Contrastive learning for neural fingerprinting from limited neuroimaging data
The contrastive method showed added value in the "leave subject out" scenario, demonstrating flexibility comparable to correlation-based methods and robustness across different data sizes. These findings suggest that contrastive learning and data augmentation offer a scalable solution for neural fingerprinting, even with limited sample sizes.
Authors
- Nikolas Kampel (ORCID: https://orcid.org/0009-0004-0629-0456)
- Jürgen Dammers (ORCID: https://orcid.org/0000-0003-1526-6592)
- Irene Neuner (ORCID: https://orcid.org/0000-0002-5164-8873)
- N. Jon Shah (ORCID: https://orcid.org/0000-0002-8151-6169)
- Farah Abdellatif
Institutions
- Forschungszentrum Jülich (DE)
- Jülich Aachen Research Alliance (DE)
- RWTH Aachen University (DE)
Publication Details
- Journal
- Frontiers in Nuclear Medicine
- Published
- 2024-11-13
- DOI
- https://doi.org/10.3389/fnume.2024.1332747
- Citations
- 1
- Primary Topic
- Functional Brain Connectivity Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.34
Funders
- Deutsche Forschungsgemeinschaft
- RWTH Aachen University