Brain Vessels Enhancement in 3D CT Data Using Eigenvalues of Hessian Matrix

Abstract

Cerebrovascular pathologies represent very serious life-threatening diseases and therefore great importance is attached to improving the diagnostic process of these diseases. In this work, an approach for brain vessels enhancement in 3D CT angiographic data has been proposed. A 3D binary mask of the brain was constructed and used for brain tissue extraction, in which the cerebral vessels were then enhanced using advanced filters based on Hessian matrix computation and analysis of Hessian eigenvalues. A dataset of 5 anonymized patient CT scans was used to design this approach.