SEEG trajectory planning: combining stability, structure and scale in vessel extraction.

Area of Science:

• Neurosurgery
• Medical Imaging
• Computational Anatomy

Background:

• Stereoelectroencephalography (SEEG) is crucial for localizing seizure onset zones in epilepsy patients.
• Intracranial hemorrhage is a significant complication of SEEG implantation, occurring in 0.6-2.7% of cases.
• Current SEEG planning lacks automated assistance for identifying safe, avascular electrode trajectories.

Purpose of the Study:

• To develop a computer-assisted blood vessel extraction method for SEEG trajectory planning.
• To enhance the safety of SEEG implantation by optimizing electrode trajectories away from critical structures.
• To improve upon existing vessel segmentation techniques for neurosurgical planning.

Main Methods:

• Developed a novel blood vessel extraction framework utilizing multi-modal imaging data.
• The method integrates object scale and neighboring structure information for robust segmentation.
• Validated the framework on twelve multi-modal patient image datasets.

Main Results:

• The proposed method achieved a mean Dice Similarity Coefficient (DSC) of 0.88 ± 0.03.
• This represents a statistically significant improvement over the current standard of care (DSC = 0.78 ± 0.02).
• The enhanced segmentation accuracy aids in identifying safer SEEG electrode paths.

Conclusions:

• The developed blood vessel extraction method significantly improves SEEG trajectory planning safety.
• Computer-assisted planning offers a promising approach to minimize complications associated with SEEG implantation.
• This technique has the potential to enhance patient outcomes in epilepsy surgery.