Artificial Intelligence–Assisted Evaluation of the Spatial Relationship between Brain Arteriovenous Malformations and the Corticospinal Tract to Predict Postsurgical Motor Defects

The workflow of segmentation, fiber tracking, and registration. Segmentation and fiber tracking were performed by the algorithm independently on TOF-MRA and DTI scans. The CSTs tracked on DTI scans were registered to TOF-MRA with BAVM segmentation to calculate the AI-based indicators.

Schematic diagram of AI-based indicator calculation. The letters a–h indicate CSTs. The red, green, and blue circles indicate the borders of the BAVM lesion and the border with radii extended by the dilation algorithm to 10 and 50mm from the lesion, respectively. Letters a–b indicate CSTs within 10 mm of the border of the BAVM lesion. Letters a–d indicate CSTs within 50mm from the border of the BAVM lesion. N_a-b and N_a-d indicate the number of fibers between a and b and between a and d, respectively. P_a-b and P_a’-d indicate the sum of voxel points of fibers between a and b and between a and d, respectively.