MCANet: Medical Image Segmentation with Multi-Scale Cross-Axis Attention
This work addresses the challenge of segmenting variable-sized lesions and organs in medical images, offering an efficient solution for healthcare applications, though it is incremental as it builds on existing axial attention methods.
The paper tackles medical image segmentation by introducing Multi-scale Cross-axis Attention (MCA) to capture multi-scale information and long-range dependencies, achieving superior performance with only 4M+ parameters compared to heavier models on tasks like skin lesion and polyp segmentation.
Efficiently capturing multi-scale information and building long-range dependencies among pixels are essential for medical image segmentation because of the various sizes and shapes of the lesion regions or organs. In this paper, we present Multi-scale Cross-axis Attention (MCA) to solve the above challenging issues based on the efficient axial attention. Instead of simply connecting axial attention along the horizontal and vertical directions sequentially, we propose to calculate dual cross attentions between two parallel axial attentions to capture global information better. To process the significant variations of lesion regions or organs in individual sizes and shapes, we also use multiple convolutions of strip-shape kernels with different kernel sizes in each axial attention path to improve the efficiency of the proposed MCA in encoding spatial information. We build the proposed MCA upon the MSCAN backbone, yielding our network, termed MCANet. Our MCANet with only 4M+ parameters performs even better than most previous works with heavy backbones (e.g., Swin Transformer) on four challenging tasks, including skin lesion segmentation, nuclei segmentation, abdominal multi-organ segmentation, and polyp segmentation. Code is available at https://github.com/haoshao-nku/medical_seg.