An advanced automated pipeline for brain tumour segmentation on magnetic resonance imaging for gamma knife radiosurgery

AND PURPOSE: Accurate delineation of intracranial tumours is crucial for stereotactic radiosurgery (SRS), where target definition directly influences treatment outcome. We developed and clinically integrated an automated multi-tumour segmentation pipeline using three-dimensional nnU-Net models for brain metastases, pituitary adenomas, vestibular schwannomas, and meningiomas.

No actionable change for audiologists; this is an imaging engineering advance, but improved tumour segmentation for acoustic neuromas could eventually improve treatment precision and reduce collateral cochlear damage.

Automated MRI segmentation pipelines that improve Gamma Knife planning accuracy could reduce radiation exposure to the cochlea and auditory nerve in acoustic neuroma cases, with downstream implications for hearing preservation.

1. 01Automated MRI pipeline developed for brain tumour segmentation to aid Gamma Knife radiosurgery planning.
2. 02Peripheral relevance to audiology via application to acoustic neuromas and vestibular schwannomas.
3. 03Improved segmentation accuracy could reduce inadvertent radiation dose to hearing structures.
4. 04Study is primarily a neuro-oncology/medical physics tool; audiology application is indirect.
5. 05No audiological outcome data reported.

PMID

42338484

DOI

10.1016/j.phro.2026.101010.

Journal

Physics and Imaging in Radiation Oncology

Publication type

research_article

Evidence level

4

Population

Brain tumour patients undergoing Gamma Knife radiosurgery planning

Intervention

Automated MRI brain tumour segmentation pipeline