Patient-specific prediction of SEEG electrode bending for stereotactic neurosurgical planning

Purpose Electrode bending observed after stereotactic interventions is typically not accounted for in either computer-assisted planning algorithms, where straight trajectories are assumed, or in quality assessment, where only metrics related to entry and target points are reported. Our aim is to provide a fully automated and validated pipeline for the prediction of stereo-electroencephalography (SEEG) electrode bending. Methods We transform electrodes of 86 cases into a common space and compare features-based and image-based neural networks on their ability to regress local displacement ($$\mathbf{lu} $$ lu ) or electrode bending ($$\hat{\mathbf{eb }}$$ eb ^ ). Electrodes were stratified into six groups based on brain structures at the entry and target point. Models, both with and without Monte Carlo (MC) dropout, were trained and validated using tenfold cross-validation. Results mage-based models outperformed features-based models for all groups, and models that predicted $$\mathbf{lu} $$ lu performed better than for $$\hat{\mathbf{eb }}$$ eb ^ . Image-based model prediction with MC dropout resulted in lower mean squared error (MSE) with improvements up to 12.9% ($$\mathbf{lu} $$ lu ) and 39.9% ($$\hat{\mathbf{eb }}$$ eb ^ ), compared to no dropout. Using an image of brain tissue types (cortex, white and deep grey matter) resulted in similar, and sometimes better performance, compared to using a T1-weighted MRI when predicting $$\mathbf{lu} $$ lu . When inferring trajectories of image-based models (brain tissue types), 86.9% of trajectories had an MSE$$\le 1$$ ≤ 1 mm. Conclusion An image-based approach regressing local displacement with an image of brain tissue types resulted in more accurate electrode bending predictions compared to other approaches, inputs, and outputs. Future work will investigate the integration of electrode bending into planning and quality assessment algorithms.