A Neighborhood Attention Transformer Network for Enhanced 3D Segmentation of the Left Anterior Descending Artery

Rafi Ibn Sultan, Chengyin Li, Yiannos Demetriou, Ahmed I. Ghanem, Joshua P. Kim et al.|August 12, 2026arXiv

Key Takeaway

Combining neighborhood attention mechanisms with uncertainty-weighted loss functions enables accurate segmentation of tiny, low-contrast anatomical structures even with limited training data—a practical approach for clinical imaging tasks where manual annotation is expensive and ambiguous.

Summary

This paper presents NA-UNETR, a transformer-based deep learning model for segmenting the Left Anterior Descending artery in CT scans.

architecture efficiency

Key Terms

transformer-architecture attention-mechanism parameter-efficient-fine-tuning homoscedastic-uncertainty anatomical-segmentation