XAG-Net: A Cross-Slice Attention and Skip Gating Network for 2.5D Femur MRI Segmentation

TL;DR

XAG-Net introduces a novel 2.5D architecture with cross-slice attention and skip gating to improve femur MRI segmentation accuracy and efficiency over existing methods.

Contribution

It presents a new 2.5D U-Net-based model with pixel-wise cross-slice attention and skip gating mechanisms for enhanced segmentation performance.

Findings

XAG-Net outperforms baseline models in accuracy.

The CSA and AG modules are critical for performance.

The model maintains computational efficiency.

Abstract

Accurate segmentation of femur structures from Magnetic Resonance Imaging (MRI) is critical for orthopedic diagnosis and surgical planning but remains challenging due to the limitations of existing 2D and 3D deep learning-based segmentation approaches. In this study, we propose XAG-Net, a novel 2.5D U-Net-based architecture that incorporates pixel-wise cross-slice attention (CSA) and skip attention gating (AG) mechanisms to enhance inter-slice contextual modeling and intra-slice feature refinement. Unlike previous CSA-based models, XAG-Net applies pixel-wise softmax attention across adjacent slices at each spatial location for fine-grained inter-slice modeling. Extensive evaluations demonstrate that XAG-Net surpasses baseline 2D, 2.5D, and 3D U-Net models in femur segmentation accuracy while maintaining computational efficiency. Ablation studies further validate the critical role of the CSA and AG modules, establishing XAG-Net as a promising framework for efficient and accurate femur MRI segmentation.