In this section
@inproceedings{Wang:2026:10.1109/ISBI61048.2026.11515427,
author = {Wang, S and Fang, Y and Li, Y and Nan, Y and Walsh, S and Yang, G},
doi = {10.1109/ISBI61048.2026.11515427},
title = {ILLUMINATING UNCERTAINTY: A TRIFOCAL FINE-GRAINED AND TRANSFORMER-LIKE AXIAL ATTENTION FRAMEWORK FOR PULMONARY VASCULAR SEGMENTATION},
url = {http://dx.doi.org/10.1109/ISBI61048.2026.11515427},
year = {2026}
}
TY - CPAPER
AB - Pulmonary artery segmentation has recently emerged as a novel biomarker for lung diseases, necessitating accurate and efficient automatic segmentation methods. However, in none contrast enhanced CT (NECT) scans, the low tissue contrast poses a persistent challenge for accurately delineating multibranch structures and small pulmonary arteries, particularly in complex pulmonary conditions. In this work, we introduce IFSAttUNet, a trifocal fine-grained attention framework enhanced by transformer-like triple-axis multi-head attention. This method provides an explicit measure for 'uncertain' or 'hard-to-recognize' regions, thereby guiding the network's focus toward artery boundaries. Moreover, IFSAttUNet features a lightweight architecture capable of capturing global dependencies effectively. Our empirical results demonstrate that IFSAttUNet outperforms state-of-the-art Gaussian-based fuzzy attention and transformer based models, offering a promising avenue for robust pulmonary vascular analysis.
AU - Wang,S
AU - Fang,Y
AU - Li,Y
AU - Nan,Y
AU - Walsh,S
AU - Yang,G
DO - 10.1109/ISBI61048.2026.11515427
PY - 2026///
SN - 1945-7928
TI - ILLUMINATING UNCERTAINTY: A TRIFOCAL FINE-GRAINED AND TRANSFORMER-LIKE AXIAL ATTENTION FRAMEWORK FOR PULMONARY VASCULAR SEGMENTATION
UR - http://dx.doi.org/10.1109/ISBI61048.2026.11515427
ER -
For enquiries about the MRI Physics Collective, please contact:
Mary Finnegan
Senior MR Physicist at the Imperial College Healthcare NHS Trust
Pete Lally
Assistant Professor in Magnetic Resonance (MR) Physics at Imperial College
Jan Sedlacik
MR Physicist at the Robert Steiner MR Unit, Hammersmith Hospital Campus