Classification system from Optical Coherence Tomography using transfer learning

This research aims to create a decision support system to identify retinal diseases using a four-class classification problem. To achieve this, the proposed system uses deep learning architecture to automatically recognize CNV, DME, and drusen from OCT images. The model employs two transfer learning...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhamad Asvial, Tobias Ivandito Margogo Silalahi, Muh. Asnoer Laagu
Format: Article
Language:English
Published: Polish Academy of Sciences 2024-11-01
Series:International Journal of Electronics and Telecommunications
Subjects:
Online Access:https://journals.pan.pl/Content/133212/PDF/12-4722-Asvial-sk.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846150843183661056
author Muhamad Asvial
Tobias Ivandito Margogo Silalahi
Muh. Asnoer Laagu
author_facet Muhamad Asvial
Tobias Ivandito Margogo Silalahi
Muh. Asnoer Laagu
author_sort Muhamad Asvial
collection DOAJ
description This research aims to create a decision support system to identify retinal diseases using a four-class classification problem. To achieve this, the proposed system uses deep learning architecture to automatically recognize CNV, DME, and drusen from OCT images. The model employs two transfer learning architectures with several additional layers to classify retinal diseases. The purpose of model training, validation, and testing, the experiment uses 6,000 grayscale images labeled into four classes from the OCT data set. The Inception V3 model’s proposed additional layer exhibits an increase in accuracy of 3.08% and a reduction in the loss by 0.3767. The experiment’s results indicate that the Inception V3 model achieved an accuracy rate of 99.31%, and the VGG-16 model reached 98.83%, which outperformed other deep learning models using the OCT data set.
format Article
id doaj-art-9edecd260f9a401cbc0a61d9ed0c8f66
institution Kabale University
issn 2081-8491
2300-1933
language English
publishDate 2024-11-01
publisher Polish Academy of Sciences
record_format Article
series International Journal of Electronics and Telecommunications
spelling doaj-art-9edecd260f9a401cbc0a61d9ed0c8f662024-11-28T08:41:30ZengPolish Academy of SciencesInternational Journal of Electronics and Telecommunications2081-84912300-19332024-11-01vol. 70No 4871877https://doi.org/10.24425/ijet.2024.152072Classification system from Optical Coherence Tomography using transfer learningMuhamad Asvial0Tobias Ivandito Margogo Silalahi1Muh. Asnoer Laagu2University of IndonesiaUniversity of IndonesiaUniversity of JemberThis research aims to create a decision support system to identify retinal diseases using a four-class classification problem. To achieve this, the proposed system uses deep learning architecture to automatically recognize CNV, DME, and drusen from OCT images. The model employs two transfer learning architectures with several additional layers to classify retinal diseases. The purpose of model training, validation, and testing, the experiment uses 6,000 grayscale images labeled into four classes from the OCT data set. The Inception V3 model’s proposed additional layer exhibits an increase in accuracy of 3.08% and a reduction in the loss by 0.3767. The experiment’s results indicate that the Inception V3 model achieved an accuracy rate of 99.31%, and the VGG-16 model reached 98.83%, which outperformed other deep learning models using the OCT data set.https://journals.pan.pl/Content/133212/PDF/12-4722-Asvial-sk.pdfdeep learningtransfer learningoptical coherence tomographyinception v3vgg-16
spellingShingle Muhamad Asvial
Tobias Ivandito Margogo Silalahi
Muh. Asnoer Laagu
Classification system from Optical Coherence Tomography using transfer learning
International Journal of Electronics and Telecommunications
deep learning
transfer learning
optical coherence tomography
inception v3
vgg-16
title Classification system from Optical Coherence Tomography using transfer learning
title_full Classification system from Optical Coherence Tomography using transfer learning
title_fullStr Classification system from Optical Coherence Tomography using transfer learning
title_full_unstemmed Classification system from Optical Coherence Tomography using transfer learning
title_short Classification system from Optical Coherence Tomography using transfer learning
title_sort classification system from optical coherence tomography using transfer learning
topic deep learning
transfer learning
optical coherence tomography
inception v3
vgg-16
url https://journals.pan.pl/Content/133212/PDF/12-4722-Asvial-sk.pdf
work_keys_str_mv AT muhamadasvial classificationsystemfromopticalcoherencetomographyusingtransferlearning
AT tobiasivanditomargogosilalahi classificationsystemfromopticalcoherencetomographyusingtransferlearning
AT muhasnoerlaagu classificationsystemfromopticalcoherencetomographyusingtransferlearning