Abstract
Diffusion MRI and tractography hold great potential for surgery planning, especially to preserve eloquent white matter during resections. However, fiber tract reconstruction requires an expert with detailed understanding of neuroanatomy. Several automated approaches have been proposed, using different strategies to reconstruct the white matter tracts in a supervised fashion. However, validation is often limited to comparison with manual delineation by overlap-based measures, which is limited in characterizing morphological and topological differences. In this work, we set up a fully automated pipeline based on anatomical criteria that does not require manual intervention, taking advantage of atlas-based criteria and advanced acquisition protocols available on clinical-grade MRI scanners. Then, we extensively validated it on epilepsy patients with specific focus on language-related bundles. The validation procedure encompasses different approaches, including simple overlap with manual segmentations from two experts, feasibility ratings from external multiple clinical raters and relation with task-based functional MRI. Overall, our results demonstrate good quantitative agreement between automated and manual segmentation, in most cases better performances of the proposed method in qualitative terms, and meaningful relationships with task-based fMRI. In addition, we observed significant differences between experts in terms of both manual segmentation and external ratings. These results offer important insights on how different levels of validation complement each other, supporting the idea that overlap-based measures, although quantitative, do not offer a full perspective on the similarities and differences between automated and manual methods.