VesSynth: Tubes Are All You Need for Robust Cross-Scale Cross-Modal 3D Vessel Segmentation
Chiara Mauri, Allison McKenzie, Cole Analoro, Emma Yeon, Rose Coviello, Jocelyn Mora, Etienne Chollet, Lucas J Deden-Binder, Ara Mahar, Stephanie Lin, Malak Benlahcen, Angelina Ream, Aliyah Jama, Itzel Garcia, Nam Tran, , Yaël Balbastre
This paper introduces VesSynth, a vessel segmentation framework trained on synthetic data that achieves state-of-the-art accuracy across multiple imaging modalities and spatial resolutions.
bioRxiv · Apr 6, 2026 · PreprintBioengineering