A 2.5D U-Net with pixel-wise cross-slice attention and skip attention gating achieves Dice 0.9535 on a private femur MRI dataset, outperforming compared 2D, 2.5D, and 3D baselines in full-scan evaluation.
U-net: Convolutional networks for biomedical image segmentation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
XAG-Net: A Cross-Slice Attention and Skip Gating Network for 2.5D Femur MRI Segmentation
A 2.5D U-Net with pixel-wise cross-slice attention and skip attention gating achieves Dice 0.9535 on a private femur MRI dataset, outperforming compared 2D, 2.5D, and 3D baselines in full-scan evaluation.