Rxivist logo

Diabetic Retinopathy detection through integration of Deep Learning classification framework

By Alexander Rakhlin

Posted 27 Nov 2017
bioRxiv DOI: 10.1101/225508

This document represents a brief account of ongoing project for Diabetic Retinopathy Detection (DRD) through integration of state-of the art Deep Learning methods. We make use of deep Convolutional Neural Networks (CNNs), which have proven revolutionary in multiple fields of computer vision including medical imaging, and we bring their power to the diagnosis of eye fundus images. For training our models we used publicly available Kaggle data set. For testing we used portion of Kaggle data withheld from training and Messidor-2 reference standard. Neither withheld Kaggle images, nor Messidor-2 were used for training. For Messidor-2 we achieved sensitivity 99%, specificity 71%, and AUC 0.97. These results close to recent state-of-the-art models trained on much larger data sets and surpass average results of diabetic retinopathy screening when performed by trained optometrists. With continuous development of our Deep Learning models we expect to further increase the accuracy of the method and expand it to cataract and glaucoma diagnostics.

Download data

  • Downloaded 5,539 times
  • Download rankings, all-time:
    • Site-wide: 1,389 out of 119,198
    • In pathology: 11 out of 700
  • Year to date:
    • Site-wide: 3,922 out of 119,198
  • Since beginning of last month:
    • Site-wide: 4,596 out of 119,198

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide


Sign up for the Rxivist weekly newsletter! (Click here for more details.)