GASA-UNet: Global Axial Self-Attention U-Net for 3D Medical Image Segmentation
This work addresses segmentation problems in medical imaging for clinicians and researchers, with incremental improvements in performance for smaller anatomical structures.
The paper tackled the challenge of accurate segmentation of multiple organs and pathological tissues in 3D medical imaging by introducing GASA-UNet with a novel Global Axial Self-Attention block, resulting in improved Dice scores and Normalized Surface Dice on benchmark datasets like BTCV, AMOS, and KiTS23.
Accurate segmentation of multiple organs and the differentiation of pathological tissues in medical imaging are crucial but challenging, especially for nuanced classifications and ambiguous organ boundaries. To tackle these challenges, we introduce GASA-UNet, a refined U-Net-like model featuring a novel Global Axial Self-Attention (GASA) block. This block processes image data as a 3D entity, with each 2D plane representing a different anatomical cross-section. Voxel features are defined within this spatial context, and a Multi-Head Self-Attention (MHSA) mechanism is utilized on extracted 1D patches to facilitate connections across these planes. Positional embeddings (PE) are incorporated into our attention framework, enriching voxel features with spatial context and enhancing tissue classification and organ edge delineation. Our model has demonstrated promising improvements in segmentation performance, particularly for smaller anatomical structures, as evidenced by enhanced Dice scores and Normalized Surface Dice (NSD) on three benchmark datasets, i.e., BTCV, AMOS, and KiTS23.