MDEU-Net: Medical Image Segmentation Network Based on Multi-Head Multi-Scale Cross-Axis.

Journal: Sensors (Basel, Switzerland)
Published Date:

Abstract

Significant advances have been made in the application of attention mechanisms to medical image segmentation, and these advances are notably driven by the development of the cross-axis attention mechanism. However, challenges remain in handling complex images, particularly in multi-scale feature extraction and fine-detail capture. To address these limitations, this paper presents a novel network architecture, multi-head multi-scale cross-axis attention MDEU-Net, that leverages a multi-head attention mechanism processing input features in parallel. The proposed architecture enables the model to focus on both local and global information while capturing features at various spatial scales. Additionally, a gated attention mechanism facilitates efficient feature fusion by selectively emphasizing key features rather than relying on simple concatenation and improves the model's ability to capture critical details at multiple scales. Furthermore, the incorporation of residual connections further mitigates the gradient vanishing problem by enhancing the model's capacity to capture complex structures and fine details. This approach accelerates computation and enhances processing efficiency, while experimental results demonstrate that the proposed network outperforms traditional architectures in terms of performance.

Authors

  • Shengxian Yan
    Shaanxi Key Laboratory of Ultrasonics, School of Physics and Information Technology, Shanxi Normal University, Xi'an 710062, China.
  • Yuyang Lei
    Shaanxi Key Laboratory of Ultrasonics, School of Physics and Information Technology, Shanxi Normal University, Xi'an 710062, China.
  • Jing Zhang
    MOEMIL Laboratory, School of Optoelectronic Information, University of Electronic Science and Technology of China, Chengdu, China.
  • Xiao Gao
    Department of Biomedical Engineering, University of Melbourne, Parkville, VIC, Australia.
  • Xiang Li
    Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, United States.
  • Penghui Wang
  • Hui Cao