Resumen
Advances have been made in the field of Machine Learning showing that it is an effective tool that can be used for solving real world problems. This success is hugely attributed to the availability of accessible data which is not the case for many fields such as healthcare, a primary reason being the issue of privacy. Federated Learning (FL) is a technique that can be used to overcome the limitation of availability of data at a central location and allows for training machine learning models on private data or data that cannot be directly accessed. It allows the use of data to be decoupled from the governance (or control) over data. In this paper, we present an easy-to-use framework that provides a complete pipeline to let researchers and end users train any model on image data from various sources in a federated manner. We also show a comparison in results between models trained in a federated fashion and models trained in a centralized fashion for Independent and Identically Distributed (IID) and non IID datasets. The Intracranial Brain Hemorrhage dataset and the Pneumonia Detection dataset provided by the Radiological Society of North America (RSNA) are used for validating the FL framework and comparative analysis.