F-IMSD-15	SD module will have a trained machine to generate synthetic data from new repositories shared by users	Medium	Algorithm
F-IMSD-16	SD algorithm shall take into account that training SD generation can suppose a long waiting time.	Low	Tabular data, Images
F-IMSD-17	SD shall be implemented so that future modular extensions can be added	Medium	Algorithms

Table 6: Image processing and synthetic data generation – non-functional requirements

ID	Description	Priority	Category
NF-IMSD-1	SD algorithm shall take into account that training SD generation can suppose a long waiting time.	Low	Algorithms
NF-IMSD-2	SD shall be implemented so that future modular extensions can be added	Medium	Algorithms
NF-IMSD-3	Synthetic data maintains data privacy and cannot correlate to patient data	High	Tabular data, Images
NF-IMSD-4	Synthetic data used in combination with real data (data augmentation) improves the prediction performance of the algorithms trained using only real data	Low	Algorithms
NF-IMSD-5	SD GUI shall be able to run several queries simultaneously to reduce total time	Low	Algorithms
NF-IMSD-6	A user manual and helping description must be provided.	Medium	Algorithm, Tabular data, Images
NF-IMSD-7	SD GUI shall incorporate an internal counter which will be in charge of recording the amount of use the customer is making to allow a possible pay per use subscription method	Medium	Algorithms