Deep learning-based automatic segmentation of brain structures on MRI: A test-retest reproducibility analysis
Computational and Structural Biotechnology Journal · 2025-01 · 28 · 128-140
DOI: 10.1016/j.csbj.2025.04.007 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational and Structural Biotechnology Journal, online erschienen am 10.04.2025. Verfasst von Tomasz Puzio und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diagnostic Imaging, Polish Mothers' Memorial Hospital - Research Institute, Lodz, Poland. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: European Commission, European Regional Development Fund.
Abstract (Originalsprache)
Objective
The aim of our study was to assess the reproducibility of deep learning-based automatic segmentation of brain structures in MRI scans across different scanner types and magnetic field strengths, particularly focusing on the comparison between 1.5 T and 3 T MRI scanners.
Methods
Our analysis encompassed a comprehensive examination of MRI images, focusing on the consistency of volumetric segmentation. We utilized advanced deep learning techniques with human-in-the-loop as a part of the workflow for segmenting brain structures and compared results across subsequent scans using the same and different scanner types.
Results
Our findings revealed high consistency in volumetric segmentation when comparing scans conducted on the same type of scanner (1.5 T to 1.5 T or 3 T to 3 T). The study revealed slightly better segmentation results for 1.5 T scanners compared to 3 T scanners when each was used independently. However, cross-comparisons between different scanner types (1.5 T vs. 3 T) demonstrated slightly less consistency, highlighting the influence of magnetic field strength on segmentation accuracy.
Conclusion
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Diagnostic Imaging, Polish Mothers' Memorial Hospital - Research Institute, Lodz, Poland.
- Pixel Technology LLC, Lodz, Poland.
- Department of Biostatistics and Translational Medicine, Medical University of Lodz, Lodz, Poland.
- Department of Neurology, Medical University of Lodz, Lodz, Poland.
- Department of Neurosurgery and Neuro-Oncology, Barlicki University Hospital, Medical University of Lodz, Lodz, Poland.
- Department of Sleep Medicine and Metabolic Disorders, Medical University of Lodz, Lodz, Poland.
Förderung
- European Commission
- European Regional Development Fund
Zitieren
APA
Puzio, T., Matera, K., Karwowski, J., Piwnik, J., Białkowski, S., Podyma, M., Dunikowski, K., Siger, M., Stasiołek, M., Grzelak, P., & Bobeff, E. J. (2025). Deep learning-based automatic segmentation of brain structures on MRI: A test-retest reproducibility analysis. Computational and Structural Biotechnology Journal, 28, 128-140. https://doi.org/10.1016/j.csbj.2025.04.007
Vancouver
Puzio T, Matera K, Karwowski J, Piwnik J, Białkowski S, Podyma M, et al. Deep learning-based automatic segmentation of brain structures on MRI: A test-retest reproducibility analysis. Computational and Structural Biotechnology Journal. 2025;28:128-140. doi:10.1016/j.csbj.2025.04.007
BibTeX
@article{Puzio2025,
author = {Puzio, Tomasz and Matera, Katarzyna and Karwowski, Jan and Piwnik, Joanna and Białkowski, Sebastian and Podyma, Marek and Dunikowski, Kosma and Siger, Małgorzata and Stasiołek, Mariusz and Grzelak, Piotr and Bobeff, Ernest J},
title = {Deep learning-based automatic segmentation of brain structures on MRI: A test-retest reproducibility analysis},
journal = {Computational and Structural Biotechnology Journal},
year = {2025},
volume = {28},
pages = {128--140},
doi = {10.1016/j.csbj.2025.04.007}
}
EUVIMED