Research Article Open Access

Restricted Boltzmann Machines for Fundus Image Reconstruction and Classification of Hypertension Retinopathy

Bambang Krismono Triwijoyo1, Boy Subirosa Sabarguna2, Widodo Budiharto1 and Edi Abdurachman1
  • 1 Binus Graduate Program University of Bina Nusantara, Indonesia
  • 2 University of Indonesia, Indonesia

Abstract

Conventionally classification of hypertensive retinopathy through analysis of fundus images by experts, but this method the results are highly dependent on the accuracy of observations and expert experience. In this study, we propose a fundus image reconstruction and Hypertensive retinopathy classification model using Restricted Boltzmann Machines (RBM), as well as the Messidor database that has been labeled as a dataset. The experimental results show that the performance of the model produces an accuracy level of 99.05% where the model can generalize image input into one of the nine classes of the severity of hypertension retinopathy.

Journal of Computer Science
Volume 17 No. 2, 2021, 156-166

DOI: https://doi.org/10.3844/jcssp.2021.156.166

Submitted On: 31 December 2020 Published On: 26 February 2021

How to Cite: Triwijoyo, B. K., Sabarguna, B. S., Budiharto, W. & Abdurachman, E. (2021). Restricted Boltzmann Machines for Fundus Image Reconstruction and Classification of Hypertension Retinopathy. Journal of Computer Science, 17(2), 156-166. https://doi.org/10.3844/jcssp.2021.156.166

  • 3,208 Views
  • 1,437 Downloads
  • 0 Citations

Download

Keywords

  • Restricted Boltzmann Machines
  • Fundus Image
  • Reconstruction
  • Classification
  • Hypertensive Retinopathy