Introducing a Novel Layer in Convolutional Neural Network for Automatic Identification of Diabetic Retinopathy

Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul:2018:5938-5941. doi: 10.1109/EMBC.2018.8513606.


Convolutional neural networks have been widely used for identifying diabetic retinopathy on color fundus images. For such application, we proposed a novel framework for the convolutional neural network architecture by embedding a preprocessing layer followed by the first convolutional layer to increase the performance of the convolutional neural network classifier. Two image enhancement techniques i.e. 1- Contrast Enhancement 2- Contrast-limited adaptive histogram equalization were separately embedded in the proposed layer and the results were compared. For identification of exudates, hemorrhages and microaneurysms, the proposed framework achieved the total accuracy of 87.6%, and 83.9% for the contrast enhancement and contrast-limited adaptive histogram equalization layers, respectively. However, the total accuracy of the convolutional neural network alone without the prreprocessing layer was found to be 81.4%. Consequently, the new convolutional neural network architecture with the proposed preprocessing layer improved the performance of convolutional neural network.

MeSH terms

  • Algorithms
  • Diabetic Retinopathy / diagnosis*
  • Exudates and Transudates
  • Fundus Oculi
  • Hemorrhage
  • Humans
  • Image Enhancement*
  • Microaneurysm
  • Neural Networks, Computer*