A Hybrid Artificial Intelligence Model for Detecting Keratoconus

Machine learning models have recently provided great promise in diagnosis of several ophthalmic disorders, including keratoconus (KCN). Keratoconus, a noninflammatory ectatic corneal disorder characterized by progressive cornea thinning, is challenging to detect as signs may be subtle. Several machi...

Full description

Saved in:
Bibliographic Details
Main Authors: Alyasseri Z.A.A., Al-Timemy A.H., Abasi A.K., Lavric A., Mohammed H.J., Takahashi H., Milhomens Filho J.A., Campos M., Hazarbassanov R.M., Yousefi S.
Other Authors: 57862594800
Format: Article
Published: MDPI 2023
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-26627
record_format dspace
spelling my.uniten.dspace-266272023-05-29T17:35:57Z A Hybrid Artificial Intelligence Model for Detecting Keratoconus Alyasseri Z.A.A. Al-Timemy A.H. Abasi A.K. Lavric A. Mohammed H.J. Takahashi H. Milhomens Filho J.A. Campos M. Hazarbassanov R.M. Yousefi S. 57862594800 35752795500 57208488241 55308321800 57202657688 57204099946 57221544458 35613019600 6508322463 36986998500 Machine learning models have recently provided great promise in diagnosis of several ophthalmic disorders, including keratoconus (KCN). Keratoconus, a noninflammatory ectatic corneal disorder characterized by progressive cornea thinning, is challenging to detect as signs may be subtle. Several machine learning models have been proposed to detect KCN, however most of the models are supervised and thus require large well-annotated data. This paper proposes a new unsupervised model to detect KCN, based on adapted flower pollination algorithm (FPA) and the k-means algorithm. We will evaluate the proposed models using corneal data collected from 5430 eyes at different stages of KCN severity (1520 healthy, 331 KCN1, 1319 KCN2, 1699 KCN3 and 579 KCN4) from Department of Ophthalmology and Visual Sciences, Paulista Medical School, Federal University of S�o Paulo, S�o Paulo in Brazil and 1531 eyes (Healthy = 400, KCN1 = 378, KCN2 = 285, KCN3 = 200, KCN4 = 88) from Department of Ophthalmology, Jichi Medical University, Tochigi in Japan and used several accuracy metrics including Precision, Recall, F-Score, and Purity. We compared the proposed method with three other standard unsupervised algorithms including k-means, Kmedoids, and Spectral cluster. Based on two independent datasets, the proposed model outperformed the other algorithms, and thus could provide improved identification of the corneal status of the patients with keratoconus. � 2022 by the authors. Final 2023-05-29T09:35:57Z 2023-05-29T09:35:57Z 2022 Article 10.3390/app122412979 2-s2.0-85144890277 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85144890277&doi=10.3390%2fapp122412979&partnerID=40&md5=18280399352ef2d0a43a7e503a3516d4 https://irepository.uniten.edu.my/handle/123456789/26627 12 24 12979 All Open Access, Gold, Green MDPI Scopus
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
description Machine learning models have recently provided great promise in diagnosis of several ophthalmic disorders, including keratoconus (KCN). Keratoconus, a noninflammatory ectatic corneal disorder characterized by progressive cornea thinning, is challenging to detect as signs may be subtle. Several machine learning models have been proposed to detect KCN, however most of the models are supervised and thus require large well-annotated data. This paper proposes a new unsupervised model to detect KCN, based on adapted flower pollination algorithm (FPA) and the k-means algorithm. We will evaluate the proposed models using corneal data collected from 5430 eyes at different stages of KCN severity (1520 healthy, 331 KCN1, 1319 KCN2, 1699 KCN3 and 579 KCN4) from Department of Ophthalmology and Visual Sciences, Paulista Medical School, Federal University of S�o Paulo, S�o Paulo in Brazil and 1531 eyes (Healthy = 400, KCN1 = 378, KCN2 = 285, KCN3 = 200, KCN4 = 88) from Department of Ophthalmology, Jichi Medical University, Tochigi in Japan and used several accuracy metrics including Precision, Recall, F-Score, and Purity. We compared the proposed method with three other standard unsupervised algorithms including k-means, Kmedoids, and Spectral cluster. Based on two independent datasets, the proposed model outperformed the other algorithms, and thus could provide improved identification of the corneal status of the patients with keratoconus. � 2022 by the authors.
author2 57862594800
author_facet 57862594800
Alyasseri Z.A.A.
Al-Timemy A.H.
Abasi A.K.
Lavric A.
Mohammed H.J.
Takahashi H.
Milhomens Filho J.A.
Campos M.
Hazarbassanov R.M.
Yousefi S.
format Article
author Alyasseri Z.A.A.
Al-Timemy A.H.
Abasi A.K.
Lavric A.
Mohammed H.J.
Takahashi H.
Milhomens Filho J.A.
Campos M.
Hazarbassanov R.M.
Yousefi S.
spellingShingle Alyasseri Z.A.A.
Al-Timemy A.H.
Abasi A.K.
Lavric A.
Mohammed H.J.
Takahashi H.
Milhomens Filho J.A.
Campos M.
Hazarbassanov R.M.
Yousefi S.
A Hybrid Artificial Intelligence Model for Detecting Keratoconus
author_sort Alyasseri Z.A.A.
title A Hybrid Artificial Intelligence Model for Detecting Keratoconus
title_short A Hybrid Artificial Intelligence Model for Detecting Keratoconus
title_full A Hybrid Artificial Intelligence Model for Detecting Keratoconus
title_fullStr A Hybrid Artificial Intelligence Model for Detecting Keratoconus
title_full_unstemmed A Hybrid Artificial Intelligence Model for Detecting Keratoconus
title_sort hybrid artificial intelligence model for detecting keratoconus
publisher MDPI
publishDate 2023
_version_ 1806424105695576064
score 13.209306