EUVIMEDEUVIMED entdecken
Crossref

Hard exudates segmentation for retinal fundus images based on longitudinal multi-scale fusion network

Shuang Liu, Xiangyu Jiang, Jie Zhang, Wei Zou

Medical & Biological Engineering & Computing · 2025-12 · 63 (12) · 3761-3775

DOI: 10.1007/s11517-025-03426-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, online erschienen am 13.08.2025. Verfasst von Shuang Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Information Engineering, Soochow University, Suzhou, 215006, China. Hauptthemen laut MEDLINE: Fundus Oculi, Exudates and Transudates, Retina, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: Suzhou Science and Technology Planning Project, Natural Science Foundation of Jiangsu Province, Specialized Research Fund for the Doctoral Program of Higher Education (SRFDP).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate segmentation of hard exudate in fundus images is crucial for early diagnosis of retinal diseases. However, hard exudate segmentation is still a challenge task for accurately detecting small lesions and precisely locating the boundaries of ambiguous lesions. In this paper, the longitudinal multi-scale fusion network (LMSF-Net) is proposed for accurate hard exudate segmentation in fundus images. In this network, an adjacent complementary correction module (ACCM) is proposed on the encoding path for complementary fusion between adjacent encoding features, and a progressive iterative fusion module (PIFM) is designed on the decoding path for fusion between adjacent decoding features. Furthermore, a spatial awareness fusion module (SAFM) is proposed at the end of the decoding path for calibration and aggregation of the two decoding outputs. The proposed method can improve segmentation results of hard exudates with different scales and shapes. The experimental results confirm the superiority of the proposed method for hard exudate segmentation with AUPR of 0.6954, 0.9017, and 0.6745 on the DDR, IDRID, and E-Ophtha EX datasets, respectively.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Fundus OculiExudates and TransudatesRetinaImage Processing, Computer-AssistedRetinal DiseasesImage Interpretation, Computer-AssistedHumansAlgorithmsNeural Networks, Computer

Stichwörter der Autor:innen

Decoding pathEncoding pathFeature fusionHard exudateLMSF-Net

Autor:innen und Institutionen

  • School of Electronic and Information Engineering, Soochow University, Suzhou, 215006, China.
  • School of Electronic and Information Engineering, Soochow University, Suzhou, 215006, China. zouwei@suda.edu.cn.

Förderung

  • Suzhou Science and Technology Planning Project
  • Natural Science Foundation of Jiangsu Province
  • Specialized Research Fund for the Doctoral Program of Higher Education (SRFDP)
  • Natural Science Foundation of the Jiangsu Higher Education Institutions of China

Zitieren

APA

Liu, S., Jiang, X., Zhang, J., & Zou, W. (2025). Hard exudates segmentation for retinal fundus images based on longitudinal multi-scale fusion network. Medical & Biological Engineering & Computing, 63(12), 3761-3775. https://doi.org/10.1007/s11517-025-03426-7

Vancouver

Liu S, Jiang X, Zhang J, Zou W. Hard exudates segmentation for retinal fundus images based on longitudinal multi-scale fusion network. Medical & Biological Engineering & Computing. 2025;63(12):3761-3775. doi:10.1007/s11517-025-03426-7

BibTeX
@article{Liu2025,
  author = {Liu, Shuang and Jiang, Xiangyu and Zhang, Jie and Zou, Wei},
  title = {Hard exudates segmentation for retinal fundus images based on longitudinal multi-scale fusion network},
  journal = {Medical & Biological Engineering & Computing},
  year = {2025},
  volume = {63},
  number = {12},
  pages = {3761--3775},
  doi = {10.1007/s11517-025-03426-7}
}
Kostenlos starten →