EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cross-spatial attention guided multi-scale fusion network for precise microaneurysm segmentation

Zuxiang Wang, Weiwei Gao iD, Yu Fang, Nan Song, Feng Xiao

Biomedical Engineering / Biomedizinische Technik · 05.11.2026

DOI: 10.1515/bmt-2025-0495 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Engineering / Biomedizinische Technik, online erschienen am 05.11.2026. Verfasst von Zuxiang Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai, China. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, scientific research plan with AI enabling of Shanghai Municipal Education Commission.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Accurate detection of Microaneurysms (MAs) is crucial for the early diagnosis of diabetic retinopathy (DR). However, due to their small size and low contrast with the background, precisely segmenting them from the background poses significant challenges.

Methods

The Cross-Spatial Attention Embedded Multi-Scale Fusion Network (CSAFNet) is proposed to enhance the segmentation accuracy of MAs in fundus images. Based on the U-Net architecture, an improved ResNet50 is used as the backbone for feature extraction. An Efficient Multi-scale Attention (EMA) module is embedded to capture key features across different spatial locations and scales. Simultaneously, a Multi-Scale Deep Fusion (MSDF) module is designed to integrate contextual features from multiple scales. Additionally, the proposed Balanced Focusing Boundary (BFB) loss function improves segmentation by enhancing geometric accuracy at object boundaries.

Results

The method is evaluated on four datasets (E-ophtha, TongjiU-DROD, IDRiD, Messidor) with various advanced methods. On IDRiD, its F1-score and IoU improved by 6.16 and 5.63 % respectively, compared to the state-of-the-art (SOTA). On the Messidor and TongjiU-DROD datasets, it demonstrated comprehensive superiority in sensitivity, specificity, F1-score, and IoU.

Conclusions

The proposed CSAFNet can accurately extract MAs from fundus images, thereby effectively assisting in the precise diagnosis of DR.

Schlagwörter

Stichwörter der Autor:innen

deep feature fusiondiabetic retinopathymicroaneurysmsmulti-scale attention

Autor:innen und Institutionen

  • School of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai, China.
  • Department of Ophthalmology, The Eye and ENT Hospital of Fudan University, Shanghai, China.
  • Department of Ophthalmology, The First Affiliated Hospital of Soochow University, Suzhou, China.

ORCID-Profile: Weiwei Gao

Förderung

  • National Natural Science Foundation of China
  • scientific research plan with AI enabling of Shanghai Municipal Education Commission

Zitieren

APA

Wang, Z., Gao, W., Fang, Y., Song, N., & Xiao, F. (2026). Cross-spatial attention guided multi-scale fusion network for precise microaneurysm segmentation. Biomedical Engineering / Biomedizinische Technik. https://doi.org/10.1515/bmt-2025-0495

Vancouver

Wang Z, Gao W, Fang Y, Song N, Xiao F. Cross-spatial attention guided multi-scale fusion network for precise microaneurysm segmentation. Biomedical Engineering / Biomedizinische Technik. 2026. doi:10.1515/bmt-2025-0495

BibTeX
@article{Wang2026,
  author = {Wang, Zuxiang and Gao, Weiwei and Fang, Yu and Song, Nan and Xiao, Feng},
  title = {Cross-spatial attention guided multi-scale fusion network for precise microaneurysm segmentation},
  journal = {Biomedical Engineering / Biomedizinische Technik},
  year = {2026},
  doi = {10.1515/bmt-2025-0495}
}
Kostenlos starten →