Application of deep neural networks in automatized ventriculometry and segmentation of the aqueduct in pediatric hydrocephalus patients
All tested models performed well in pediatric hydrocephalus segmentation, with no fundamental differences in overall performance. However, nnU-Net demonstrated key advantages due to its lack of preprocessing requirements, which allow the successful handling of even the most challenging subjects. These features make it easily implementable for clinical applications, providing fast and reliable ventricular segmentation and quantification.
Authors
- Christopher Güttler (ORCID: https://orcid.org/0000-0003-2448-3986)
- Fabienne Kühne (ORCID: https://orcid.org/0000-0002-1735-0125)
- Andrea Dell’Orco (ORCID: https://orcid.org/0000-0002-3964-8360)
- Juliane Stöckel
- Kilian Rüther
- Anna Tietze (ORCID: https://orcid.org/0000-0002-2601-9055)
- Ulrich-Wilhelm Thomale
Institutions
- Berlin Institute of Health at Charité - Universitätsmedizin Berlin (DE)
- Charité - Universitätsmedizin Berlin (DE)
Publication Details
- Journal
- Neuroradiology
- Published
- 2025-11-27
- DOI
- https://doi.org/10.1007/s00234-025-03848-y
- Primary Topic
- Cerebrospinal fluid and hydrocephalus
- Type
- article
- Field-Weighted Citation Impact
- 0.00