Recent advances in the open-source ClinicaDL software for reproducible neuroimaging with deep learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2024

Recent advances in the open-source ClinicaDL software for reproducible neuroimaging with deep learning

Elina Thibeau-Sutre

Abstract

In this paper, we present ClinicaDL, an open-source software platform that aims at enhancing the reproducibility and rigor of research for deep learning in neuroimaging. We first provide an overview of the software platform and then focus on recent advances. Features of the software aim at addressing three key issues in the field: the lack of reproducibility, the methodological flaws that plague many published studies and the difficulties using neuroimaging datasets for people with little expertise in this application area. Key existing functionalities include automatic data splitting, checking for data leakage, standards for data organization and results storing, continuous integration and integration with Clinica for preprocessing, amongst others. The most prominent recent features are as follows. We now provide various data augmentation and synthetic data generation functions (both standard and advanced ones including motion and hypometabolism simulation). Continuous integration test data are now versioned using DVC (data version control). Tools for generating validation splits have been made more generic. We made major improvements regarding usability and performance. We now support multi-GPU training and automatic mixed precision (to exploit tensor cores). We created a graphical interface to easily generate training specifications. We allow tracking of experiments through standard tools (MLflow, Weights&Biases). We believe that ClinicaDL can contribute to enhance the trustworthiness of research in deep learning for neuroimaging. Moreover, its functionalities and coding practices may serve as inspiration for the whole medical imaging community, beyond neuroimaging.
Fichier principal
Vignette du fichier
Hassanaly_SPIE_2024_ClinicaDL.pdf (573.6 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04419141 , version 1 (26-01-2024)

Licence

Attribution

Identifiers

  • HAL Id : hal-04419141 , version 1

Cite

Ravi Hassanaly, Camille Brianceau, Mauricio Diaz, Sophie Loizillon, Elina Thibeau-Sutre, et al.. Recent advances in the open-source ClinicaDL software for reproducible neuroimaging with deep learning. SPIE Medical Imaging, Feb 2024, San Diego, United States. ⟨hal-04419141⟩
14 View
0 Download

Share

Gmail Facebook X LinkedIn More