EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Performance of ResNet‐18 and InceptionResNetV2 in Automated Detection of Diabetic Retinopathy

Akwasi Asare, Alvin Adjei Broni, Alex Kwasi Asare Dickson, Mary Sagoe, Joshua Makafui Cudjoe

Medicine Advances · 2025-09 · 3 (3) · 231-241

DOI: 10.1002/med4.70023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medicine Advances, online erschienen am 15.07.2025. Verfasst von Akwasi Asare und 4 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Diabetic retinopathy (DR) is a leading cause of blindness worldwide, particularly in diabetic individuals. Manual detection of DR by ophthalmologists is time‐consuming and resource‐intensive, making early automated detection essential for mitigating the risk of vision impairment. This study evaluates the effectiveness of two deep learning models, ResNet‐18 and InceptionResNetV2, for detecting and classifying DR from retinal fundus images, with the aim of identifying the most suitable model for clinical application.

Methods

A dataset of 3662 retinal fundus images, divided into five DR severity classes, was used to train and test ResNet‐18 and InceptionResNetV2. The key performance metrics used to assess classification across the DR stages included testing accuracy, precision, recall, specificity, F 1 score, and area under the curve (AUC).

Results

ResNet‐18 achieved a testing accuracy of 83% and an AUC of 0.946, showing robust generalization across DR stages. InceptionResNetV2 achieved a testing accuracy of 70.4% and an AUC of 0.9305, with high precision in distinguishing “No DR” cases. However, it exhibited overfitting, particularly in “Mild” and “Proliferative DR” classifications, whereas ResNet‐18 demonstrated a more stable performance across categories.

Conclusions

Our results suggest that ResNet‐18 holds significant potential as an automated DR detection tool, providing reliable classification and superior generalization across DR stages. Integrating deep learning models such as ResNet‐18 into clinical workflows may enhance early DR diagnosis and timely intervention, reducing the risk of vision impairment among patients with diabetes.

Zitieren

APA

Asare, A., Broni, A. A., Dickson, A. K. A., Sagoe, M., & Cudjoe, J. M. (2025). Performance of ResNet‐18 and InceptionResNetV2 in Automated Detection of Diabetic Retinopathy. Medicine Advances, 3(3), 231-241. https://doi.org/10.1002/med4.70023

Vancouver

Asare A, Broni AA, Dickson AKA, Sagoe M, Cudjoe JM. Performance of ResNet‐18 and InceptionResNetV2 in Automated Detection of Diabetic Retinopathy. Medicine Advances. 2025;3(3):231-241. doi:10.1002/med4.70023

BibTeX
@article{Asare2025,
  author = {Asare, Akwasi and Broni, Alvin Adjei and Dickson, Alex Kwasi Asare and Sagoe, Mary and Cudjoe, Joshua Makafui},
  title = {Performance of ResNet‐18 and InceptionResNetV2 in Automated Detection of Diabetic Retinopathy},
  journal = {Medicine Advances},
  year = {2025},
  volume = {3},
  number = {3},
  pages = {231--241},
  doi = {10.1002/med4.70023}
}
Kostenlos starten →