CAVE: Cerebral artery-vein segmentation in digital subtraction angiography

Ruisheng Su, Matthijs van der Sluijs, Yuan Chen, Sandra A. P. Cornelissen, Ruben van den Broek, Wim H. van Zwam, Aad van der Lugt, Wiro J. Niessen, Danny Ruijters, Theo van Walsum

Abstract: Highlights•The first automatic deep learning-based method for artery–vein segmentation in DSA is proposed.•CAVE generates artery–vein segmentations from 2D+time DSA series with variable frame lengths.•CAVE simultaneously harnesses spatial vasculature and temporal contrast flow characteristics.•CAVE promises to facilitate fast, accurate, and objective vasculature interpretation in DSA.