Exploiting the Generative Adversarial Network Approach to Create a Synthetic Topography Corneal Image

Corneal diseases are the most common eye disorders. Deep learning techniques are used to perform automated diagnoses of cornea. Deep learning networks require large-scale annotated datasets, which is conceded as a weakness of deep learning. In this work, a method for synthesizing medical images usin...

Full description

Bibliographic Details
Main Authors: Samer Kais, Jameel, Sezgin, Aydin, Nebras H., Ghaeb, Jafar, Majidpour, Tarik A., Rashid, Sinan Q., Salih, Ng, Joseph, Poh Soon
Format: Article
Published: Molecular Diversity Preservation International (MDPI) 2022
Subjects:
Online Access:http://eprints.intimal.edu.my/1700/
_version_ 1848766810358284288
author Samer Kais, Jameel
Sezgin, Aydin
Nebras H., Ghaeb
Jafar, Majidpour
Tarik A., Rashid
Sinan Q., Salih
Ng, Joseph, Poh Soon
author_facet Samer Kais, Jameel
Sezgin, Aydin
Nebras H., Ghaeb
Jafar, Majidpour
Tarik A., Rashid
Sinan Q., Salih
Ng, Joseph, Poh Soon
author_sort Samer Kais, Jameel
building INTI Institutional Repository
collection Online Access
description Corneal diseases are the most common eye disorders. Deep learning techniques are used to perform automated diagnoses of cornea. Deep learning networks require large-scale annotated datasets, which is conceded as a weakness of deep learning. In this work, a method for synthesizing medical images using conditional generative adversarial networks (CGANs), is presented. It also illustrates how produced medical images may be utilized to enrich medical data, improve clinical decisions, and boost the performance of the conventional neural network (CNN) for medical image diagnosis. The study includes using corneal topography captured using a Pentacam device from patients with corneal diseases. The dataset contained 3448 different corneal images. Furthermore, it shows how an unbalanced dataset affects the performance of classifiers, where the data are balanced using the resampling approach. Finally, the results obtained from CNN networks trained on the balanced dataset are compared to those obtained from CNN networks trained on the imbalanced dataset. For performance, the system estimated the diagnosis accuracy, precision, and F1-score metrics. Lastly, some generated images were shown to an expert for evaluation and to see how well experts could identify the type of image and its condition. The expert recognized the image as useful for medical diagnosis and for determining the severity class according to the shape and values, by generating images based on real cases that could be used as new different stages of illness between healthy and unhealthy patients.
first_indexed 2025-11-14T11:57:04Z
format Article
id intimal-1700
institution INTI International University
institution_category Local University
last_indexed 2025-11-14T11:57:04Z
publishDate 2022
publisher Molecular Diversity Preservation International (MDPI)
recordtype eprints
repository_type Digital Repository
spelling intimal-17002022-12-29T03:06:19Z http://eprints.intimal.edu.my/1700/ Exploiting the Generative Adversarial Network Approach to Create a Synthetic Topography Corneal Image Samer Kais, Jameel Sezgin, Aydin Nebras H., Ghaeb Jafar, Majidpour Tarik A., Rashid Sinan Q., Salih Ng, Joseph, Poh Soon R Medicine (General) RA Public aspects of medicine RE Ophthalmology Corneal diseases are the most common eye disorders. Deep learning techniques are used to perform automated diagnoses of cornea. Deep learning networks require large-scale annotated datasets, which is conceded as a weakness of deep learning. In this work, a method for synthesizing medical images using conditional generative adversarial networks (CGANs), is presented. It also illustrates how produced medical images may be utilized to enrich medical data, improve clinical decisions, and boost the performance of the conventional neural network (CNN) for medical image diagnosis. The study includes using corneal topography captured using a Pentacam device from patients with corneal diseases. The dataset contained 3448 different corneal images. Furthermore, it shows how an unbalanced dataset affects the performance of classifiers, where the data are balanced using the resampling approach. Finally, the results obtained from CNN networks trained on the balanced dataset are compared to those obtained from CNN networks trained on the imbalanced dataset. For performance, the system estimated the diagnosis accuracy, precision, and F1-score metrics. Lastly, some generated images were shown to an expert for evaluation and to see how well experts could identify the type of image and its condition. The expert recognized the image as useful for medical diagnosis and for determining the severity class according to the shape and values, by generating images based on real cases that could be used as new different stages of illness between healthy and unhealthy patients. Molecular Diversity Preservation International (MDPI) 2022-12 Article PeerReviewed Samer Kais, Jameel and Sezgin, Aydin and Nebras H., Ghaeb and Jafar, Majidpour and Tarik A., Rashid and Sinan Q., Salih and Ng, Joseph, Poh Soon (2022) Exploiting the Generative Adversarial Network Approach to Create a Synthetic Topography Corneal Image. Biomolecules, 12 (12). ISSN 2218-273X https://doi.org/10.3390/biom12121888
spellingShingle R Medicine (General)
RA Public aspects of medicine
RE Ophthalmology
Samer Kais, Jameel
Sezgin, Aydin
Nebras H., Ghaeb
Jafar, Majidpour
Tarik A., Rashid
Sinan Q., Salih
Ng, Joseph, Poh Soon
Exploiting the Generative Adversarial Network Approach to Create a Synthetic Topography Corneal Image
title Exploiting the Generative Adversarial Network Approach to Create a Synthetic Topography Corneal Image
title_full Exploiting the Generative Adversarial Network Approach to Create a Synthetic Topography Corneal Image
title_fullStr Exploiting the Generative Adversarial Network Approach to Create a Synthetic Topography Corneal Image
title_full_unstemmed Exploiting the Generative Adversarial Network Approach to Create a Synthetic Topography Corneal Image
title_short Exploiting the Generative Adversarial Network Approach to Create a Synthetic Topography Corneal Image
title_sort exploiting the generative adversarial network approach to create a synthetic topography corneal image
topic R Medicine (General)
RA Public aspects of medicine
RE Ophthalmology
url http://eprints.intimal.edu.my/1700/
http://eprints.intimal.edu.my/1700/