TL;DR
The proposed Skeleton-Aware SAM2 improves both overlap-based and topology-aware performance over strong baselines and topology-aware loss variants and suggests that explicit morphology-guided conditioning provides useful structural bias for topology-sensitive angiographic vessel segmentation under domain shifts.
TAPDecoderFT is proposed, a topology-responsive, role-structured adaptation framework that improves both DSC and clDice over GenericLoRA-r4 and narrow TAP-r4 in all six directions and is comparable to full fine-tuning.
Unsupervised domain adaptation (UDA) enables segmentation models to generalize to unlabeled clinical domains. However, existing methods primarily address appearance-level discrepancies, while neglecting topological mismatches in connectivity, branching, and loop structure-characteristics of curvilinear anatomies. This...
This paper proposes ReG-SAM, a SAM-based framework tailored to 2D vessel segmentation that leverages reference graph set for enhancing vascular representations and introduces two modality-aware representations derived from the reference masks.
This work proposes a novel two-stage segmentation framework that provides a favorable trade-off between segmentation accuracy and inference efficiency, supporting its potential for practical clinical deployment.
B-MIM is introduced, a modification of the iBOT objective that stochastically reduces global semantic alignment to prioritize local patch reconstruction and suggests that reducing global semantic pressure during pretraining enhances generalization to intricate anatomical structures.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
