EUVIMEDEUVIMED entdecken
Crossref

AMPPNet : A Lightweight 3D Medical Image Segmentation Network With Dual‐Bond Efficient Hybrid Attention Mechanism

Xiangru Wang, Chuanzhi Zang, Zhijia Zhang, Xinxin Wang, Yetian Tian, Xiaoming Han

International Journal of Imaging Systems and Technology · 2026-11 · 36 (6)

DOI: 10.1002/ima.70457 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Imaging Systems and Technology, online erschienen am 28.10.2026. Verfasst von Xiangru Wang und 5 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent medical image segmentation networks, such as SwinUNet and AttentionUNet, achieve high accuracy through complex architectures containing hundreds of millions of parameters. However, due to expensive annotation and limited data (e.g., the MSD‐Pancreas dataset contains only 281 samples), these models often suffer from overfitting and poor generalization. To address these challenges, we propose a lightweight 3D medical image segmentation network, AMPPNet, with only 1.97 M parameters and three major innovations: the Adaptive Multi‐stage Polarization Perception (AMPP) module, which integrates two key submodules: dual‐bond efficient polarization multi‐scale channel self‐attention (DPMC) and dual‐bond multi‐scale polarization hybrid spatial attention (MSPHA). The DPMC module achieves cross‐layer channel semantic alignment and local–global polarization fusion through a dual‐bond design, while the MSPHA module captures multi‐scale spatial dependencies by jointly attending to local texture details and global structural cues. These modules, combined with the Adaptive Multi‐stage Feature Fusion (AMFF) mechanism, enable hierarchical semantic aggregation with minimal computational overhead. The Pyramid Adaptive Matrix Multi‐Level Loss (PAMMLoss) dynamically combines Dice, cross‐entropy, and Tversky losses at shallow, mid, and deep layers with learnable adaptive weights, enabling fine‐grained optimization and mitigating gradient conflicts. AMPPNet is highly parameter‐efficient and accurate—despite its compact design, it achieves excellent Dice scores of 81.17% (NIH), MSD (10 datasets) of 72.71%, demonstrating its strong generalization capabilities under data‐scarce conditions. Our code is publicly available: https://github.com/XiangruW/AMPPNet .

Zitieren

APA

Wang, X., Zang, C., Zhang, Z., Wang, X., Tian, Y., & Han, X. (2026). AMPPNet : A Lightweight 3D Medical Image Segmentation Network With Dual‐Bond Efficient Hybrid Attention Mechanism. International Journal of Imaging Systems and Technology, 36(6). https://doi.org/10.1002/ima.70457

Vancouver

Wang X, Zang C, Zhang Z, Wang X, Tian Y, Han X. AMPPNet : A Lightweight 3D Medical Image Segmentation Network With Dual‐Bond Efficient Hybrid Attention Mechanism. International Journal of Imaging Systems and Technology. 2026;36(6). doi:10.1002/ima.70457

BibTeX
@article{Wang2026,
  author = {Wang, Xiangru and Zang, Chuanzhi and Zhang, Zhijia and Wang, Xinxin and Tian, Yetian and Han, Xiaoming},
  title = {AMPPNet : A Lightweight 3D Medical Image Segmentation Network With Dual‐Bond Efficient Hybrid Attention Mechanism},
  journal = {International Journal of Imaging Systems and Technology},
  year = {2026},
  volume = {36},
  number = {6},
  doi = {10.1002/ima.70457}
}
Kostenlos starten →