ClinicaDL
Open source deep learning python package for reproducible neuroimaging studies
ClinicaDL is an open-source deep learning python package for reproducible neuroimaging processing. It can be seen as the deep learning extension of Clinica, an open-source Python library for neuroimaging preprocessing and analysis. The combination of ClinicaDL and Clinica allows performing an end-to-end neuroimaging analysis, from the download of raw data sets to the interpretation of trained networks, including neuroimaging preprocessing, quality check, label definition, architecture search, and network training and evaluation
ClinicaDL uses several open-source projects, which greatly contribute to its success.
ClinicaDL brings answers to three common issues encountered by deep learning users who are not always familiar with neuroimaging data.
Accessing properly formatted and pre-processed datasets can be difficult, which can be partly tackled by a dataset format established by the community: the Brain Imaging Data Structure (BIDS)
There are methodological flaws in many studies which results are contaminated by data leakage.
a lack of reproducibility that discredits results,
