eduzhai > Applied Sciences > Engineering >

Diabetic Retinopathy Diagnosis based on Convolutional Neural Network

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 8 pages

Abstract: Diabetic Retinopathy DR is a popular disease for many people as a result ofage or the diabetic, as a result, it can cause blindness. therefore, diagnosisof this disease especially in the early time can prevent its effect for a lotof patients. To achieve this diagnosis, eye retina must be examinedcontinuously. Therefore, computer-aided tools can be used in the field based oncomputer vision techniques. Different works have been performed using variousmachine learning techniques. Convolutional Neural Network is one of the promisemethods, so it was for Diabetic Retinopathy detection in this paper. Also, theproposed work contains visual enhancement in the pre-processing phase, then theCNN model is trained to be able for recognition and classification phase, todiagnosis the healthy and unhealthy retina image. Three public datasetDiaretDB0, DiaretDB1 and DrimDB were used in practical testing. Theimplementation of this work based on Matlab- R2019a, deep learning toolbox anddeep network designer to design the architecture of the convolutional neuralnetwork and train it. The results were evaluated to different metrics; accuracyis one of them. The best accuracy that was achieved: for DiaretDB0 is 100 ,DiaretDB1 is 99.495 and DrimDB is 97.55 .

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×