Retina Screening Condition Using CNN

  • Unique Paper ID: 164027
  • Volume: 10
  • Issue: 12
  • PageNo: 1033-1038
  • Abstract:
  • Retinopathy arises from poorly managed chronic diabetes and, if left untreated, can lead to complete vision loss. Thus, early detection and treatment are vital to mitigate its serious consequences. Manual diagnosis by eye specialists is time-intensive and burdensome for patients. An automated system offers a faster detection method, facilitating prompt treatment and reducing ocular complications. This research proposes a ML technique to extract features such as exudates, hemorrhages, and capillary aneurysms, utilizing a hybrid classifier comprising support vector machine, Logistic regression, random forest, and k-nearest neighbour multilayer perceptron network. The experiments resulted in an accuracy rate of 82%, with a precision score of 0.8120, a recall score of 0.8115 approximately, and an f-measure score of 0.8028 for the hybrid approach.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 10
  • Issue: 12
  • PageNo: 1033-1038

Retina Screening Condition Using CNN

Related Articles