Welcome to the InfoSci Platform
Multistage Transfer Learning for Stage Detection of Diabetic Retinopathy

Multistage Transfer Learning for Stage Detection of Diabetic Retinopathy

Varshini Venkatesan, Haripriya K., Mounika M., Angelin Gladston
Copyright: © 2022 |Volume: 13 |Issue: 1 |Pages: 24
ISSN: 1941-6237|EISSN: 1941-6245|EISBN13: 9781683180647|DOI: 10.4018/IJACI.304725
Cite Article Cite Article

MLA

Venkatesan, Varshini, et al. "Multistage Transfer Learning for Stage Detection of Diabetic Retinopathy." IJACI vol.13, no.1 2022: pp.1-24. http://doi.org/10.4018/IJACI.304725

APA

Venkatesan, V., K., H., M., M., & Gladston, A. (2022). Multistage Transfer Learning for Stage Detection of Diabetic Retinopathy. International Journal of Ambient Computing and Intelligence (IJACI), 13(1), 1-24. http://doi.org/10.4018/IJACI.304725

Chicago

Venkatesan, Varshini, et al. "Multistage Transfer Learning for Stage Detection of Diabetic Retinopathy," International Journal of Ambient Computing and Intelligence (IJACI) 13, no.1: 1-24. http://doi.org/10.4018/IJACI.304725

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Diabetic retinopathy is one of the most threatening complications of diabetes that leads to permanent blindness if left untreated. Severity of the diabetic retinopathy disease is based on presence of microaneurysms, exudates, neovascularisation and haemorrhages. Convolutional neural networks have been successfully applied in many adjacent subjects, and for diagnosis of diabetic retinopathy itself. In this paper, an automatic deep-learning-based method for stage detection of diabetic retinopathy by single photography of the human fundus is proposed. Additionally, the multistage approach to transfer learning, which makes use of similar datasets with different labelling, is experimented. The proposed architecture gives high accuracy in classification through spatial analysis. Amongst other supervised algorithms involved, proposed solution is to find a better and optimized way to classifying the fundus image with little pre-processing techniques. The proposed architecture deployed with dropout layer techniques yields 78 percent accuracy.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.