AG-TAL
Cross-source consensus on AG-TAL from 1 sources and 4 claims.
1 sources · 4 claims
Uses
How it works
Evidence quality
Highlighted claims
- AG-TAL is added to cross-entropy loss as a composite objective with radius-aware Dice, breakage-aware clDice, and adjacency-aware co-occurrence components. — AG-TAL: Anatomically-Guided Topology-Aware Loss for Multiclass Segmentation of the Circle of Willis Using Large-Scale Multi-Center Datasets
- AG-TAL combines anatomical and topological priors to improve computationally efficient multiclass Circle of Willis segmentation. — AG-TAL: Anatomically-Guided Topology-Aware Loss for Multiclass Segmentation of the Circle of Willis Using Large-Scale Multi-Center Datasets
- AG-TAL is intended to function without architecture changes or inference pipeline changes. — AG-TAL: Anatomically-Guided Topology-Aware Loss for Multiclass Segmentation of the Circle of Willis Using Large-Scale Multi-Center Datasets
- AG-TAL improved performance across CNN, Transformer-based, and Mamba-based backbones. — AG-TAL: Anatomically-Guided Topology-Aware Loss for Multiclass Segmentation of the Circle of Willis Using Large-Scale Multi-Center Datasets