Meeting Banner
Abstract #4795

Deep learning Circle of Willis arterial labeling strategies for pipeline of cerebrovascular disease analysis

Žiga Bizjak1, Aichi Chien, PhD, FAHA2, Jan Tasič1, and Žiga Špiclin1
1Laboratory of Imaging Technologies, Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia, 2Division of Interventional Neuroradiology, Department of Radiological Sciences, Ronald Reagan UCLA Medical Center, David Geffen School of Medicine at UCLA, Los Angeles, CA, United States


The correlation between different variants of the Circle of Willis (CoW) and cerebrovascular disorders such as stroke, aneurysms and mental disorders is not yet well understood. A step towards a better understanding of the role of CoW in the aforementioned diseases is the automatic labeling of main vessels. In this work we tested three different approaches and observed high mIoU value of 0.870. As such the automatic anatomical labelling of the CoW seems feasible for clinical evaluation of the association of different anatomical variants with the risk factors of cerebrovascular pathologies.

This abstract and the presentation materials are available to members only; a login is required.

Join Here