IIUM Repository

Utlizing sgans for generating synthetic images of pterygium: training future optometrists and ophthalmologists

Che Azemin, Mohd Zulfaezal and Mohd Tamrin, Mohd Izzuddin and Hilmi, Mohd Radzi and Mohd Kamal, Khairidzan (2023) Utlizing sgans for generating synthetic images of pterygium: training future optometrists and ophthalmologists. International Journal of Allied Health Sciences. p. 52.

[img] PDF (Article) - Published Version
Restricted to Registered users only

Download (44MB) | Request a copy


Pterygium, an ocular surface disorder, poses diagnostic challenges for optometrists and ophthalmologists. Wepropose using Style-Generative Adversarial Networks (SGANs) to generate synthetic pterygium images fortraining purposes. A training dataset of 68 pterygium images collected during routine clinical examinationswas used. Fréchet inception distance (FID) was employed to evaluate the similarity between the synthetic andoriginal images. FID analysis revealed that the synthetic images closely resemble the original pterygiumimages, suggesting a high degree of similarity. This indicates the potential of SGANs in generating realisticpterygium images. The successful generation of synthetic pterygium images using SGANs provides a valuabletool for training future optometrists and ophthalmologists in pterygium diagnosis and grading. By expandingthe availability of diverse pterygium images, trainees can enhance their skills and proficiency. The use ofsynthetic images overcomes limitations associated with obtaining a sufficient number of real pterygiumimages. Additionally, the availability of a large dataset of synthetic images enables the development ofadvanced machine learning algorithms and computer-assisted diagnostic tools, improving the accuracy andefficiency of pterygium grading. SGAN-generated images have the potential to standardize and control thetraining process, leading to improved patient care and management of pterygium

Item Type: Article (other)
Uncontrolled Keywords: Pterygium, Generative AI, Style-Generative Adversarial Network, Fréchet inception distance
Subjects: R Medicine > R Medicine (General)
T Technology > T Technology (General)
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button): Kulliyyah of Allied Health Sciences
Kulliyyah of Medicine
Kulliyyah of Information and Communication Technology
Kulliyyah of Information and Communication Technology
Depositing User: Dr. Mohd Zulfaezal Che Azemin
Date Deposited: 19 Dec 2023 09:58
Last Modified: 19 Dec 2023 14:12
URI: http://irep.iium.edu.my/id/eprint/108842

Actions (login required)

View Item View Item


Downloads per month over past year