Medical imaging data structure extended to multiple modalities and anatomical regions

J. M. Saborit-Torres, J. À. Montell, J. M. Salinas, J. A. Gómez, I. Stefan, M. Caparrós, F. García-García, J. Domenech, J. V. Manjón, G. Rojas, A. Pertusa, A. Bustos, G. González, J. Galant, M. de la Iglesia-Vayá


Brain Imaging Data Structure (BIDS) allows the user to organise brain imaging data into a clear and easy standard directory structure. BIDS is widely supported by the scientific community and is considered a powerful standard for management. The original BIDS is limited to images or data related to the brain. Medical Imaging Data Structure (MIDS) was therefore conceived with the objective of extending this methodology to other anatomical regions and other types of imaging systems in these areas.

Keywords: standardisation · extension · Brain Imaging Data Structure · Medical Imaging Data Structure · database · anatomical region · modality


XNAT2MIDS is a software written in Python 3 and can be found at the public Github repository listed above. This software allows the users of an XNAT platform to connect to their assigned projects and download the projects of interest in MIDS format. The figure below shows the execution flow in which a XNAT session is generated. It can store all the requested projects and, once saved in a temporary directory, the program generates the general MIDS structure and its tabular metadata.


This directory structure was applied to the data in the medical image bank of the Valencian community in the BIMCV COVID19 + project. This project is a large dataset of the Medical Imaging Databank in BIMCV with chest X-ray images CXR (CR, DX) and computed tomography (CT) imaging of SARS-CoV-2 (COVID 19).


If you want to know more about the project, or contact the research team, write to us.