青岛大学学报（自然科学版）2026，Vol.39Issue(2)：14-22,9.DOI:10.3969/j.issn.1006-1037.2026.02.03
基于Swin Transformer与注意力机制的腺样体图像分割模型
Adenoid Image Segmentation Model Based on Swin Transformer and Attention Mechanism
王恒澳 1王琨 1刁瑞新 1计晓斐1
作者信息
- 1. 青岛大学计算机科学技术学院,青岛 266071
- 折叠
摘要
Abstract
To address the specific challenges of adenoid regions,such as low contrast be-tween lesions and surrounding tissues,unclear edge textures,and occlusions caused by na-sal cavity obstructions,a U-shaped adenoid segmentation model was proposed based on Swin Transformer and self-attention mechanisms.The Swin Transformer was employed as the encoder to efficiently extract adenoid features.An attention-based feature fusion module was introduced to effectively integrate low-level detailed information and high-level semantic information.Additionally,a multi-level aggregation module was introduced to enhance feature complementarity through a cross-scale information fusion strategy.Ex-periments conducted on an internal adenoid dataset demonstrate that the proposed method achieves significant improvements in mIoU,mDice,Accuracy,Precision and Recall,vali-dating its effectiveness in improving adenoid segmentation performance.关键词
图像分割/腺样体图像/Swin Transformer/注意力机制/特征融合Key words
image segmentation/adenoid images/Swin Transformer/attention mecha-nism/feature fusion分类
信息技术与安全科学引用本文复制引用
王恒澳,王琨,刁瑞新,计晓斐..基于Swin Transformer与注意力机制的腺样体图像分割模型[J].青岛大学学报（自然科学版）,2026,39(2):14-22,9.
