{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T21:39:55Z","timestamp":1788817195084,"version":"build-2803163510"},"reference-count":30,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T00:00:00Z","timestamp":1683676800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Association for Research in Vision and Ophthalmology (ARVO) Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Detection of early clinical keratoconus (KCN) is a challenging task, even for expert clinicians. In this study, we propose a deep learning (DL) model to address this challenge. We first used Xception and InceptionResNetV2 DL architectures to extract features from three different corneal maps collected from 1371 eyes examined in an eye clinic in Egypt. We then fused features using Xception and InceptionResNetV2 to detect subclinical forms of KCN more accurately and robustly. We obtained an area under the receiver operating characteristic curves (AUC) of 0.99 and an accuracy range of 97\u2013100% to distinguish normal eyes from eyes with subclinical and established KCN. We further validated the model based on an independent dataset with 213 eyes examined in Iraq and obtained AUCs of 0.91\u20130.92 and an accuracy range of 88\u201392%. The proposed model is a step toward improving the detection of clinical and subclinical forms of KCN.<\/jats:p>","DOI":"10.3390\/diagnostics13101689","type":"journal-article","created":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T01:37:09Z","timestamp":1683769029000},"page":"1689","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["A Deep Feature Fusion of Improved Suspected Keratoconus Detection with Deep Learning"],"prefix":"10.3390","volume":"13","author":[{"given":"Ali H.","family":"Al-Timemy","sequence":"first","affiliation":[{"name":"Biomedical Engineering Department, Al-Khwarizmi College of Engineering, University of Baghdad, Baghdad 10011, Iraq"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7296-5413","authenticated-orcid":false,"given":"Laith","family":"Alzubaidi","sequence":"additional","affiliation":[{"name":"School of Mechanical, Medical, and Process Engineering, Queensland University of Technology, Brisbane, QLD 4000, Australia"},{"name":"ARC Industrial Transformation Training Centre\u2014Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zahraa M.","family":"Mosa","sequence":"additional","affiliation":[{"name":"Department of Physics, College of Science, Al-Nahrain University, Baghdad 64021, Iraq"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7429-3796","authenticated-orcid":false,"given":"Hazem","family":"Abdelmotaal","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Assiut University, Assiut 71526, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9812-0718","authenticated-orcid":false,"given":"Nebras H.","family":"Ghaeb","sequence":"additional","affiliation":[{"name":"Biomedical Engineering Department, Al-Khwarizmi College of Engineering, University of Baghdad, Baghdad 10011, Iraq"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7734-4854","authenticated-orcid":false,"given":"Alexandru","family":"Lavric","sequence":"additional","affiliation":[{"name":"Computers, Electronics and Automation Department, Stefan cel Mare University of Suceava, 720229 Suceava, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rossen M.","family":"Hazarbassanov","sequence":"additional","affiliation":[{"name":"Medical School, Universidade Anhembi Morumbi, S\u00e3o Paulo 03101-001, Brazil"},{"name":"Department of Ophthalmology and Visual Sciences, Paulista Medical School, Federal University of S\u00e3o Paulo, S\u00e3o Paulo 04021-001, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5331-4730","authenticated-orcid":false,"given":"Hidenori","family":"Takahashi","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Jichi Medical University, Tochigi 329-0431, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuantong","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Mechanical, Medical, and Process Engineering, Queensland University of Technology, Brisbane, QLD 4000, Australia"},{"name":"ARC Industrial Transformation Training Centre\u2014Joint Biomechanics, Queensland University of Technology, Brisbane, QLD 4000, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siamak","family":"Yousefi","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, University of Tennessee Health Science Center, Memphis, TN 38163, USA"},{"name":"Department of Genetics, Genomics, and Informatics, University of Tennessee Health Science Center, Memphis, TN 38163, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,5,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Yousefi, S., Yousefi, E., Takahashi, H., Hayashi, T., Tampo, H., Inoda, S., Arai, Y., and Asbell, P. (2018). Keratoconus severity identification using unsupervised machine learning. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0205998"},{"key":"ref_2","first-page":"1627","article-title":"Deep Transfer Learning for Improved Detection of Keratoconus using Corneal Topographic Maps","volume":"14","author":"Ghaeb","year":"2021","journal-title":"Cognit. Comput."},{"key":"ref_3","first-page":"2101-F0090","article-title":"A device-agnostic deep learning model for detecting keratoconus based on anterior elevation corneal maps","volume":"63","author":"Ghaeb","year":"2022","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"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., and Yousefi, S. (2022). A Hybrid Artificial Intelligence Model for Detecting Keratoconus. Appl. Sci., 12.","DOI":"10.3390\/app122412979"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"149113","DOI":"10.1109\/ACCESS.2020.3016060","article-title":"Detecting Keratoconus From Corneal Imaging Data Using Machine Learning","volume":"8","author":"Lavric","year":"2020","journal-title":"IEEE Access"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.1097\/01.opx.0000192350.01045.6f","article-title":"Automated decision tree classification of corneal shape","volume":"82","author":"Twa","year":"2005","journal-title":"Optom. Vis. Sci. Off. Publ. Am. Acad. Optom."