Vessel tractography using an intensity based tensor model
Suheyla Cetin, Gozde Unal, Ali Demir, Anthony Joseph Yezzi, Muzaffer Degertekin
In this paper, we propose a novel tubular structure segmentation method, which is based on an intensity-based tensor that fits to a vessel. Our model is initialized with a single seed point and it is capable of capturing whole vessel tree by an automatic branch detection algorithm. The centerline of the vessel as well as its thickness is extracted. We demonstrated the performance of our algorithm on 3 complex contrast varying tubular structured synthetic datasets for quantitative validation. Additionally, extracted arteries from 10 CTA (Computed Tomography Angiography) volumes are qualitatively evaluated by a cardiologist expert's visual scores.