TY - JOUR
T1 - Restricted Boltzmann Machines for Fundus Image Reconstruction and Classification of Hypertension Retinopathy
AU - Triwijoyo, Bambang Krismono
AU - Sabarguna, Boy Subirosa
AU - Budiharto, Widodo
AU - Abdurachman, Edi
N1 - Funding Information:
The author would like to thank the availability of the MESSIDOR dataset used in this study. This research study was supported by Bumigora University, Indonesia.
Funding Information:
We used database Methods to Evaluate Segmentation and Indexing Techniques in the Field of Retinal Ophthalmology (MESSIDOR) as a dataset (Messidor, 2010). Messidor is a research program funded by the French Ministry of Research and Defense within a 2004 TECHNO-VISION program. This database can be used, free of charge, only for research and educational purposes. Messidor database consists of 1200 eye fundus color digital images of the posterior pole, which were acquired by three ophthalmologic departments, using a color video 3CCD camera on a Topcon TRC NW6 non-mydriatic retina graph with a 45 degrees field of view. Figure 1 shows an example of fundus images from the Messidor database.
Publisher Copyright:
© 2021 Bambang Krismono Triwijoyo, Boy Subirosa Sabarguna, Widodo Budiharto and Edi Abdurachman. This open access article is distributed under a Creative Commons Attribution (CC-BY) 4.0 license.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
KW - Classification
KW - Fundus Image
KW - Hypertensive Retinopathy
KW - Reconstruction
KW - Restricted Boltzmann Machines
UR - http://www.scopus.com/inward/record.url?scp=85103138857&partnerID=8YFLogxK
U2 - 10.3844/jcssp.2021.156.166
DO - 10.3844/jcssp.2021.156.166
M3 - Article
AN - SCOPUS:85103138857
SN - 1549-3636
VL - 17
SP - 156
EP - 166
JO - Journal of Computer Science
JF - Journal of Computer Science
IS - 2
ER -