GCA-ResUNet: Medical Image Segmentation Using Grouped Coordinate Attention

TL;DR

This work addresses the challenge of long-range context modeling in medical image segmentation by introducing GCA-ResUNet, which inserts a lightweight Grouped Coordinate Attention (GCA) module into a ResNet50 backbone. By partitioning channels into groups and applying direction-aware pooling, GCA learns diverse group-specific context that enhances small-structure delineation while preserving CNN efficiency. Across Synapse and ACDC benchmarks, GCA-ResUNet achieves state-of-the-art Dice scores and improves boundary accuracy compared with both CNN and Transformer baselines, with minimal compute overhead. The approach offers a practical, scalable solution for clinical deployment and lays groundwork for future extensions to 3D segmentation and pretraining-based improvements.

Abstract

Accurate segmentation of heterogeneous anatomical structures is pivotal for computer-aided diagnosis and subsequent clinical decision-making. Although U-Net based convolutional neural networks have achieved remarkable progress, their intrinsic locality and largely homogeneous attention formulations often limit the modeling of long-range contextual dependencies, especially in multi-organ scenarios and low-contrast regions. Transformer-based architectures mitigate this issue by leveraging global self-attention, but they usually require higher computational resources and larger training data, which may impede deployment in resource-constrained clinical environments.In this paper, we propose GCA-ResUNet, an efficient medical image segmentation framework equipped with a lightweight and plug-and-play Grouped Coordinate Attention (GCA) module. The proposed GCA decouples channel-wise context modeling into multiple groups to explicitly account for semantic heterogeneity across channels, and integrates direction-aware coordinate encoding to capture structured spatial dependencies along horizontal and vertical axes. This design enhances global representation capability while preserving the efficiency advantages of CNN backbones. Extensive experiments on two widely used benchmarks, Synapse and ACDC, demonstrate that GCA-ResUNet achieves Dice scores of 86.11% and 92.64%, respectively, outperforming a range of representative CNN and Transformer-based methods, including Swin-UNet and TransUNet. In particular, GCA-ResUNet yields consistent improvements in delineating small anatomical structures with complex boundaries. These results indicate that the proposed approach provides a favorable trade-off between segmentation accuracy and computational efficiency, offering a practical and scalable solution for clinical deployment.

Figures (7)

• Figure 1: Schematic diagram of the GCA-ResUNet network. The architecture adopts a U-Net–style encoder–decoder structure, with residual blocks incorporated in the encoder and skip connections to enable multi-scale feature extraction and precise pixel-level segmentation.
• Figure 2: Grouped Coordinate Attention (GCA) network model diagram.
• Figure 3: Comparison of segmentation performance on the Synapse dataset.
• Figure 4: Comparison of segmentation performance on the ACDC.
• Figure 5: Performance comparison of the original and modified Res50 UNet equipped with different modules on the Synapse dataset in terms of DSC (%). The y-axis is truncated to [50, 100] for better visualization.