Comparative Study of Automated Algorithms for Brain Arteriovenous Malformation Nidus Extent Identification Using 3DRA

GARCÍA, CAMILA; NARATA, ANA PAULA; LIU, JIANMIN; FANG, YIBIN; LARRABIDE, IGNACIO

Cardiovascular Engineering and Technology

Springer

Año: 2023

1869-408X

Purpose When performing a brain arteriovenous malformation (bAVMs) intervention, computer-assisted analysis of bAVMscan aid clinicians in planning precise therapeutic alternatives. Therefore, we aim to assess currently available methods forbAVMs nidus extent identifcation over 3DRA. To this end, we establish a unifed framework to contrast them over the samedataset, fully automatising the workfows.Materials and Methods We retrospectively collected contrast-enhanced 3DRA scans of patients with bAVMs. A segmentation network was used to automatically acquire the brain vessels segmentation for each case. We applied the nidus extentidentifcation algorithms over each of the segmentations, computing overlap measurements against manual nidus delineations.Results We evaluated the methods over a private dataset with 22 3DRA scans of individuals with bAVMs. The best-performing alternatives resulted in ퟎ.ퟖퟐ ± ퟎ.ퟏퟒ and ퟎ.ퟖퟏ ± ퟎ.ퟏퟔ dice coefcient values.Conclusions The mathematical morphology-based approach showed higher robustness through inter-case variability. Theskeleton-based approach leverages the skeleton topomorphology characteristics, while being highly sensitive to anatomicalvariations and the skeletonisation method employed. Overall, nidus extent identifcation algorithms are also limited by thequality of the raw volume, as the consequent imprecise vessel segmentation will hinder their results. Performance of theavailable alternatives remains subpar. This analysis allows for a better understanding of the current limitations