ScarNet: a novel foundation model for automated myocardial scar quantification from late gadolinium-enhancement images

Neda Tavakoli, Amir Ali Rahsepar, Brandon Benefield, Daming Shen, Santiago López-Tapia, Florian Schiffers, Jeffrey J. Goldberger, Christine M. Albert, Edwin Wu, Aggelos K. Katsaggelos, Daniel Lee, Daniel KimJournal of Cardiovascular Magnetic Resonance 2025 · DOI

Abstract

ScarNet outperformed MedSAM and nnU-Net for predicting myocardial and scar boundaries in LGE images of patients with ischemic cardiomyopathy. The Monte Carlo simulations demonstrated that ScarNet is less sensitive to noise perturbations than other tested networks.
BibTeX
@article{tavakoli2025scarnet,
  author = {Neda Tavakoli and Amir Ali Rahsepar and Brandon Benefield and Daming Shen and Santiago López-Tapia and Florian Schiffers and Jeffrey J. Goldberger and Christine M. Albert and Edwin Wu and Aggelos K. Katsaggelos and Daniel Lee and Daniel Kim},
  title = {{ScarNet: a novel foundation model for automated myocardial scar quantification from late gadolinium-enhancement images}},
  journal = {Journal of Cardiovascular Magnetic Resonance},
  year = {2025},
  doi = {10.1016/j.jocmr.2025.101945},
}
Figure