ClinicaDL: an open-source deep learning software for reproducible neuroimaging processing

Elina Thibeau-Sutre (1, 2, 3, 4) , Mauricio Diaz (1, 2, 3, 4) , Ravi Hassanaly (1, 2, 3, 4) , Alexandre M Routier (1, 2, 3, 4) , Didier Dormont (1, 2, 3, 4) , Olivier Colliot (1, 2, 3, 4) , Ninon Burgos (1, 2, 3, 4)

1 ICM - Institut du Cerveau = Paris Brain Institute
2 ARAMIS - Algorithms, models and methods for images and signals of the human brain = Algorithmes, modèles et méthodes pour les images et les signaux du cerveau humain [ICM Paris]
3 SU - Sorbonne Université
4 CHU Pitié-Salpêtrière [AP-HP]

Background and Objective As deep learning faces a reproducibility crisis and studies on deep learning applied to neuroimaging are contaminated by methodological flaws, there is an urgent need to provide a safe environment for deep learning users to help them avoid common pitfalls that will bias and discredit their results. Several tools have been proposed to help deep learning users design their framework for neuroimaging data sets. Software overview We present here ClinicaDL, one of these software tools. ClinicaDL interacts with BIDS, a standard format in the neuroimaging field, and its derivatives, so it can be used with a large variety of data sets. Moreover, it checks the absence of data leakage when inferring the results of new data with trained networks, and saves all necessary information to guarantee the reproducibility of results. The combination of ClinicaDL and its companion project 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. Conclusions We implemented ClinicaDL to bring answers to three common issues encountered by deep learning users who are not always familiar with neuroimaging data: (1) the format and preprocessing of neuroimaging data sets, (2) the contamination of the evaluation procedure by data leakage and (3) a lack of reproducibility. We hope that its use by researchers will allow producing more reliable and thus valuable scientific studies in our field.

Mots clés: Deep learning; Reproducibility; Neuroimaging; Data leakage; Open-source

Domaines: Imagerie médicale; Intelligence artificielle [cs.AI]

Elina Thibeau-Sutre, Mauricio Diaz, Ravi Hassanaly, Alexandre M Routier, Didier Dormont, et al.. ClinicaDL: an open-source deep learning software for reproducible neuroimaging processing. Computer Methods and Programs in Biomedicine, In press, ⟨10.1016/j.cmpb.2022.106818⟩. ⟨hal-03351976v1⟩