Identification of diabetic retinopathy in eye images using transfer learning
Authors:
- 1 May 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1183-1187
Abstract
Convolutional Neural Networks have been performing exceptionally well for the recognition of worldly objects and there are various trained models available which can give you the class of an object if an image of the object is fed as their input. But, we can also retrain an already trained model for anotherset of classes of our interest and we have retrained such a model to check the severity of Diabetic Retinopathy in eye images (data has been provided by eyePacs as color fundus images) on the scale of 0-5. A convolutional neural network classifier engineered from Inception V3 network (trained for ImageNet) for 5-class severity classification performed best with an accuracy of 48.2%.Keywords
This publication has 7 references indexed in Scilit:
- Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus PhotographsJAMA, 2016
- Rethinking the Inception Architecture for Computer Vision2016
- Going deeper with convolutions2015
- Algorithms for the Automated Detection of Diabetic Retinopathy Using Digital Fundus Images: A ReviewJournal of Medical Systems, 2010
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Screening for Diabetic Retinopathy: 1 and 3 Nonmydriatic 45-degree Digital Fundus Photographs vs 7 Standard Early Treatment Diabetic Retinopathy Study FieldsAmerican Journal of Ophthalmology, 2009
- A contribution of image processing to the diagnosis of diabetic retinopathy-detection of exudates in color fundus images of the human retinaIEEE Transactions on Medical Imaging, 2002