English

When Experts Disagree: Characterizing Annotator Variability for Vessel Segmentation in DSA Images

Image and Video Processing 2025-08-15 v1 Computer Vision and Pattern Recognition

Abstract

We analyze the variability among segmentations of cranial blood vessels in 2D DSA performed by multiple annotators in order to characterize and quantify segmentation uncertainty. We use this analysis to quantify segmentation uncertainty and discuss ways it can be used to guide additional annotations and to develop uncertainty-aware automatic segmentation methods.

Keywords

Cite

@article{arxiv.2508.10797,
  title  = {When Experts Disagree: Characterizing Annotator Variability for Vessel Segmentation in DSA Images},
  author = {M. Geshvadi and G. So and D. D. Chlorogiannis and C. Galvin and E. Torio and A. Azimi and Y. Tachie-Baffour and N. Haouchine and A. Golby and M. Vangel and W. M. Wells and Y. Epelboym and R. Du and F. Durupinar and S. Frisken},
  journal= {arXiv preprint arXiv:2508.10797},
  year   = {2025}
}
R2 v1 2026-07-01T04:50:14.173Z