Glossary

Digital Imaging and Communications in Medicine (DICOM)

This is the standard data format for medical imaging information and related data, and enables integration between medical imaging devices and picture archiving and communication systems (PACS).

Federated learning

Federated learning is a machine learning (ML) technique that trains an algorithm across multiple decentralized edge devices or servers holding local data samples, without exchanging them.

Flower Framework

Flower is an open-source framework for building federated learning systems. It provides tools and libraries to facilitate the development and deployment of federated learning applications. For more information, please see its official documentation.

NVIDIA FLARE

NVIDIA Federated Learning Application Runtime Environment is a domain-agnostic, open-source, extensible SDK that allows researchers and data scientists to adapt existing ML/DL workflows to a federated paradigm. For more information, please see the documentation here.

OMOP

Observational Medical Outcomes Partnership (OMOP). In FLIP documentation, this typically refers to the OMOP Common Data Model (CDM) used to standardise clinical data for federated cohort queries.

PACS

Picture Archiving and Communication System (PACS), the clinical system used to store and retrieve medical imaging studies (such as DICOM series).

RBAC

Role Based Access Control (RBAC) defines what users are able to access within the FLIP platform.

XNAT

XNAT is an open-source imaging informatics platform used in FLIP to store, manage and access imaging data for research workflows. For more information on XNAT, please see the documentation.