Related Experiment Video
Updated: Sep 17, 2025
09:41
A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
Published on: May 20, 2016
12.4K
Fully automatic anatomical landmark localization and trajectory planning for navigated external ventricular drain
Mathijs de Boer1, Jesse A M van Doormaal2, Mare H Köllen2
11Image Sciences Institute, University Medical Centre Utrecht; and.
Neurosurgical Focus
|July 1, 2025
Summary
This study developed an automated method for external ventricular drain (EVD) placement, achieving accurate landmark localization and trajectory planning with CT/MRI scans. The efficient process is suitable for emergency settings.
Area of Science:
- Neurosurgery
- Medical Imaging
- Computational Anatomy
Background:
- Accurate placement of external ventricular drains (EVDs) is crucial for managing intracranial pressure.
- Current methods for EVD trajectory planning often rely on manual landmark identification, which can be time-consuming and prone to error.
Purpose of the Study:
- To develop and validate a fully automatic method for anatomical landmark localization and trajectory planning for EVD placement.
- To assess the accuracy and robustness of the automated method using CT and MRI scans.
Main Methods:
- A neural network was trained on 125 CT and 137 MRI scans for automatic localization of seven anatomical landmarks.
- EVD trajectories were automatically planned targeting the foramen of Monro, with performance evaluated using Kakarla grades by three clinicians.
- Interobserver agreement and the impact of landmark localization error on trajectory planning were analyzed.
Main Results:
- The automated landmark localization achieved a mean error of 4.0 mm (SD 2.6 mm).
- Automated trajectory planning resulted in a Kakarla grade of 1 in 92.9% of cases, with strong interobserver agreement.
- No significant differences in performance were observed between CT and MRI modalities or placement sides.
Conclusions:
- The developed method is efficient and robust for anatomical landmark localization and accurate EVD trajectory planning.
- The short processing time makes this method suitable for emergency neurosurgical applications.
