Deep Learning for Automated Ventricle and Periventricular Space Segmentation on CT and T1CE MRI in Neuro-Oncology Patients
The nnU-Net model outperformed the SynthSeg model on the internal dataset in both segmentation metrics and clinician ratings. While segmentation metrics showed no significant differences between the models on the external set, clinician ratings favored nnU-Net, suggesting enhanced clinical acceptability. This suggests that nnU-Net could contribute to more time-efficient and streamlined radiotherapy planning workflows.
Authors
- Mart Wubbels
- Miranda C.A. Kramer (ORCID: https://orcid.org/0009-0003-5040-998X)
- Jelmer M. Wolterink (ORCID: https://orcid.org/0000-0001-5505-475X)
- Charlotte L. Brouwer (ORCID: https://orcid.org/0000-0002-2349-7369)
- Daniëlle B. P. Eekers (ORCID: https://orcid.org/0000-0003-1917-6279)
- Hiska L. van der Weide (ORCID: https://orcid.org/0000-0001-6734-2345)
- Inge Compter (ORCID: https://orcid.org/0000-0002-6155-1565)
- Wouter van Elmpt
- Femke Vaassen
- Catharina M.L. Zegers
- Kati Palmgren
- Hendrik H.G. Hansen (ORCID: https://orcid.org/0000-0001-5860-8981)
- David Hofstede (ORCID: https://orcid.org/0000-0001-6717-8864)
- Nikolina Birimac
- Marvin Ribeiro (ORCID: https://orcid.org/0000-0002-1522-4299)
Institutions
- University Medical Center Groningen (NL)
- University of Groningen (NL)
- Maastricht University Medical Centre (NL)
- Maastricht University (NL)
- Maastro Clinic (NL)
- University of Twente (NL)
Publication Details
- Journal
- Cancers
- Published
- 2025-05-08
- DOI
- https://doi.org/10.3390/cancers17101598
- Primary Topic
- Advanced Radiotherapy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- ZonMw