EUVIMEDEUVIMED entdecken
Übersichtsarbeit

Multi-step framework for glaucoma diagnosis in retinal fundus images using deep learning

Sanli Yi, Lingxiang Zhou

Medical & Biological Engineering & Computing · 2025-01 · 63 (1) · 1-13

DOI: 10.1007/s11517-024-03172-2 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Medical & Biological Engineering & Computing, online erschienen am 05.08.2024. Verfasst von Sanli Yi und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, 650500, China. 152514845@qq.com. Hauptthemen laut MEDLINE: Deep Learning, Glaucoma, Fundus Oculi. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Glaucoma is one of the most common causes of blindness in the world. Screening glaucoma from retinal fundus images based on deep learning is a common method at present. In the diagnosis of glaucoma based on deep learning, the blood vessels within the optic disc interfere with the diagnosis, and there is also some pathological information outside the optic disc in fundus images. Therefore, integrating the original fundus image with the vessel-removed optic disc image can improve diagnostic efficiency. In this paper, we propose a novel multi-step framework named MSGC-CNN that can better diagnose glaucoma. In the framework, (1) we combine glaucoma pathological knowledge with deep learning model, fuse the features of original fundus image and optic disc region in which the interference of blood vessel is specifically removed by U-Net, and make glaucoma diagnosis based on the fused features. (2) Aiming at the characteristics of glaucoma fundus images, such as small amount of data, high resolution, and rich feature information, we design a new feature extraction network RA-ResNet and combined it with transfer learning. In order to verify our method, we conduct binary classification experiments on three public datasets, Drishti-GS, RIM-ONE-R3, and ACRIMA, with accuracy of 92.01%, 93.75%, and 97.87%. The results demonstrate a significant improvement over earlier results.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningGlaucomaFundus OculiHumansOptic DiskImage Interpretation, Computer-AssistedNeural Networks, ComputerImage Processing, Computer-AssistedAlgorithms

Stichwörter der Autor:innen

Fundus imageGlaucoma diagnosisMulti-stepRA-ResNetVessel elimination

Autor:innen und Institutionen

  • School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, 650500, China. 152514845@qq.com.
  • Key Laboratory of Computer Technology Application of Yunnan Province, Kunming, Yunnan, China. 152514845@qq.com.
  • School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, 650500, China.
  • Key Laboratory of Computer Technology Application of Yunnan Province, Kunming, Yunnan, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Yi, S., & Zhou, L. (2025). Multi-step framework for glaucoma diagnosis in retinal fundus images using deep learning. Medical & Biological Engineering & Computing, 63(1), 1-13. https://doi.org/10.1007/s11517-024-03172-2

Vancouver

Yi S, Zhou L. Multi-step framework for glaucoma diagnosis in retinal fundus images using deep learning. Medical & Biological Engineering & Computing. 2025;63(1):1-13. doi:10.1007/s11517-024-03172-2

BibTeX
@article{Yi2025,
  author = {Yi, Sanli and Zhou, Lingxiang},
  title = {Multi-step framework for glaucoma diagnosis in retinal fundus images using deep learning},
  journal = {Medical & Biological Engineering & Computing},
  year = {2025},
  volume = {63},
  number = {1},
  pages = {1--13},
  doi = {10.1007/s11517-024-03172-2}
}
Kostenlos starten →