ClinicaDL: an open-source deep learning software for reproducible neuroimaging processing
Résumé
In addition to facing a reproducibility crisis (Hutson, 2018), deep learning studies often include methodological flaws, especially in the field of neuroimaging in which deep learning contributors may not be aware of the specificities of the domain. This situation leads to the production of biased and overestimated results. To overcome this issue, we developed ClinicaDL: an end-to-end deep learning framework for deep learning users working on neuroimaging data that aims to prevent common pitfalls that we identified and described in our previous study (Wen et al., 2020).
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|
