Analysis of Large-Scale Diabetic Retinopathy Datasets Using Texture and Blood Vessel Features

Devvi Sarwinda, Ari Wibisono, Hanifa Arrumaisha, Zaki Raihan, Rosa N. Rizky FT, Rico Putra Pradana, Mohammad Aulia Hafidh, Petrus Mursanto

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review


Diabetic retinopathy is a disease caused by the complications of diabetes mellitus and can cause blindness. In this study, we classified the stages of diabetic retinopathy using a large-scale dataset that consists of 35,126 fundus images. The classification of diabetic retinopathy includes five stages, from normal to proliferative diabetic retinopathy. In the proposed approach, a morphological feature extraction method and advanced local binary patterns were employed to extract blood vessel and texture features, respectively. The support vector machine, K-nearest neighbor, random forest, and logistic regression techniques were compared as classifiers. The classification was conducted on fundus images from a Kaggle dataset. The experimental results show that the texture feature extraction method based on advanced local binary patterns leads to higher accuracy, precision, and recall score than the blood vessel features extracted using morphological operators.

Original languageEnglish
Title of host publicationStudies in Computational Intelligence
PublisherSpringer Verlag
Number of pages15
Publication statusPublished - 1 Jan 2020

Publication series

NameStudies in Computational Intelligence
ISSN (Print)1860-949X
ISSN (Electronic)1860-9503


  • Blood vessel
  • Diabetic retinopathy
  • Fundus images
  • Large scale dataset
  • Texture feature


Dive into the research topics of 'Analysis of Large-Scale Diabetic Retinopathy Datasets Using Texture and Blood Vessel Features'. Together they form a unique fingerprint.

Cite this