Artificial Intelligence-Driven 3-Dimensional Segmentation of Pediatric Brain Tumors Based on Navigated Intraoperative Ultrasound
This study demonstrates that automatic segmentation of pediatric brain tumors using navigated iUS is feasible and achieved high performance in most cases, with few outliers that showed moderate performance in tumor prediction. Future efforts will focus on real-time segmentation of residual tumor tissue during tumor resection. Ultimately, real-time visualization of automatically segmented tumors in 3 dimensions could improve intraoperative navigation and support neurosurgical decision making.
Authors
- Mariska Sie (ORCID: https://orcid.org/0000-0003-0404-381X)
- Eelco W. Hoving (ORCID: https://orcid.org/0000-0002-5587-0439)
- Tristan P. C. van Doormaal (ORCID: https://orcid.org/0000-0002-6299-3859)
- Kevin Klein Gunnewiek (ORCID: https://orcid.org/0009-0006-5476-6820)
- Karina J. Kersbergen (ORCID: https://orcid.org/0000-0001-8358-4635)
- Oscar H. J. Eelkman Rooda (ORCID: https://orcid.org/0000-0002-6407-0863)
- Emma E. Trouw
- Sander J. E. Eggermont
Institutions
- University Medical Center Utrecht (NL)
- University Hospital of Zurich (CH)
- Princess Máxima Center (NL)
- University of Twente (NL)
Publication Details
- Journal
- Operative Neurosurgery
- Published
- 2025-11-13
- DOI
- https://doi.org/10.1227/ons.0000000000001832
- Primary Topic
- Medical Image Segmentation Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00