GASA-UNet: Global Axial Self-Attention U-Net for 3D Medical Image Segmentation

2024-09-20 · Chengkun Sun, Russell Stevens Terry, Jiang Bian, Jie Xu

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.

📄 PDF Abstract BibTeX arXiv:2409.13146

Code (0)

등록된 구현이 없습니다.

Tasks

Image Segmentation Medical Image Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

HCMA-UNet: A Hybrid CNN-Mamba UNet with Axial Self-Attention for Efficient Breast Cancer Segmentation

2025-01-01 · Haoxuan Li, Wei Song, Peiwu Qin, Xi Yuan 외

Breast cancer lesion segmentation in DCE-MRI remains challenging due to heterogeneous tumor morphology and indistinct boundaries. To address these challenges, this study proposes a novel hybrid segmentation network, HCMA…

Computational Efficiency Lesion Segmentation Mamba Segmentation

Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation

2020-03-17 · ECCV 2020 8 · Huiyu Wang, Yukun Zhu, Bradley Green, Hartwig Adam 외

Convolution exploits locality for efficiency at a cost of missing long range context. Self-attention has been adopted to augment CNNs with non-local interactions. Recent works prove it possible to stack self-attention la…

image-classification Image Classification Panoptic Segmentation Position

Axially Expanded Windows for Local-Global Interaction in Vision Transformers

2022-09-19 · Zhemin Zhang, Xun Gong

Recently, Transformers have shown promising performance in various vision tasks. A challenging issue in Transformer design is that global self-attention is very expensive to compute, especially for the high-resolution vi…

AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentation

2021-10-20 · Xiangyi Yan, Hao Tang, Shanlin Sun, Haoyu Ma 외

Recent advances in transformer-based models have drawn attention to exploring these techniques in medical image segmentation, especially in conjunction with the U-Net model (or its variants), which has shown great succes…

Decoder GPU Image Segmentation Medical Image Segmentation+3

IGASA: Integrated Geometry-Aware and Skip-Attention Modules for Enhanced Point Cloud Registration

2026-03-13 · Dongxu Zhang, Jihua Zhu, Shiqi Li, Wenbiao Yan 외 arxiv

Point cloud registration (PCR) is a fundamental task in 3D vision and provides essential support for applications such as autonomous driving, robotics, and environmental modeling. Despite its widespread use, existing met…

Point Cloud Registration Autonomous Driving