EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Novel Convolutional Neural Network for Explainable Diabetic Retinopathy Detection and Grade Identification

Simona Correra, Valeria Sorgente, Mario Cesarelli, Fabio Martinelli, Antonella Santone, Francesco Mercaldo iD

Sensors · 18.04.2026 · 26 (8) · 2510

DOI: 10.3390/s26082510 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.04.2026. Verfasst von Simona Correra und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine and Health Sciences "Vincenzo Tiberio", University of Molise, 86100 Campobasso, Italy. Hauptthemen laut MEDLINE: Diabetic Retinopathy. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetic retinopathy represents one of the leading causes of blindness worldwide, making early diagnosis essential for effective clinical intervention. We propose an explainable method aimed at automatically identifying the severity levels of diabetic retinopathy in retinal images using deep learning. The proposed method considers several convolutional neural network architectures, i.e., VGG16, StandardCNN, ResNet, CustomCNN, EfficientNet, MobileNet, and a novel architecture, i.e., FGNet, specifically designed and developed by the authors for diabetic retinopathy detection. The proposed network achieves an accuracy of 0.75 when trained for 10 epochs and 0.71 for 20 epochs. Explainability behind model prediction is further supported through Gradient-weighted Class Activation Mapping, providing visual insight into the learned decision-making process and potentially supporting early clinical assessment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diabetic RetinopathyConvolutional Neural NetworksHumansDeep LearningAlgorithmsNeural Networks, ComputerImage Processing, Computer-Assisted

Stichwörter der Autor:innen

artificial intelligenceclassificationconvolutional neural networkdeep learningdiabetic retinopathy

Autor:innen und Institutionen

  • Department of Medicine and Health Sciences "Vincenzo Tiberio", University of Molise, 86100 Campobasso, Italy.
  • Department of Engineering, University of Sannio, 82100 Benevento, Italy.
  • Institute for High Performance Computing and Networking, National Research Council of Italy (CNR), 87036 Rende, Italy.

ORCID-Profile: Francesco Mercaldo

Zitieren

APA

Correra, S., Sorgente, V., Cesarelli, M., Martinelli, F., Santone, A., & Mercaldo, F. (2026). A Novel Convolutional Neural Network for Explainable Diabetic Retinopathy Detection and Grade Identification. Sensors, 26(8), 2510. https://doi.org/10.3390/s26082510

Vancouver

Correra S, Sorgente V, Cesarelli M, Martinelli F, Santone A, Mercaldo F. A Novel Convolutional Neural Network for Explainable Diabetic Retinopathy Detection and Grade Identification. Sensors. 2026;26(8):2510. doi:10.3390/s26082510

BibTeX
@article{Correra2026,
  author = {Correra, Simona and Sorgente, Valeria and Cesarelli, Mario and Martinelli, Fabio and Santone, Antonella and Mercaldo, Francesco},
  title = {A Novel Convolutional Neural Network for Explainable Diabetic Retinopathy Detection and Grade Identification},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {8},
  pages = {2510},
  doi = {10.3390/s26082510}
}
Kostenlos starten →