Saved in:
Bibliographic Details
Main Authors: Zhao, Yican, Wang, Ce, Hao, You, Li, Lei, Liao, Tianli
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.12763
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918142084644864
author Zhao, Yican
Wang, Ce
Hao, You
Li, Lei
Liao, Tianli
author_facet Zhao, Yican
Wang, Ce
Hao, You
Li, Lei
Liao, Tianli
contents Medical image segmentation grapples with challenges including multi-scale lesion variability, ill-defined tissue boundaries, and computationally intensive processing demands. This paper proposes the DyGLNet, which achieves efficient and accurate segmentation by fusing global and local features with a dynamic upsampling mechanism. The model innovatively designs a hybrid feature extraction module (SHDCBlock), combining single-head self-attention and multi-scale dilated convolutions to model local details and global context collaboratively. We further introduce a dynamic adaptive upsampling module (DyFusionUp) to realize high-fidelity reconstruction of feature maps based on learnable offsets. Then, a lightweight design is adopted to reduce computational overhead. Experiments on seven public datasets demonstrate that DyGLNet outperforms existing methods, particularly excelling in boundary accuracy and small-object segmentation. Meanwhile, it exhibits lower computation complexity, enabling an efficient and reliable solution for clinical medical image analysis. The code will be made available soon.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12763
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DyGLNet: Hybrid Global-Local Feature Fusion with Dynamic Upsampling for Medical Image Segmentation
Zhao, Yican
Wang, Ce
Hao, You
Li, Lei
Liao, Tianli
Computer Vision and Pattern Recognition
Medical image segmentation grapples with challenges including multi-scale lesion variability, ill-defined tissue boundaries, and computationally intensive processing demands. This paper proposes the DyGLNet, which achieves efficient and accurate segmentation by fusing global and local features with a dynamic upsampling mechanism. The model innovatively designs a hybrid feature extraction module (SHDCBlock), combining single-head self-attention and multi-scale dilated convolutions to model local details and global context collaboratively. We further introduce a dynamic adaptive upsampling module (DyFusionUp) to realize high-fidelity reconstruction of feature maps based on learnable offsets. Then, a lightweight design is adopted to reduce computational overhead. Experiments on seven public datasets demonstrate that DyGLNet outperforms existing methods, particularly excelling in boundary accuracy and small-object segmentation. Meanwhile, it exhibits lower computation complexity, enabling an efficient and reliable solution for clinical medical image analysis. The code will be made available soon.
title DyGLNet: Hybrid Global-Local Feature Fusion with Dynamic Upsampling for Medical Image Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.12763