EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hypermixed Convolutional Neural Network for Retinal Vein Occlusion Classification

Guanghua Zhang iD, Bin Sun iD, Zhaoxia Zhang iD, Shiyu Wu iD, Guangping Zhuo iD, Huifang Rong iD, Yunfang Liu iD, Weihua Yang iD

Disease Markers · 11.11.2022 · 2022 · 1-9

DOI: 10.1155/2022/1730501 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Disease Markers, erschienen am 11.11.2022. Verfasst von Guanghua Zhang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Intelligence and Automation, Taiyuan University, Taiyuan 030000, China. Hauptthemen laut MEDLINE: Retinal Vein Occlusion. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Planning Project of Shenzhen Municipality, Sanming Project of Medicine in Shenzhen, Shenzhen Fund for Guangdong Provincial High-level Clinical Key Specialties.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Retinal vein occlusion (RVO) is one of the most common retinal vascular diseases leading to vision loss if not diagnosed and treated in time. RVO can be classified into two types: CRVO (blockage of the main retinal veins) and BRVO (blockage of one of the smaller branch veins). Automated diagnosis of RVO can improve clinical workflow and optimize treatment strategies. However, to the best of our knowledge, there are few reported methods for automated identification of different RVO types. In this study, we propose a new hypermixed convolutional neural network (CNN) model, namely, the VGG-CAM network, that can classify the two types of RVOs based on retinal fundus images and detect lesion areas using an unsupervised learning method. The image data used in this study is collected and labeled by three senior ophthalmologists in Shanxi Eye Hospital, China. The proposed network is validated to accurately classify RVO diseases and detect lesions. It can potentially assist in further investigating the association between RVO and brain vascular diseases and evaluating the optimal treatments for RVO.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Retinal Vein OcclusionHumansRisk FactorsNeural Networks, ComputerChina

Autor:innen und Institutionen

  • Department of Intelligence and Automation, Taiyuan University, Taiyuan 030000, China.
  • Graphics and Imaging Laboratory, University of Girona, Spain.
  • Shanxi Eye Hospital, Taiyuan 030002, China.
  • Department of Computer, Taiyuan Normal University, Jinzhong 030619, China.
  • The First Affiliated Hospital of Huzhou University, Huzhou 313000, China.
  • Shenzhen Eye Hospital, Jinan University, Shenzhen 518040, China.

ORCID-Profile: Guanghua Zhang, Bin Sun, Zhaoxia Zhang, Shiyu Wu, Guangping Zhuo, Huifang Rong, Yunfang Liu, Weihua Yang

Förderung

  • Science and Technology Planning Project of Shenzhen Municipality
  • Sanming Project of Medicine in Shenzhen
  • Shenzhen Fund for Guangdong Provincial High-level Clinical Key Specialties
  • Shanxi Scholarship Council of China
  • Innovation and Entrepreneurship Training Program for College Students
  • Scientific Innovation Plan of Universities in Shanxi Province
  • Shanxi Provincial Key Research and Development Project
  • Fund for Shanxi “1331 Project”

Zitieren

APA

Zhang, G., Sun, B., Zhang, Z., Wu, S., Zhuo, G., Rong, H., Liu, Y., & Yang, W. (2022). Hypermixed Convolutional Neural Network for Retinal Vein Occlusion Classification. Disease Markers, 2022, 1-9. https://doi.org/10.1155/2022/1730501

Vancouver

Zhang G, Sun B, Zhang Z, Wu S, Zhuo G, Rong H, et al. Hypermixed Convolutional Neural Network for Retinal Vein Occlusion Classification. Disease Markers. 2022;2022:1-9. doi:10.1155/2022/1730501

BibTeX
@article{Zhang2022,
  author = {Zhang, Guanghua and Sun, Bin and Zhang, Zhaoxia and Wu, Shiyu and Zhuo, Guangping and Rong, Huifang and Liu, Yunfang and Yang, Weihua},
  title = {Hypermixed Convolutional Neural Network for Retinal Vein Occlusion Classification},
  journal = {Disease Markers},
  year = {2022},
  volume = {2022},
  pages = {1--9},
  doi = {10.1155/2022/1730501}
}
Kostenlos starten →