},{"key":"ref_7","first-page":"1327","article-title":"Neural Network Classification of Corneal Topography Preliminary Demonstration","volume":"36","author":"Maeda","year":"1995","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_8","first-page":"4","article-title":"Detecting Keratoconus by Using SVM and Decision Tree Classifiers with the Aid of Image Processing","volume":"16","author":"Mosa","year":"2019","journal-title":"Baghdad Sci. J."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"724902","DOI":"10.3389\/fmed.2021.724902","article-title":"Diagnosability of keratoconus using deep learning with Placido disk-based corneal topography","volume":"8","author":"Kamiya","year":"2021","journal-title":"Front. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2554","DOI":"10.1177\/11206721221087566","article-title":"KEDOP: Keratoconus early detection of progression using tomography images","volume":"32","author":"Reddy","year":"2022","journal-title":"Eur. J. Ophthalmol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-023-00727-2","article-title":"A survey on deep learning tools dealing with data scarcity: Definitions, challenges, solutions, tips, and applications","volume":"10","author":"Alzubaidi","year":"2023","journal-title":"J. Big Data"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.inffus.2023.03.008","article-title":"A systematic review of trustworthy and explainable artificial intelligence in healthcare: Assessment of quality, bias risk, and data fusion","volume":"96","author":"Albahri","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1167\/tvst.9.2.53","article-title":"Keratoconus screening based on deep learning approach of corneal topography","volume":"9","author":"Kuo","year":"2020","journal-title":"Transl. Vis. Sci. Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1167\/tvst.9.13.30","article-title":"Classification of color-coded Scheimpflug camera corneal tomography images using deep learning","volume":"9","author":"Abdelmotaal","year":"2020","journal-title":"Transl. Vis. Sci. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.ajo.2020.06.005","article-title":"Corneal topography raw data classification using a convolutional neural network","volume":"219","author":"Bouvet","year":"2020","journal-title":"Am. J. Ophthalmol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3898","DOI":"10.1109\/JBHI.2021.3079430","article-title":"KerNet: A novel deep learning approach for keratoconus and sub-clinical keratoconus detection based on raw data of the Pentacam HR system","volume":"25","author":"Feng","year":"2021","journal-title":"IEEE J. Biomed. Heal. Informatics"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"6566","DOI":"10.1038\/s41598-023-33793-w","article-title":"Automated cornea diagnosis using deep convolutional neural networks based on cornea topography maps","volume":"13","author":"Fassbind","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1287","DOI":"10.21037\/atm-21-1772","article-title":"Prediction of keratoconus progression using deep learning of anterior segment optical coherence tomography maps","volume":"9","author":"Kamiya","year":"2021","journal-title":"Ann. Transl. Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e000824","DOI":"10.1136\/bmjophth-2021-000824","article-title":"Keratoconus detection of changes using deep learning of colour-coded maps","volume":"6","author":"Chen","year":"2021","journal-title":"BMJ Open Ophthalmol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"8162567","DOI":"10.1155\/2019\/8162567","article-title":"KeratoDetect: Keratoconus Detection Algorithm Using Convolutional Neural Networks","volume":"2019","author":"Lavric","year":"2019","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"e27363","DOI":"10.2196\/27363","article-title":"Machine Learning Algorithms to Detect Subclinical Keratoconus: Systematic Review","volume":"9","author":"Maile","year":"2021","journal-title":"JMIR Med. Inform."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1002\/ima.22717","article-title":"Automatic detection of keratoconus on Pentacam images using feature selection based on deep learning","volume":"32","author":"Tuncer","year":"2022","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1167\/tvst.10.14.16","article-title":"A Hybrid Deep Learning Construct for Detecting Keratoconus From Corneal Maps","volume":"10","author":"Mosa","year":"2021","journal-title":"Transl. Vis. Sci. Technol."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017, January 21\u201326). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A.A. (2017, January 4\u20139). Inception-v4, inception-resnet and the impact of residual connections on learning. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref_26","unstructured":"Sinjab, M.M. (2015). Step by Step\u00ae: Reading Pentacam Topography: Basics and Case Study Series, Jaypee Brothers Medical Publishers."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions","volume":"8","author":"Alzubaidi","year":"2021","journal-title":"J. Big Data"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_29","unstructured":"Mungoli, N. (2023). Adaptive Ensemble Learning: Boosting Model Performance through Intelligent Feature Fusion in Deep Neural Networks. arXiv."},{"key":"ref_30","first-page":"920","article-title":"Keratoviz-A multistage keratoconus severity analysis and visualization using deep learning and class activated maps","volume":"13","author":"Dhinakaran","year":"2023","journal-title":"Int. J. Electr. Comput. Eng."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/13\/10\/1689\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:32:16Z","timestamp":1760124736000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/13\/10\/1689"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,10]]},"references-count":30,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2023,5]]}},"alternative-id":["diagnostics13101689"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics13101689","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,10]]}}}