Despite recent advances in tractography, automatically reconstructing brain bundles in clinical settings remains a challenge. Here we present Q-FiberMapper (QFM), a framework that automatically preprocesses clinical data and reconstructs 33 major brain bundles with minimal user intervention. Furthermore, it derives insightful biomarkers and summarizes the findings in a human readable report. We validate QFM using a large cohort of 600 subjects, and show that it correctly reconstructs the shape and lateralization of major white-matter bundles. By simplifying and speeding the process of clinical reconstruction, QFM could help clinicians in the diagnosis and monitoring of brain pathologies.
This abstract and the presentation materials are available to members only; a login is required.