Deep learning-based automatic segmentation of brain structures on MRI: A test-retest reproducibility analysis
This study emphasizes the necessity of using the same scanner type and protocol for reliable MRI studies, particularly for brain atrophy monitoring. The high repeatability of deep learning-based segmentation under these conditions confirms its efficacy for clinical and research applications.
Authors
- Jan Karwowski (ORCID: https://orcid.org/0000-0003-0431-3170)
- Ernest J. Bobeff (ORCID: https://orcid.org/0000-0003-1891-3791)
- Piotr Grzelak (ORCID: https://orcid.org/0000-0002-0970-2717)
- Mariusz Stasiołek (ORCID: https://orcid.org/0000-0002-2582-1708)
- Katarzyna Matera (ORCID: https://orcid.org/0000-0002-5108-369X)
- Marek Podyma (ORCID: https://orcid.org/0000-0001-5117-6821)
- Tomasz Puzio (ORCID: https://orcid.org/0000-0003-3793-7422)
- Małgorzata Siger (ORCID: https://orcid.org/0000-0001-5806-374X)
- Kosma Dunikowski
- Joanna Piwnik (ORCID: https://orcid.org/0000-0003-4605-7347)
- Sebastian Białkowski
Institutions
- Lodz University of Technology (PL)
- Medical University of Lodz (PL)
- Polish Mother’s Memorial Hospital Research Institute (PL)
Publication Details
- Journal
- Computational and Structural Biotechnology Journal
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1016/j.csbj.2025.04.007
- Citations
- 7
- Primary Topic
- Functional Brain Connectivity Studies
- Type
- article
- Field-Weighted Citation Impact
- 10.02
Funders
- European Commission
- European Regional Development Fund